WO2024179595A1 - Obstacle recognition method and apparatus, electronic device, vehicle, and storage medium - Google Patents

Abstract

Disclosed are an obstacle recognition method and apparatus, an electronic device, a vehicle, a storage medium, a computer program, and a computer program product. The method comprises: acquiring original point cloud data; determining a first strong reflection point in the original point cloud data, wherein an intensity value of the first strong reflection point is greater than a first intensity threshold; performing dilation on the first strong reflection point to obtain a dilation area, and using coordinates of points in the dilation area to obtain a coordinate set of an obstacle suppression layer; using coordinates in the original point cloud data to obtain a coordinate set of an obstacle layer; and removing the area in the obstacle layer overlapping with the obstacle suppression layer to obtain an obstacle recognition result.

Description

Obstacle recognition method, device, electronic equipment, vehicle and storage medium

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims priority to Chinese patent application No. 202310201082.5 filed in China on March 2, 2023, the entire contents of which are incorporated herein by reference.

Technical Field

The present disclosure relates to the field of vehicle technology, and in particular to an obstacle recognition method, device, electronic equipment, vehicle, storage medium, computer program product, and computer program.

Background Art

In the scene where the vehicle is driving on the road, various overhead objects such as gantries, signboards, or detection equipment will be set above the road. On rainy days, the laser reflected by the overhead objects will be refracted and/or reflected by raindrops before it can be collected by the laser radar equipment. However, these point cloud points refracted and/or reflected by raindrops cannot accurately describe the position, distance and other information of the overhead objects. Usually, the gantry restored based on these point cloud points refracted and/or reflected by raindrops is much larger than the actual size of the gantry, and may even be misjudged as blocking the vehicle passage area and constituting an obstacle. According to the existing obstacle detection strategy, the driving safety perception module will prompt that there is an obstacle on the road and even control the vehicle to brake. But in fact, because the overhead objects such as the gantry are suspended and the height from the ground is very large, usually 5.0m-5.5m, it will not hinder the normal driving of the vehicle. That is, the existing obstacle detection strategy has a high probability of error when detecting obstacles on rainy days. How to improve the accuracy of obstacle detection in rainy days is an urgent problem to be solved.

Summary of the invention

In order to solve the above technical problems, the embodiments of the present disclosure provide an obstacle recognition method, an apparatus, an electronic device, a vehicle, a storage medium, a computer program product and a computer program.

In a first aspect, an embodiment of the present disclosure provides an obstacle recognition method, including:

Get the original point cloud data;

Determine a first strong reflection point in the original point cloud data, wherein an intensity value of the first strong reflection point is greater than a first intensity threshold;

Expanding the first strong reflection point to obtain an expanded area, and using the coordinates of each point in the expanded area to obtain a coordinate set of the obstacle suppression layer;

Using the coordinates in the original point cloud data, obtaining a coordinate set of the obstacle layer; and

After removing the area in the obstacle layer that overlaps with the obstacle suppression layer, the obstacle recognition result is obtained.

In a second aspect, an embodiment of the present disclosure provides an obstacle recognition device, including:

Acquisition module, used to obtain original point cloud data;

A first strong reflection point identification module, used to determine a first strong reflection point in the original point cloud data, wherein the intensity value of the first strong reflection point is greater than a first intensity threshold;

An expansion module, used to expand the first strong reflection point to obtain an expansion area, and obtain a coordinate set of the obstacle suppression layer using the coordinates of each point in the expansion area;

An obstacle identification module, used to obtain a coordinate set of an obstacle layer using the coordinates in the original point cloud data; and

The obstacle correction module is used to remove the area in the obstacle layer that overlaps with the obstacle suppression layer to obtain the obstacle recognition result.

In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor and a memory;

The processor is used to execute the steps of the method of any embodiment of the first aspect above by calling the program or instructions stored in the memory.

In a fourth aspect, an embodiment of the present disclosure provides a vehicle, comprising a device according to any embodiment of the second aspect or an electronic device according to any embodiment of the third aspect.

In a fifth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, which stores a program or instruction, and the program or instruction enables a computer to execute the steps of the method of any embodiment of the first aspect above.

In a sixth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, which implements the method of any embodiment of the above-mentioned first aspect when executed by a processor.

In a seventh aspect, an embodiment of the present disclosure provides a computer program, including a computer program code, which, when executed on a computer, enables the computer to execute the method of any one of the embodiments of the first aspect.

Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

The technical solution provided by the embodiment of the present disclosure determines a first strong reflection point by setting in the original point cloud data, wherein the intensity value of the first strong reflection point is greater than a first intensity threshold; the first strong reflection point is expanded to obtain an expanded area, and the coordinate set of the obstacle suppression layer is obtained by using the coordinates of each point in the expanded area; the coordinate set of the obstacle layer is obtained by using the coordinates in the original point cloud data; and the obstacle recognition result is obtained after removing the area in the obstacle layer that overlaps with the obstacle suppression layer. The essence of the technical solution is to use the first strong reflection point to predict the possible detection area of the overhead object that forms the first strong reflection point, and then remove the image in the possible detection area of the overhead object in the obstacle layer, so as to achieve the purpose of removing the overhead objects that do not constitute obstacles from the identified obstacles and the purpose of correcting the obstacle recognition result. The above method can improve the accuracy of obstacle detection in rainy days.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

FIG1 is a flow chart of an obstacle recognition method in an embodiment of the present disclosure;

FIG2 is a schematic diagram of the structure of an obstacle recognition device in an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of the structure of an electronic device in an embodiment of the present disclosure.

DETAILED DESCRIPTION

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and/or in parallel. In addition, the method embodiments may include additional steps and/or omit the steps shown. The scope of the present disclosure is not limited in this respect.

The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

FIG1 is a flow chart of an obstacle recognition method in an embodiment of the first aspect of the present disclosure. The method can be applied to a scenario in which an in-vehicle terminal performs obstacle recognition. It can be understood that the obstacle recognition method provided in the embodiment of the present disclosure can also be applied in other scenarios.

As shown in FIG. 1 , the method may specifically include steps S110 to S150 .

S110, obtaining original point cloud data.

Raw point cloud data refers to laser point cloud data directly collected by laser radar equipment. When a laser beam hits the surface of an object, the reflected laser will carry information such as the object's position and distance. Based on scanning along a certain trajectory using a laser beam, a large number of laser points can be obtained to form laser point cloud data.

In one embodiment, a laser radar device is installed on the vehicle. During the driving of the vehicle, the laser radar device can continuously emit laser to the surrounding environment of the vehicle and receive reflected laser to obtain original point cloud data.

S120. Determine a first strong reflection point in the original point cloud data, wherein an intensity value of the first strong reflection point is greater than a first intensity threshold.

In the disclosed embodiment, the first strong reflection point is considered to be a laser point received by the laser radar device after the laser is reflected by the overhead object and then refracted and/or reflected by raindrops. There may be multiple first strong reflection points.

Usually, the reflection intensity of the laser reflection in some areas of the overhead object is very high, and the intensity value of the laser point is still very large even after refraction and/or reflection by raindrops. The first intensity threshold is pre-set and is used to identify the first strong reflection point from the numerous point cloud points of the original point cloud data. The embodiment of the present disclosure does not limit the specific value of the first intensity threshold, and it can adaptively adjust the first intensity threshold according to the laser radar's own parameters, as long as the first strong reflection point can be identified. In some embodiments, the first intensity threshold is 100.

The obstacle identification method provided by the embodiment of the present disclosure can be applied to both sunny and rainy days. However, on sunny days, the probability of misidentifying an overhead object as an obstacle is very low. In some embodiments, on sunny days, the obstacle identification method provided by the embodiment of the present disclosure is not used to improve the efficiency of obstacle detection.

In practice, the probability of mistakenly identifying overhead objects such as gantries as obstacles is higher on rainy days than on sunny days. Therefore, the specific implementation method of setting this step includes: when rain is detected, determining the first strong reflection point in the original point cloud data. There are many ways to detect rain, and the present disclosure does not limit this. In some embodiments, by detecting the working status of the vehicle wiper, it is determined whether it is currently raining; or, the current weather information is obtained through the Internet; based on the current weather information, it is determined whether it is currently raining.

In one embodiment, the specific implementation method of this step may also include: determining the first point cloud data in the original point cloud data, wherein the height above the ground corresponding to the first point cloud data is greater than or equal to the first height threshold, and less than or equal to the second height threshold, and the first height threshold is less than the second height threshold; and determining the first strong reflection point in the first point cloud data. In practice, the installation height of overhead objects such as gantries is relatively uniform and is restricted by mandatory national standards, so the point cloud point distribution formed by the reflection of overhead objects such as gantries is also concentrated. The first height threshold and the second height threshold are used to narrow the screening range for screening out the first strong reflection point, thereby increasing the determination rate of the first strong reflection point. The present disclosure does not limit the specific values of the first height threshold and the second height threshold.

According to mandatory national standards, the height of overhead objects such as gantries on highways is 5.5m, and the height in cities is 5.0m. Accordingly, in some embodiments, the first height threshold is set to 2m and the second height threshold is set to 9m. Alternatively, the first height threshold is set to 2.5m and the second height threshold is set to 9m.

S130, dilate the first strong reflection point to obtain an expansion area, and use the coordinates of each point in the expansion area to obtain a coordinate set of the obstacle suppression layer.

The obstacle suppression layer is a reference layer. The obstacle suppression layer includes the obstacle suppression area, which is inferred based on the orientation, distance and other information of the object carried by the first strong reflection point. The obstacle suppression area indicates the possible detection area of the overhead object.

The coordinate set of the obstacle suppression layer may be, for example, a coordinate set obtained by summarizing the coordinates of each point in the expansion area.

The expansion area obtained by expanding the first strong reflection point refers to an area obtained by expanding outwards from the position corresponding to the first strong reflection point as a base point, and the area is the expansion area. Since the first strong reflection point is formed by an overhead object, the area obtained after the expansion of the first strong reflection point (i.e., the expansion area) can be regarded as an area where the overhead object may be detected.

There are many methods for implementing this step, and the present disclosure does not limit this. In one embodiment, the implementation method of this step includes: for each first strong reflection point, taking each first strong reflection point as the center point, based on the expansion radius, determining the expansion area corresponding to each first strong reflection point; and aggregating the coordinates of each point in the expansion area corresponding to multiple first strong reflection points to obtain a coordinate set of the obstacle suppression layer. Among them, the expansion radius is pre-set and used to determine the expansion area. The present disclosure does not limit the specific value of the expansion radius. In one embodiment, based on converting the laser point cloud data into a laser point cloud image, each point cloud point is converted into a pixel point, and the expansion radius can be 1 pixel, 3 pixels or 5 pixels in size, etc. Since the coordinates of each point cloud point (such as the coordinates in the laser point cloud image) are known, the expansion area obtained after the first strong reflection point is expanded, and the coordinates of each point in the expansion area can also be obtained, so the coordinates of each point in the expansion area corresponding to multiple first strong reflection points can be aggregated, and specifically, the union of the coordinates of each point in the expansion area corresponding to multiple first strong reflection points can be determined, and the union is used as the coordinate set of the obstacle suppression area.

It should be noted that, in some cases, the ultimately determined minimum distance between the obstacle suppression zone and the ground may be smaller than the first height threshold.

S140. Obtain a coordinate set of the obstacle layer using the coordinates in the original point cloud data.

In this step, the method of obtaining the coordinate set of the obstacle layer by using the coordinates in the original point cloud data is a prior art, that is, the original point cloud data contains coordinate information (such as the coordinates in the laser point cloud image). Since each point cloud point can appear in the obstacle layer as an obstacle, the coordinate set of the obstacle layer can be determined; in addition, filtering conditions can also be set, such as setting an intensity threshold or depth information to filter out specific points from the original point cloud as points in the obstacle layer, thereby obtaining the coordinate set of the obstacle layer. The specific details are not repeated in this disclosure.

In one embodiment, this step includes: removing the first strong reflection point from the original point cloud data; and obtaining a coordinate set of the obstacle layer based on the coordinates in the original point cloud data after removing the first strong reflection point. In order to reduce the interference caused by the first strong reflection point to the formation of the obstacle layer.

It should be noted that the obstacle layer includes obstacle images, wherein the obstacles included in the obstacle layer may represent objects that actually hinder the normal driving of the vehicle (ie, real obstacles), or may represent objects that do not hinder the normal driving of the vehicle but are misjudged as obstacles.

S150: After removing the area in the obstacle layer that overlaps with the obstacle suppression layer, an obstacle recognition result is obtained.

Since overhead objects are suspended in the air and at a great height from the ground, they do not hinder the normal driving of vehicles and do not constitute obstacles. The obstacle suppression layer includes the area where overhead objects may be detected (i.e., the obstacle suppression area). The obstacle images in the obstacle suppression area of the obstacle layer are removed, that is, the images representing the overhead objects are removed.

There are many methods for implementing this step, and the present disclosure does not limit this. In one embodiment, the implementation method of this step includes: unifying the points in the obstacle layer and the points in the obstacle suppression layer into the same coordinate system; and removing the points that exist in both the obstacle layer and the obstacle suppression layer from the obstacle layer to obtain the obstacle recognition result. The method of setting up such a method for removing the image representing the overhead object is relatively simple and easy to implement. It should be noted that since the first strong reflection point is extracted from the original point cloud data, the points in the obstacle suppression layer come from the original point cloud data, and the points in the obstacle layer also come from the original point cloud data, so that the coordinates of each point in the obstacle layer and the coordinates of each point in the obstacle suppression layer are in the same coordinate system. Even if the coordinate systems of the obstacle layer and the obstacle suppression layer are different, the points in the obstacle layer and the points in the obstacle suppression layer can be unified into the same coordinate system using the known coordinate system conversion relationship, and then the area in the obstacle layer that overlaps with the obstacle suppression layer can be obtained by judging whether there are points with the same coordinates. After obtaining the area in the obstacle layer that overlaps with the obstacle suppression layer, points that exist in both the obstacle layer and the obstacle suppression layer can be removed from the obstacle layer, and the points in the obstacle layer after removing the overlapping area can be used as the obstacle identification result. Alternatively, the existing method for generating obstacles can be used to generate corresponding obstacles using the points in the obstacle layer after removing the overlapping area, and the obstacles can be used as the obstacle identification result.

The above technical solution determines a first strong reflection point by setting it in the original point cloud data, wherein the intensity value of the first strong reflection point is greater than a first intensity threshold; the first strong reflection point is expanded to obtain an expanded area, and the coordinate set of the obstacle suppression layer is obtained by using the coordinates of each point in the expanded area; the coordinate set of the obstacle layer is obtained by using the coordinates in the original point cloud data; and the obstacle layer is removed after the area overlapping with the obstacle suppression layer, to obtain the obstacle recognition result. The essence of the technical solution is to use the first strong reflection point to predict the possible detection area of the overhead object that forms the first strong reflection point, and then remove the image in the possible detection area of the overhead object in the obstacle layer, so as to achieve the purpose of removing the overhead objects that do not constitute obstacles from the identified obstacles, and to achieve the purpose of correcting the obstacle recognition result. The above method can improve the accuracy of obstacle detection in rainy days.

Based on the above technical solutions, in some embodiments, step S130 may further include: when the number of first strong reflection points in the first point cloud data is greater than a first number threshold, dilating the first strong reflection points to obtain an expanded area. The first number threshold is preset and used to determine whether the first strong reflection point can be regarded as a noise point. The sound point appears randomly, and the probability of its appearance is low. Based on the fact that the number of the first strong reflection points in the first point cloud data is greater than the first number threshold, the first strong reflection point cannot be regarded as a noise point. Based on the fact that the number of the first strong reflection points in the first point cloud data is less than or equal to the first number threshold, the first strong reflection point is regarded as a noise point. The present disclosure does not limit the specific value of the first number threshold. In some embodiments, the first number threshold is 3 or 5, etc.

By setting the first strong reflection points to be expanded to obtain an expanded area when the number of the first strong reflection points in the first point cloud data is greater than a first number threshold, it is possible to avoid mistaking noise points for laser points formed by overhead objects, thereby further improving the accuracy of the identified obstacles.

In some embodiments, when the number of first strong reflection points in the first point cloud data is greater than a first number threshold, the first strong reflection points are expanded to obtain an expanded area, which may also include: in the original point cloud data, second point cloud data is determined, and the height above the ground corresponding to the second point cloud data is less than a third height threshold; in the second point cloud data, the number of second strong reflection points is determined; the intensity value of the second strong reflection point is greater than the set second intensity threshold; when the number of second strong reflection points in the second point cloud data is less than the second number threshold, and the number of first strong reflection points in the first point cloud data is greater than the first number threshold, the first strong reflection points are expanded to obtain an expanded area.

The third height threshold is pre-set, and the present disclosure does not limit the specific value of the third height threshold. In some embodiments, the third height threshold is less than or equal to the first height threshold. In some embodiments, the third height threshold is 2m.

The second intensity threshold is pre-set and is used to identify the second strong reflection point from the plurality of point cloud points of the second point cloud data. The present disclosure does not limit the specific value of the second intensity threshold, as long as the purpose of identifying the second strong reflection point can be achieved. The second intensity threshold may be the same as or different from the first intensity threshold in the foregoing text. In some embodiments, the second intensity threshold is 100.

The second number threshold is pre-set and is used to determine whether the second strong reflection point can be regarded as a noise point. Since noise points appear randomly and have a low probability of appearing, the second strong reflection point cannot be regarded as a noise point based on the number of second strong reflection points in the second point cloud data being greater than the second number threshold. The second strong reflection point is regarded as a noise point based on the number of second strong reflection points in the second point cloud data being less than or equal to the second number threshold. The present disclosure does not limit the specific value of the second number threshold. In some embodiments, the second number threshold is 3 or 5, etc.

In some embodiments, the second number threshold may be set to 0. That is, as long as a second strong reflection point is determined in the second point cloud data, the second strong reflection point is not processed as a noise point.

Those skilled in the art will appreciate that after the first strong reflection point is expanded, the resulting point cloud may expand in all directions, that is, the height of the lower edge of the expanded point cloud from the ground is very small, or even less than the height of the vehicle license plate from the ground under normal circumstances. In practice, objects such as vehicle license plates may also form strong reflection points. If there are other vehicles in front of the vehicle executing the obstacle recognition method provided by the embodiment of the present disclosure, the obstacle image corresponding to the vehicle in front may be located in the obstacle suppression area. When executing step S150, the obstacle image corresponding to the vehicle in front may be erased. However, in practice, the vehicle in front constitutes an obstacle. If the obstacle image corresponding to the vehicle in front is erased from the obstacle layer, it may cause the obstacle to be Obstacles missed detection.

If the number of second strong reflection points in the second point cloud data is less than the second number threshold, it usually means that there is no vehicle ahead that may constitute an obstacle. By setting the first strong reflection points to be expanded to obtain an obstacle suppression layer when the number of second strong reflection points in the second point cloud data is less than the second number threshold and the number of first strong reflection points in the first point cloud data is greater than the first number threshold, the obstacle suppression layer can be fully avoided from being mistakenly erased from the obstacle image corresponding to the vehicle ahead, so as to further improve the accuracy of obstacle detection in rainy days.

It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should know that the present disclosure is not limited by the order of the actions described, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

FIG2 is a schematic diagram of the structure of an obstacle recognition device in an embodiment of the second aspect of the present disclosure. The obstacle recognition device provided in the embodiment of the present disclosure can be configured in a vehicle-mounted terminal, and the obstacle recognition device specifically includes:

An acquisition module 210 is used to acquire original point cloud data;

A first strong reflection point identification module 220, configured to determine a first strong reflection point in the original point cloud data, wherein the intensity value of the first strong reflection point is greater than a first intensity threshold;

An expansion module 230, configured to expand the first strong reflection point to obtain an expansion area, and obtain a coordinate set of an obstacle suppression layer using the coordinates of each point in the expansion area;

The obstacle identification module 240 is used to obtain a coordinate set of an obstacle layer using the coordinates in the original point cloud data; and

The obstacle correction module 250 is used to remove the area in the obstacle layer that overlaps with the obstacle suppression layer to obtain an obstacle recognition result.

In some embodiments, the first strong reflection point identification module 220 is used to:

Determine first point cloud data in the original point cloud data, wherein the height above the ground corresponding to the first point cloud data is greater than or equal to a first height threshold and less than or equal to a second height threshold, and the first height threshold is less than the second height threshold; and

In the first point cloud data, a first strong reflection point is determined.

In some embodiments, the expansion module 230 is used to:

When the number of the first strong reflection points in the first point cloud data is greater than a first number threshold, the first strong reflection points are expanded to obtain an expanded area.

In some embodiments, the expansion module 230 is used to:

In the original point cloud data, second point cloud data is determined, and the height above the ground corresponding to the second point cloud data is less than The third height threshold;

In the second point cloud data, determining the number of second strong reflection points; the intensity value of the second strong reflection point is greater than a set second intensity threshold; and

When the number of second strong reflection points in the second point cloud data is less than a second number threshold, and the number of first strong reflection points in the first point cloud data is greater than a first number threshold, the first strong reflection points are expanded to obtain an expanded area.

In some embodiments, the expansion module 230 is used to:

For each of the first strong reflection points, taking each of the first strong reflection points as a center point and based on an expansion radius, determining an expansion area corresponding to each of the first strong reflection points; and

The expansion areas corresponding to the plurality of the first strong reflection points are aggregated to obtain an obstacle suppression layer.

In some embodiments, the obstacle identification module 240 is used to:

Eliminating the first strong reflection point from the original point cloud data; and

Based on the coordinates in the original point cloud data after removing the first strong reflection point, a coordinate set of the obstacle layer is obtained.

In some embodiments, the obstacle correction module 250 is used to:

Unifying the points in the obstacle layer and the points in the obstacle suppression layer into the same coordinate system;

Points existing in both the obstacle layer and the obstacle suppression layer are removed from the obstacle layer to obtain an obstacle recognition result.

The obstacle recognition device provided in the embodiment of the present disclosure can execute the steps executed by the vehicle-mounted terminal in the obstacle recognition method provided in the method embodiment of the present disclosure, and the execution steps and beneficial effects are no longer repeated here.

FIG3 is a schematic diagram of the structure of an electronic device in an embodiment of the third aspect of the present disclosure. Specific reference is made to FIG3 below, which shows a schematic diagram of the structure of an electronic device 500 suitable for implementing the embodiment of the present disclosure. The electronic device 500 in the embodiment of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), wearable electronic devices, etc., and fixed terminals such as digital TVs, desktop computers, smart home devices, etc. The electronic device shown in FIG3 is merely an example and should not impose any limitations on the functions and scope of use of the embodiments of the present disclosure.

As shown in FIG3 , the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 to a random access memory (RAM) 503 to implement the obstacle recognition method of the embodiment described in the present disclosure. Various programs and data required for the operation of the electronic device 500 are also stored in the RAM 503. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input/output (I/O) interface 505 Also connected to bus 504 .

Typically, the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 508 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 509. The communication devices 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although FIG. 3 shows an electronic device 500 with various devices, it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have alternatively.

In some embodiments, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart, thereby implementing the obstacle identification method as described above. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

In some embodiments, the client and server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network). and any currently known or future developed networks.

The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device:

Get the original point cloud data;

Determine a first strong reflection point in the original point cloud data; the intensity value of the first strong reflection point is greater than a first intensity threshold;

Expanding the first strong reflection point to obtain an expanded area, and using the coordinates of each point in the expanded area to obtain a coordinate set of the obstacle suppression layer;

Using the coordinates in the original point cloud data, a coordinate set of the obstacle layer is obtained;

After removing the area in the obstacle layer that overlaps with the obstacle suppression layer, the obstacle recognition result is obtained.

In some embodiments, when the above one or more programs are executed by the electronic device, the electronic device may also execute other steps described in the above embodiments.

Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and/or flow chart, and the combination of the square boxes in the block diagram and/or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

The units involved in the embodiments of the present disclosure may be implemented by software or by hardware. The name of a unit does not, in some cases, limit the unit itself.

The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

A third aspect of the present disclosure provides an electronic device, including:

one or more processors; and

A memory for storing one or more programs;

When the one or more programs are executed by the one or more processors, the one or more processors implement the obstacle recognition method as in any embodiment of the first aspect of the present disclosure.

The fourth aspect embodiment of the present disclosure further provides a vehicle, which includes the obstacle recognition device of any embodiment of the second aspect of the present disclosure or the electronic device of any embodiment of the third aspect of the present disclosure.

An embodiment of the fifth aspect of the present disclosure provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the obstacle recognition method of any embodiment of the first aspect of the present disclosure is implemented.

Since the vehicle provided by the embodiment of the present disclosure includes the obstacle recognition device or electronic device provided by the present disclosure, it has the same or corresponding beneficial effects as the obstacle recognition device or electronic device included therein, which will not be described in detail here.

A sixth aspect of the present disclosure provides a computer program product, including a computer program, which implements the method of any one of the embodiments of the first aspect when executed by a processor.

An embodiment of a seventh aspect of the present disclosure provides a computer program, including computer program code. When the computer program code is run on a computer, the computer executes the method of any embodiment of the first aspect.

It should be noted that the explanations and descriptions of the obstacle identification method and apparatus in the aforementioned embodiments are also applicable to the computer-readable storage medium, vehicle, computer program product and computer program in the embodiments of the present disclosure, and will not be repeated here.

All embodiments of the present disclosure may be implemented individually or in combination with other embodiments, and are all deemed to be within the protection scope required by the present disclosure.

The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other.

In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

Although the subject matter has been described in language specific to structural features and/or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims (13)

An obstacle recognition method, comprising: Get the original point cloud data; Determine a first strong reflection point in the original point cloud data, wherein an intensity value of the first strong reflection point is greater than a first intensity threshold; Expanding the first strong reflection point to obtain an expanded area, and using the coordinates of each point in the expanded area to obtain a coordinate set of the obstacle suppression layer; Using the coordinates in the original point cloud data, obtaining a coordinate set of the obstacle layer; and After removing the area in the obstacle layer that overlaps with the obstacle suppression layer, the obstacle recognition result is obtained. The method according to claim 1, wherein determining a first strong reflection point in the original point cloud data comprises: Determine first point cloud data in the original point cloud data, wherein the height above the ground corresponding to the first point cloud data is greater than or equal to a first height threshold and less than or equal to a second height threshold, and the first height threshold is less than the second height threshold; and In the first point cloud data, a first strong reflection point is determined. The method according to claim 2, wherein the step of expanding the first strong reflection point to obtain the expanded area comprises: When the number of the first strong reflection points in the first point cloud data is greater than a first number threshold, the first strong reflection points are expanded to obtain an expanded area. The method according to claim 3, wherein when the number of the first strong reflection points in the first point cloud data is greater than a first number threshold, dilating the first strong reflection points to obtain a dilated area comprises: Determine second point cloud data in the original point cloud data, wherein the height above the ground corresponding to the second point cloud data is less than a third height threshold; In the second point cloud data, determining the number of second strong reflection points; the intensity value of the second strong reflection point is greater than a set second intensity threshold; and When the number of second strong reflection points in the second point cloud data is less than a second number threshold and the number of first strong reflection points in the first point cloud data is greater than a first number threshold, the first strong reflection points are expanded to obtain an expanded area. The method according to any one of claims 1 to 4, wherein the step of expanding the first strong reflection point to obtain the expanded area comprises: For each of the first strong reflection points, taking each of the first strong reflection points as the center point, based on the expansion radius, A dilation area corresponding to each of the first strong reflection points is determined. The method according to any one of claims 1 to 5, wherein the step of obtaining a coordinate set of an obstacle layer by using the coordinates in the original point cloud data comprises: Eliminating the first strong reflection point from the original point cloud data; and Based on the coordinates in the original point cloud data after removing the first strong reflection point, a coordinate set of the obstacle layer is obtained. The method according to any one of claims 1 to 6, wherein the obstacle recognition result is obtained after removing the area in the obstacle layer that overlaps with the obstacle suppression layer, comprising: unifying the points in the obstacle layer and the points in the obstacle suppression layer into the same coordinate system; and Points existing in both the obstacle layer and the obstacle suppression layer are removed from the obstacle layer to obtain an obstacle recognition result. An obstacle recognition device, comprising: Acquisition module, used to obtain original point cloud data; A first strong reflection point identification module, used to determine a first strong reflection point in the original point cloud data, wherein the intensity value of the first strong reflection point is greater than a first intensity threshold; An expansion module, used to expand the first strong reflection point to obtain an expansion area, and obtain a coordinate set of the obstacle suppression layer using the coordinates of each point in the expansion area; An obstacle identification module, used to obtain a coordinate set of an obstacle layer using the coordinates in the original point cloud data; and The obstacle correction module is used to remove the area in the obstacle layer that overlaps with the obstacle suppression layer to obtain the obstacle recognition result. An electronic device, comprising: a processor and a memory; The processor is configured to execute the steps of the method according to any one of claims 1 to 7 by calling the program or instruction stored in the memory. A vehicle comprises the obstacle recognition device as claimed in claim 8 or the electronic device as claimed in claim 9. A computer-readable storage medium, wherein the computer-readable storage medium stores a program or instruction, wherein the program or instruction enables a computer to execute the steps of the method according to any one of claims 1 to 7. A computer program product comprises a computer program, wherein when the computer program is executed by a processor, the computer program implements the method according to any one of claims 1 to 7. A computer program, comprising a computer program code, which enables the computer to perform the method according to any one of claims 1 to 7 when the computer program code is run on a computer.