CN112991179B - Method, apparatus, device and storage medium for outputting information - Google Patents

Abstract

The present disclosure provides methods, devices, devices and storage media for outputting information, which relate to the field of artificial intelligence, specifically the technical fields of computer vision and deep learning, and can be used in image splicing scenarios. The specific implementation plan is: obtain the image sequence corresponding to the target image and the simulated homography matrix sequence corresponding to the image sequence; use the target feature point recognition algorithm to determine the feature points of each image frame in the image sequence, and based on the feature points of each image frame, Determine the estimated homography matrix sequence between any two adjacent image frames in the image sequence; determine the evaluation information for the target feature point recognition algorithm according to the simulated homography matrix sequence and the estimated homography matrix sequence; output the evaluation information. This implementation can evaluate the feature point recognition algorithm, thereby providing a basis for optimizing the feature point recognition algorithm and providing a basis for image splicing.

Description

Method, device, device and storage medium for outputting information

technical field

The present disclosure relates to the field of artificial intelligence, specifically to the technical fields of computer vision and deep learning, and in particular to methods, devices, equipment and storage media for outputting information, which can be used in image stitching scenarios.

Background technique

Image mosaic (image mosaic) is an increasingly popular research field, which has become a hot topic in photogrammetry, computer vision, image processing and computer graphics research. In the process of image stitching, the feature points in the image can be identified first. But the performance of the feature point recognition algorithm directly affects the effect of image stitching.

Contents of the invention

Provided are a method, device, device and storage medium for outputting information.

According to the first aspect, a method for outputting information is provided, including: acquiring an image sequence corresponding to a target image and a simulated homography matrix sequence corresponding to the image sequence; using a target feature point recognition algorithm to determine each image frame in the image sequence , and based on the feature points of each image frame, determine the estimated homography matrix sequence between any two adjacent image frames in the image sequence; according to the simulated homography matrix sequence and the estimated homography matrix sequence, determine the target feature point Identify the evaluation information of the algorithm; output the evaluation information.

According to a second aspect, there is provided an apparatus for outputting information, comprising: an acquisition unit configured to acquire an image sequence corresponding to a target image and a simulated homography matrix sequence corresponding to the image sequence; an estimation unit configured to utilize The target feature point recognition algorithm determines the feature points of each image frame in the image sequence, and based on the feature points of each image frame, determines the estimated homography matrix sequence between any two adjacent image frames in the image sequence; the generating unit is configured as According to the simulated homography matrix sequence and the estimated homography matrix sequence, the evaluation information for the target feature point recognition algorithm is determined; the output unit is configured to output the evaluation information.

According to a third aspect, there is provided an electronic device for outputting information, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor , the above instructions are executed by at least one processor, so that the at least one processor can execute the method as described in the first aspect.

According to a fourth aspect, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the method described in the first aspect.

According to a fifth aspect, a computer program product includes a computer program, and when executed by a processor, the computer program implements the method as described in the first aspect.

According to the technology of the present disclosure, the feature point recognition algorithm can be evaluated, thereby providing a basis for optimizing the feature point recognition algorithm and providing a basis for image splicing.

It should be understood that what is described in this section is not intended to identify key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will be readily understood through the following description.

Description of drawings

The accompanying drawings are used to better understand the present solution, and do not constitute a limitation to the present disclosure. in:

FIG. 1 is a flowchart of one embodiment of a method for outputting information according to the present disclosure;

Fig. 2 is a schematic diagram of an application scenario of a method for outputting information according to the present disclosure;

FIG. 3 is a flowchart of another embodiment of a method for outputting information according to the present disclosure;

Fig. 4 is a schematic structural diagram of an embodiment of an apparatus for outputting information according to the present disclosure;

FIG. 5 is a block diagram of an electronic device for implementing a method for outputting information of an embodiment of the present disclosure.

Detailed ways

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

It should be noted that, in the case of no conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and embodiments.

Continuing to refer to FIG. 1 , a flow 100 of an embodiment of a method for outputting information according to the present disclosure is shown. The method for outputting information in this embodiment includes the following steps:

Step 101, acquiring an image sequence corresponding to a target image and a simulated homography matrix sequence corresponding to the image sequence.

In this embodiment, the execution subject may acquire the image sequence corresponding to the target image. Here, the target image may be any wide-angle image or panoramic image, or an image whose pixel width is greater than a certain value. The image sequence may be an image sequence obtained by simulating continuous scanning of the target image, or an image sequence obtained by dividing the image sequence. An overlapping area may be included between two adjacent image frames in the image sequence.

The execution subject can also obtain a simulated homography matrix sequence corresponding to the image sequence. Here, the simulated homography matrix sequence can be determined by matching after extracting the feature points of each image frame in the image sequence through a feature point recognition algorithm with better performance. The aforementioned feature point recognition algorithm with better performance may be a pre-trained convolutional neural network. Alternatively, the above-mentioned target image may include marking points, and the divided image sequence may include the above-mentioned marking points, and the simulated homography matrix sequence is determined through the positions of the marking points in two adjacent image frames.

The homography matrix can also be called the homography matrix, which is used to describe the position mapping relationship between the object in the world coordinate system and the pixel coordinate system.

Step 102, using the target feature point recognition algorithm to determine the feature points of each image frame in the image sequence, and based on the feature points of each image frame, determine the estimated homography matrix sequence between any two adjacent image frames in the image sequence.

After the execution subject acquires the image sequence, it can use the target feature point recognition algorithm to perform feature point recognition on each image frame in the image sequence to obtain the feature point of each image frame. The target feature point recognition algorithm can be a variety of algorithms that can extract features, such as SIFT (Scale-invariant feature transform, scale-invariant feature transformation), SURF (Speeded Up Robust Features, accelerated robust features), ORB (Oriented FAST and RotatedBRIEF ), feature point recognition based on deep learning (convolutional neural network) and other algorithms. After the feature points of each image frame are obtained, the feature points of adjacent image frames can be matched. And use the matched feature points to determine the homography matrix between two adjacent image frames. According to the position of the image frame corresponding to the homography matrix in the image sequence, the homography matrices are sorted to obtain the homography matrix sequence, which is recorded as the estimated homography matrix sequence.

Step 103: Determine the evaluation information for the target feature point recognition algorithm according to the simulated homography matrix sequence and the estimated homography matrix sequence.

Since each homography in the simulated homography sequence has high accuracy, it can be used as a standard to evaluate the estimated homography sequence. It can be understood that if the estimated homography matrix sequence is more similar to the simulated homography matrix sequence, the performance of the target feature point recognition algorithm is better. In this embodiment, the execution subject can calculate the similarity of the simulated homography matrix sequence and the estimated homography matrix sequence, and generate evaluation information according to the above similarity. Alternatively, the execution subject may separately calculate the similarity between each homography matrix in the simulated homography matrix sequence and the corresponding homography matrix in the estimated homography matrix sequence to obtain a similarity sequence. And generate evaluation information based on the above similarity sequence. Alternatively, the execution subject may also directly output the above simulated homography matrix sequence and estimated homography matrix sequence as evaluation information. The evaluation information may include the above two homography matrix sequences and the corresponding similarity or similarity sequences, and may also include conclusions generated based on the above similarity or similarity sequences, such as "the performance of the current feature point recognition algorithm is better", etc. .

In this embodiment, algorithms such as RANSAC (RANdom SAmple Consensus, random sampling consensus) and LMeDS (least median method) may be used for calculation of the homography matrix.

Step 104, output evaluation information.

The executive body can also output the evaluation information for technicians to view, and the technicians can optimize the target feature point recognition algorithm according to the evaluation information, or select an appropriate feature point recognition algorithm for data processing, etc.

Continue referring to FIG. 2 , which shows a schematic diagram of an application scenario of the method for outputting information according to the present disclosure. In the application scenario in FIG. 2 , the terminal device 201 may divide the target image to obtain an image sequence. There are overlapping regions between adjacent image frames in the image sequence. By using the feature point recognition algorithm with better performance, the feature point recognition is carried out for each image frame in the image sequence, and the recognized feature points are matched. The homography matrix between every two adjacent image frames is calculated based on the matched feature points, and the obtained homography matrix sequence is recorded as the simulated homography matrix sequence. Then, the target feature point recognition algorithm is used to identify the feature points in each image frame for matching. The homography matrix between every two adjacent image frames is calculated based on the matched feature points, and the obtained homography matrix sequence is recorded as the estimated homography matrix sequence. Calculate the similarity between the simulated homography matrix sequence and the estimated homography matrix sequence, and generate evaluation information for the target feature point recognition algorithm based on the similarity. And the evaluation information is displayed, and technicians can optimize the target feature point recognition algorithm based on the evaluation information.

The method for outputting information provided by the above-mentioned embodiments of the present disclosure can use the image sequence corresponding to the target image and the corresponding simulated homography matrix sequence to compare with the estimated homography matrix sequence obtained based on the target feature point recognition algorithm, thereby realizing Evaluate the target feature point recognition algorithm to provide the algorithm basis for image stitching.

Continue referring to FIG. 3 , which shows a flow 300 of another embodiment of the method for outputting information according to the present disclosure. The method of this embodiment may include the following steps:

Step 301, according to the simulated camera and the target image, determine the image sequence corresponding to the target image.

In this embodiment, the execution subject may use the analog camera to continuously scan the target image to obtain an image sequence corresponding to the target image. During scanning, the execution subject can control the simulated camera to simulate scan the target image at multiple preset positions to obtain multiple image frames.

In some optional implementations of this embodiment, the execution subject can obtain the image sequence corresponding to the target image through the following steps not shown in FIG. The image is simulated and scanned continuously to obtain an image sequence.

In this implementation manner, the execution subject may use the simulated camera to move along the preset route with a preset posture to perform simulated continuous scanning of the target image to obtain an image sequence. For example, the simulated camera may be at a height h above the target image, and the angle between the simulated camera and the target image is θ. The preset route may be a line parallel to the center line of the target image, so that the contents of the target image can be photographed to the greatest extent. Specifically, when the analog camera continuously scans the target image, it can capture the target image at a preset frequency to obtain an image sequence.

Assuming that the angle between the virtual camera along the scanning direction x and the paper surface is θ, and the angle of random shaking is α, (the y and z directions are the same), then 4 points on the camera plane under different attitudes can be determined. With 4 points as the starting point and 4 vertices of any fixed rectangular frame as the target point, the real homography matrix sequence can be obtained.

Step 302, determining a simulated homography matrix sequence between any two adjacent image frames in the image sequence.

After the execution subject obtains the image sequence, it can determine the homography matrix between any two adjacent image frames in the image sequence. The obtained homography matrices are sorted to obtain a sequence of homography matrices, which is denoted as a sequence of simulated homography matrices. In this embodiment, the target image may include marking points, and adjacent image frames may be matched using the marking points, so as to calculate a homography matrix between the adjacent image frames.

In some optional implementation manners of this embodiment, the execution subject may also determine the simulated homography matrix sequence according to the pose transformation of the simulated camera during continuous scanning.

In this embodiment, since the camera is simulated, the pose of the camera can be preset. That is, when the simulated camera moves along the preset route with the preset pose, the pose transformation of the simulated camera can also be calculated. The attitude above may include position and pitch angle. The execution subject can determine the homography matrix between adjacent image frames according to the pose of the simulated camera. And according to the positions of the image frames corresponding to each homography matrix in the image sequence, a homography matrix sequence is obtained, which is denoted as a simulated homography matrix sequence.

In some optional implementation manners of this embodiment, the execution subject may firstly determine the camera pose sequence according to the pose transformation of the simulated camera during the continuous scanning process. Then, based on the sequence of camera poses, the sequence of simulated homography matrices is determined.

In this implementation manner, the execution subject may first determine the camera pose corresponding to each image frame in the image sequence according to the pose of the simulated camera during continuous scanning of the target image. In this way, the camera pose sequence corresponding to the image sequence can be obtained. Then, corresponding to each camera pose, a homography matrix is determined to obtain a sequence of simulated homography matrices.

Step 303, using the target feature point recognition algorithm to determine the feature points of each image frame in the image sequence, and based on the feature points of each image frame, determine the estimated homography matrix sequence between any two adjacent image frames in the image sequence.

Step 304, determining the distance between the simulated homography matrix sequence and the estimated homography matrix sequence; according to the distance, determining the evaluation information for the target feature point recognition algorithm.

In this embodiment, the execution subject can calculate the simulated homography matrix sequence and estimate the distance between the homography matrix sequences. Specifically, the execution subject may separately calculate the distance between each homography matrix in the simulated homography matrix sequence and the corresponding homography matrix in the estimated homography matrix sequence, and then calculate the average value of each distance. The above average value is used as the similarity value of the simulated homography matrix sequence and the estimated homography matrix sequence. According to the above distance, the evaluation information for the target feature point recognition algorithm is determined. Specifically, the above-mentioned evaluation information may include the above-mentioned distance value, and may also include conclusion information corresponding to the above-mentioned distance value.

Step 305, output evaluation information.

In the method for outputting information provided by the above embodiments of the present disclosure, a simulated scan is performed on the target image to generate a sequence of simulated pictures, which avoids the process of collecting and labeling real pictures, and can generate images arbitrarily as long as there are original images. And based on the pose transformation of the simulated camera, the homography matrix sequence corresponding to the image sequence is calculated. It avoids the problem that it is difficult to estimate the homography matrix accurately based on the real scan picture sequence, and can cover all real poses and their sequence combinations by artificially setting the pose of the simulated camera. The target feature point matching algorithm is evaluated directly based on the homography matrix sequence and the distance mean between the homography matrix estimation sequences, which avoids the defects of the reprojection error method on projective transformation.

Further referring to FIG. 4 , as an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a device for outputting information. The device embodiment corresponds to the method embodiment shown in FIG. 1 . The device can be specifically applied to various electronic devices.

As shown in FIG. 4 , the apparatus 400 for outputting information in this embodiment includes: an acquiring unit 401 , an estimating unit 402 , a generating unit 403 and an output unit 404 .

The acquiring unit 401 is configured to acquire an image sequence corresponding to the target image and a simulated homography matrix sequence corresponding to the image sequence.

The estimation unit 402 is configured to use the target feature point recognition algorithm to determine the feature points of each image frame in the image sequence, and based on the feature points of each image frame, determine the estimated homography matrix between any two adjacent image frames in the image sequence sequence.

The generation unit 403 is configured to determine evaluation information for the target feature point recognition algorithm according to the simulated homography matrix sequence and the estimated homography matrix sequence;

The output unit 404 is configured to output evaluation information.

In some optional implementations of this embodiment, the acquisition unit 401 may be further configured to: determine the image sequence corresponding to the target image according to the simulated camera and the target image; determine the image sequence between any two adjacent image frames in the image sequence homography matrix, get the simulated homography matrix sequence.

In some optional implementation manners of this embodiment, the acquisition unit 401 may be further configured to: use a simulated camera to move along a preset route with a preset posture, and perform simulated continuous scanning on the target image to obtain an image sequence.

In some optional implementation manners of this embodiment, the acquiring unit 401 may be further configured to: determine a simulated homography matrix sequence according to pose transformation of the simulated camera during continuous scanning.

In some optional implementations of this embodiment, the acquisition unit 401 may be further configured to: determine the camera pose sequence according to the pose transformation of the simulated camera in the continuous scanning process; determine the simulated homography matrix sequence according to the camera pose sequence .

In some optional implementations of this embodiment, the generation unit 403 may be further configured to: determine the simulated homography matrix sequence and estimate the distance between the homography matrix sequences; according to the distance, determine the target feature point recognition algorithm Evaluation information.

It should be understood that the units 401 to 405 recorded in the apparatus 400 for outputting information respectively correspond to the steps in the method described with reference to FIG. 1 . Therefore, the operations and features described above for the method for outputting information are also applicable to the device 400 and the units contained therein, and will not be repeated here.

In the technical solution of the present disclosure, the acquisition, storage and application of the user's personal information involved are in compliance with relevant laws and regulations, and do not violate public order and good customs.

According to the embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

FIG. 5 shows a block diagram of an electronic device 500 performing a method for outputting information according to an embodiment of the present disclosure. Electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in FIG. 5 , an electronic device 500 includes a processor 501 that can execute according to a computer program stored in a read-only memory (ROM) 502 or loaded from a memory 508 into a random access memory (RAM) 503. Various appropriate actions and treatments. In the RAM 503, various programs and data necessary for the operation of the electronic device 500 can also be stored. The processor 501 , ROM 502 , and RAM 503 are connected to each other through a bus 504 . An I/O interface (input/output interface) 505 is also connected to the bus 504 .

Multiple components in the electronic device 500 are connected to the I/O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a memory 508, such as a magnetic disk, an optical disk, etc. ; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 509 allows the electronic device 500 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.

Processor 501 may be various general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 501 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various dedicated artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 501 executes various methods and processes described above, such as a method for outputting information. For example, in some embodiments, the method for outputting information may be implemented as a computer software program tangibly embodied on a machine-readable storage medium, such as memory 508 . In some embodiments, part or all of the computer program may be loaded and/or installed on the electronic device 500 via the ROM 502 and/or the communication unit 509 . When the computer program is loaded into RAM 503 and executed by processor 501, one or more steps of the method for outputting information described above may be performed. Alternatively, in other embodiments, the processor 501 may be configured in any other suitable manner (for example, by means of firmware) to execute the method for outputting information.

Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips Implemented in a system of systems (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpreted on a programmable system including at least one programmable processor, the programmable processor Can be special-purpose or general-purpose programmable processor, can receive data and instruction from storage system, at least one input device, and at least one output device, and transmit data and instruction to this storage system, this at least one input device, and this at least one output device an output device.

Program codes for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. The above program code can be packaged into a computer program product. These program codes or computer program products may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, so that the program codes, when executed by the processor 501, make the flow diagrams and/or block diagrams specified The function/operation is implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

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

To provide for interaction with the user, the systems and techniques described herein can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user. ); and a keyboard and pointing device (eg, a mouse or a trackball) through which a user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and can be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.

The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN) and the Internet.

A computer system may include clients and servers. Clients and servers are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the problem of traditional physical host and VPS service ("Virtual Private Server", or "VPS") Among them, there are defects such as difficult management and weak business scalability. The server can also be a server of a distributed system, or a server combined with a blockchain.

It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, each step described in the present disclosure may be executed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution of the present disclosure can be achieved, no limitation is imposed herein.

The specific implementation manners described above do not limit the protection scope of the present disclosure. It should be apparent to those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present disclosure shall fall within the protection scope of the present disclosure.

Claims (8)

1. A method for outputting information, comprising: Use the simulated camera to move along the preset route with a preset attitude, and simulate and continuously scan the target image to obtain an image sequence; Determining the homography matrix between any two adjacent image frames in the image sequence to obtain a simulated homography matrix sequence; Using the target feature point recognition algorithm to determine the feature points of each image frame in the image sequence, and based on the feature points of each image frame, determine the estimated homography matrix sequence between any two adjacent image frames in the image sequence; determining a distance between the sequence of simulated homography matrices and the sequence of estimated homography matrices; determining evaluation information for the target feature point recognition algorithm according to the distance; The evaluation information is output. 2. The method according to claim 1, wherein the determination of the homography matrix between any two adjacent image frames in the image sequence obtains a simulated homography matrix sequence, comprising: The simulated homography matrix sequence is determined according to the pose transformation of the simulated camera during continuous scanning. 3. The method according to claim 2, wherein, according to the attitude transformation of the simulated camera in the continuous scanning process, determining the simulated homography matrix sequence comprises: Determine the camera pose sequence according to the pose transformation of the simulated camera during the continuous scanning process; According to the camera pose sequence, the simulated homography matrix sequence is determined. 4. A device for outputting information, comprising: The acquiring unit is configured to use the simulated camera to move along a preset route with a preset posture, simulate and continuously scan the target image to obtain an image sequence; and determine a homography matrix between any two adjacent image frames in the image sequence, Obtain the simulated homography matrix sequence; The estimation unit is configured to determine the feature points of each image frame in the image sequence by using the target feature point recognition algorithm, and determine an estimated value between any two adjacent image frames in the image sequence based on the feature points of each image frame sequence of homography matrices; a generating unit configured to determine a distance between the simulated homography matrix sequence and the estimated homography matrix sequence; and determine evaluation information for the target feature point recognition algorithm according to the distance; an output unit configured to output the evaluation information. 5. The device according to claim 4, wherein the acquiring unit is further configured to: The simulated homography matrix sequence is determined according to the pose transformation of the simulated camera during continuous scanning. 6. The device according to claim 5, wherein the acquiring unit is further configured to: Determine the camera pose sequence according to the pose transformation of the simulated camera during the continuous scanning process; According to the camera pose sequence, the simulated homography matrix sequence is determined. 7. An electronic device for performing a method for outputting information, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can perform any one of claims 1-3. Methods. 8. A non-transitory computer-readable storage medium storing computer instructions, the computer instructions being used to cause the computer to execute the method according to any one of claims 1-3.

Images