JP2000067368A - Road monitoring system - Google Patents

Abstract

(57) [Problem] To detect that a vehicle is moving on a scanning line when a vehicle is several tens of meters away when an image sensor such as an ITV widens the field of view to widen a road monitoring area. This makes it difficult to accurately measure the amount of movement such as distance and speed. Conversely, if the field of view is narrowed in order to accurately measure the amount of movement of the vehicle, the road monitoring area is limited, and as a result, the road monitoring area is configured by several image sensors and several image processing devices. There was a problem that the cost of the monitoring system would be high. SOLUTION: By utilizing the features of both a radar sensor and an image sensor, by compensating for the weaknesses of the respective sensors, the accuracy of event determination is improved, the event is automatically detected, and information is immediately notified to a following vehicle. .

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention is applied to a system for traffic control, and particularly in a monitoring area on a road, such as a traffic condition such as a traffic jam and an emergency stop due to an accident or carelessness of a driver. The present invention relates to a road monitoring system that detects an incident and alerts a following vehicle.

[0002]

2. Description of the Related Art FIG. 5 is a diagram showing the operation of a conventional road monitoring system. A vehicle 2 traveling in a lane L2 on a road is unintentional or slipped by a driver, and a state unintended by the driver occurs. Indicates that the vehicle is in a dangerous state for the following vehicle 3 due to the emergency stop.
In recent years, there have been many accidents in which the following vehicle crashes when the vehicle is emergency stopped due to an accident or breakdown, or the following vehicle crashes into the end of traffic congestion. In view of the situation, there is a demand for a safety measure that promptly and automatically notifies a following vehicle of a dangerous event that has occurred ahead. Under such a background, an intelligent transportation system (ITS: Intelligent Tr.) For achieving safe driving support and optimizing traffic control, etc.
Active systems are being actively promoted. Among them, an unexpected event detection device using an image sensor such as an ITV camera, a traffic flow measurement, and the like are partially put into practical use. Such a system is described in, for example, Mitsubishi Electric Technical Report VO
L. 70 No. 12 (1996) pages 78-83, "Sudden Event Detection System", Mitsubishi Electric Technical Report VOL. 66 N
o. 7 (1992) P42-45 "Traffic flow image measurement",
Hitachi Review Vol. 76 (1994), "Next-generation public systems for building a relaxed society" and the like.

In FIG. 5, reference numeral 1 denotes a vehicle that travels straight in the lane L1 and a vehicle 2 that stops near the shoulder of the lane L2 due to an unintended driver situation such as slipping while traveling straight in the lane L2. Reference numerals 2 and 3 denote vehicles 3 and 4 that travel straight in the lane L2 from behind the vehicle 2, first sensors 5 installed on the side of the road, 5 first sensor monitoring areas monitored by the first sensors, Reference numeral 6 denotes a controller for detecting that the traveling vehicle 2 is stopped on the road shoulder near the lane L2 and is in a dangerous situation with respect to the following vehicle, based on the output of the first sensor. Reference numeral 7 denotes the controller output information. This is a display that alerts the following vehicle by.

FIG. 6 is a block diagram showing the configuration of a conventional road monitoring system, for example, when an image sensor using a TV camera is used as the first sensor. The image acquired by the first sensor 4 is shown in FIG. As the data, the first signal processor 8 can obtain information such as the type of the vehicle, the distance from the first sensor to the traveling vehicle, and the relative speed of the traveling vehicle. For example, the contour shape of the vehicle is provided as a reference table for each type of vehicle, and the reference table is compared with the image data obtained from the first sensor 4 to detect the type of the vehicle. Using the position of the vehicle and the distance conversion coefficient proportional to the position in the image data, the first
By calculating the distance from the sensor to the vehicle and calculating the time difference of the image data, the relative speed of the vehicle is obtained from the differential of the distance. Next, the running state of the vehicle in the monitoring area is measured by the traffic flow measuring device using the output of the image processor. Next, in the event determination unit 10, when an unexpected event such as an accident or traffic congestion occurs, the output of the traffic flow measuring device indicates a change as compared with the case where the vehicle is running normally. By utilizing this, an event is determined, and an alarm is output to the display 11.

[0005]

In the road management system configured as described above, if the field of view is widened in order to widen the road monitoring area by the image sensor, the image sensor is not used when detecting the speed of the vehicle. If the distance between the vehicle and the vehicle is several tens of meters apart, it is difficult to find a temporal change with respect to the position of the vehicle in the image data, and there is a problem that the speed cannot be extracted. Conversely, if the field of view is set at a narrow angle to measure the speed of the vehicle, the road monitoring area is limited, and if it is desired to cover a wide monitoring area, it is configured with several image sensors and the road monitoring system There was a problem that the cost would increase. In addition, the image sensor has a problem in that the detection performance is reduced when the distance from the vehicle is increased by several tens of meters or more with respect to environmental changes such as a decrease in visibility due to rain or snow.

SUMMARY OF THE INVENTION The present invention has been made to solve such a problem, and makes use of the respective characteristics of an image sensor and a radar sensor using radio waves to interpolate a defect in each sensor and to cause an accident or the like. The purpose is to build a system that can determine events in any environment. For example, in a radar sensor, the distance between the vehicle and the radar sensor, the relative speed data of the vehicle, and the running speed of the vehicle are not affected by differences in brightness between day and night, and changes in the outside world such as poor visibility due to snow or fog. Although there is an advantage that position information such as lanes can be obtained, there is a disadvantage that it is difficult to determine the type of a running vehicle. On the other hand, the image sensor has a drawback that the performance as a single sensor greatly changes due to the above-described environmental change. However, if the distance is a short distance, the vehicle type is determined based on the contour shape of the running object in the image data. There is an advantage that can be. Therefore, by constructing a system using the characteristics of both sensors and compensating for the shortcomings of each sensor, it is possible to accurately determine events such as accident occurrence, traffic congestion occurrence, dangerous vehicle stop, and quickly move to the following vehicle The purpose is to notify dangerous information. In the above system, the image sensor can be replaced by an infrared camera in addition to a visible camera such as a TV camera, and the radar sensor uses millimeter wave band radio waves having radio wave characteristics that are strong against environmental changes. Radar sensors are particularly desirable.

[0007]

A road monitoring system according to a first aspect of the present invention transmits an electromagnetic wave to a radar sensor and a vehicle existing in an area monitored by the radar sensor, and receives a reflected wave from the vehicle to reach the vehicle. Distance, speed of the vehicle, a signal processor for calculating position information such as the angle or lane of the vehicle, and the vehicle type discriminator output of the vehicle detected by the image sensor and the output of the signal processor correspond to the travel locus of the vehicle. A tracking means for tracking and an event judging unit for judging an event by utilizing the fact that the distance, speed data and the like suddenly stop due to an accident or the like by the output of the tracking means are added.

A road monitoring system according to a second aspect of the present invention transmits an electromagnetic wave to a radar sensor and a vehicle existing in an area monitored by the radar sensor, and uses a reflected wave from the vehicle to determine the distance to the vehicle and the vehicle distance. A radar signal processor for calculating position information such as speed, vehicle angle or lane, a tracking means for tracking a vehicle traveling trajectory in a radar sensor monitoring area, and a vehicle type discriminator output of a vehicle entering the monitoring area. When the distance and velocity data are suddenly stopped due to an accident or the like by a correction unit that removes a target object that should not be present in the monitoring area by associating the output with the radar signal processor and the output of the tracking unit. An event determiner that determines an event that has occurred on a road, such as an accident or traffic congestion, using the change is added.

A road monitoring system according to a third aspect of the present invention transmits an electromagnetic wave to a radar sensor and a vehicle existing in an area monitored by the radar sensor. A radar signal processor for calculating position information such as a speed, a vehicle angle or a lane; and a tracking means for tracking a vehicle traveling locus by associating a vehicle type discriminator output detected by an image sensor with the signal processor output. When the vehicle is stopped due to an accident or the like due to the output of the tracking means, an event determination unit that determines a sudden event or traffic congestion using a change in distance or speed data, and a monitoring area by an image processor output. An entry number counter for counting the number of vehicles that have entered, a passage number counter for counting the number of vehicles that have passed through the monitoring area according to the output of the tracking means, A comparator for comparing the passage counter outputs Quantity counter output by said comparator output,
A reliability judging device for judging the reliability of an event such as an accident or traffic congestion using the difference between the number of passes and the number of approaches within a certain time and the number of vehicles existing in the monitoring area is added.

[0010]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Embodiment 1 FIG. 1A is an operation diagram showing Embodiment 1 of the present invention. In FIG. 1, reference numeral 1 denotes a vehicle 1, which travels straight in a lane L1, and 2 shows a situation in which the driver unintentionally slips while traveling straight in a lane L2. Occurs, and the vehicles 2 and 3 stopped near the shoulder of the lane L2 are the vehicles 3 and 4 traveling straight on the lane L2 from behind the vehicle 2 and the first sensors installed at appropriate places on the side of the road.
5 is a first sensor monitoring area monitored by the first sensor, 11 is a second sensor installed on the same roadside as the first sensor 5, and 12 is monitored by the second sensor. The second sensor monitoring area 6 is based on the output of the first sensor and the output of the second sensor.
Is stopped on the road shoulder near the lane L2, and a controller that detects a dangerous situation for the following vehicle, and 7 is a display that alerts the following vehicle based on the controller output information. . FIG. 2 is a block diagram showing the configuration of the road monitoring system according to the first embodiment of the present invention. Reference numeral 11 denotes a second sensor which is not affected by a change in the environment with respect to the first sensor 4. Reference numeral 13 calculates information such as a distance to the vehicle, a relative speed of the vehicle, and a traveling lane of the vehicle based on the output of the second sensor 11. The second signal processor 14 performs data such as the type, lane, and speed of the traveling vehicle for each vehicle that has entered the monitoring area based on the output of the first signal processor 8 and the vehicle based on the output of the second signal processor 13. The first sensor management area 5 and the second sensor management area 5 are associated with data such as lane, relative speed, and distance from the second sensor for each.
Tracking means for tracking the traveling locus of the vehicle within the monitoring area composed of the sensor monitoring area 12; information such as the distance from the second sensor 11 to the traveling vehicle being tracked and the relative speed of the traveling vehicle based on the output of the tracking means. Is an event determination unit that determines an event such as an accident or a traffic jam by measuring a temporal change of the event.

In the road monitoring system configured as described above, an image sensor such as a TV camera or an infrared camera is used as a first sensor, and a radar sensor using an electromagnetic wave in a millimeter wave band is used as a second sensor. Will be described in detail. First, based on the image data of the vehicle 1 and the vehicle 2 that have entered the first sensor monitoring area 5 obtained by the first sensor 4, the traveling lanes of the vehicle 1 and the vehicle 2 are obtained by the first signal processor. Information such as the type of the vehicle and the relative speed of the vehicle is calculated. Next, based on the reception signals obtained from the reflected waves from the vehicle 1 and the vehicle 2 entering the second sensor monitoring area by the second sensor, the second signal processor 13 Information such as distance from the second sensor, relative speed, and lane is calculated. The output of the first signal processor 8 and the output of the second signal processor 13 are made to correspond to each other, and the track of the vehicle in the second sensor monitoring area 12 is measured by the tracking means 14. The event determination unit 10 detects the distance from the second sensor of the vehicle 1 or the vehicle 2 or the point of change in the relative speed data based on the output of the tracking means 14 to recognize that the vehicle has stopped due to an accident or failure. it can. Further, by using the output of the tracking means 14, the situation such as traffic congestion can be recognized by using the number of tracked vehicles in the monitoring area and the relative speed data of each vehicle. For example, FIG. 1B shows the distance, the relative speed, and the trajectory of the lane from the second sensor to the vehicle when the vehicle 2 travels straight in the lane L2 in the monitoring area and stops near the road shoulder due to a slip or a failure. Show. Vehicle 2
The distance data, the speed data, and the lane data change every time the second signal processor 13 calculates, and a trajectory as shown in FIG. 1B can be obtained. Here, when a failure or accident occurs in the vehicle 2 and the vehicle 2 runs at a low speed or stops as shown in FIG. 1B, a change point is set in each data as shown in FIG. It can be detected, and occurrence of an event can be determined.

Embodiment 2 FIG. FIG. 1A is an operation diagram showing a second embodiment of the present invention. In FIG. 1, reference numeral 1 denotes a traveling vehicle traveling straight on lane L1, and reference numeral 2 denotes a situation unintended by the driver such as slipping while traveling straight on lane L2. The vehicle that has occurred and stops near the shoulder of the lane L2, 3 is a vehicle that travels straight in the lane L2 from behind the vehicle 2, 4 is a first sensor installed at a suitable place on the side of the road, and 5 is First
First sensor monitoring area monitored by the sensor of
1 is a second sensor installed on the same side of the road as the first sensor 5.
, A reference numeral 12 denotes a second sensor monitoring area monitored by the second sensor, and 6 denotes a vehicle stopped at a road shoulder near the lane L2 based on the first sensor output and the second sensor output. The controller 7 detects a dangerous situation with respect to the following vehicle 3 and a display 7 that alerts the following vehicle based on the controller output information.
FIG. 3 is a block diagram showing a configuration of a road monitoring system according to a second embodiment of the present invention. Reference numerals 4, 7, and 8 are the same as those in the related art. Numeral 11 denotes a second sensor which is not affected by changes in the environment with respect to the first sensor 4. Numeral 13 calculates information such as a distance to the vehicle, a relative speed of the vehicle, and a traveling lane of the vehicle based on the output of the second sensor 12. Second signal processor, 14
Is data such as the type, lane, and speed of the traveling vehicle for each vehicle that has entered the monitoring area based on the output of the first signal processor, and the lane, relative speed, and second sensor of each vehicle based on the output of the second signal processor. A tracking means for tracking the traveling locus of the vehicle in the monitoring area in association with data such as a distance from the vehicle, and removing the output of the second signal processor 13 other than the traveling vehicle being tracked by the output of the tracking means. The correction means 10 performs an event to determine an event such as an accident or traffic jam by measuring a temporal change in information such as a distance data to a traveling vehicle being tracked or a relative speed of the traveling vehicle by the output of the tracking means. It is a determination unit.

In the road monitoring system configured as described above, an image sensor such as a TV camera or an infrared camera is used as a first sensor, and a radar sensor using an electromagnetic wave in a millimeter wave band is used as a second sensor. Will be described in detail. First, based on the image data of the vehicle 1 and the vehicle 2 that have entered the first sensor monitoring area obtained by the first sensor 8, the first signal processor processes the vehicles 1 and 2
The information such as the traveling lane, the type of the vehicle, and the relative speed of the vehicle is calculated. Next, based on the reception signals obtained from the reflected waves from the vehicle 1 and the vehicle 2 entering the second sensor monitoring area by the second sensor, the second signal processor 13 Information such as distance from the second sensor, relative speed, and lane is calculated. The output of the first signal processor 8 and the output of the second signal processor 13 are made to correspond to each other, and the traveling locus of the vehicle in the second monitoring area is tracked by the tracking means 14.
Measure with. Here, when data other than the vehicle that has entered the monitoring area detected by the output of the first signal processor 8 is included in the output of the second signal processor, the correction means 1
At 5, it is regarded as something other than the vehicle, for example, a guardrail or a sign, and is removed. The event determination unit 10 detects the distance from the second sensor of the vehicle 1 or the vehicle 2 or the point of change in the relative speed data based on the output of the tracking means 14 to recognize that the vehicle has stopped due to an accident or failure. it can. Further, by using the output of the tracking means 14, the situation such as traffic congestion can be recognized by using the number of tracked vehicles in the monitoring area and the relative speed data of each vehicle. For example, FIG. 1B shows the locus of the distance data and the speed data when the vehicle 2 travels straight in the lane L2 in the monitoring area and stops near the road shoulder due to a slip or a failure. The distance data, speed data, and lane data of the vehicle 2 change each time the second signal processor 13 calculates the distance data, and a trajectory as shown in FIG. 1B can be obtained. Here, when a failure or accident occurs in the vehicle 2 and the vehicle 2 runs at a low speed or stops as shown in FIG. 1B, a change point is set in each data as shown in FIG. It can be detected, and occurrence of an event can be determined.

Embodiment 3 FIG. 1A is an operation diagram showing a third embodiment of the present invention. In FIG. 1, reference numeral 1 denotes a traveling vehicle traveling straight on lane L1, and reference numeral 2 denotes a situation unintended by the driver such as slipping while traveling straight on lane L2. The vehicle that has occurred and stops near the shoulder of the lane L2, 3 is a vehicle that travels straight in the lane L2 from behind the vehicle 2, 4 is a first sensor installed at a suitable place on the side of the road, and 5 is First
First sensor monitoring area monitored by the sensor of
1 is a second sensor installed on the same side of the road as the first sensor 5.
, The sensor 12 is a second sensor monitoring area monitored by the second sensor, and 6 is a signal indicating that the traveling vehicle 2 is on the road shoulder near the lane L2 based on the output of the first sensor and the output of the second sensor. The controller 7 detects that the vehicle is stopped and is in danger to the following vehicle, and 7 is a display that alerts the following vehicle based on the controller output information.
FIG. 4 is a block diagram showing a configuration of a road monitoring system according to a third embodiment of the present invention. Reference numerals 4, 7, and 8 are the same as those in the related art. Reference numeral 11 denotes a second sensor which is not affected by changes in the environment with respect to the first sensor 8, and 13 calculates information such as the distance to the vehicle, the relative speed of the vehicle, and the traveling lane of the vehicle based on the output of the second sensor 11. Second signal processor, 14
Is data such as the type, lane, and speed of the traveling vehicle for each vehicle that has entered the monitoring area based on the output of the first signal processor, and the lane, relative speed, and second sensor of each vehicle based on the output of the second signal processor. Tracking means for tracking the traveling trajectory of the vehicle in the monitoring area in association with data such as distance from the vehicle, and 16 outputs the number of vehicles entering the monitoring area in a unit time by the output of the first signal processor. The entry number counter for counting, 17 is based on the output of the tracking means,
A pass counter for counting the number of vehicles passing outside the monitoring area within a unit time, 18 is a comparator for comparing the output of the entry counter with the output of the pass counter, and 19 is a comparator for the output of the pass counter. The reliability determination unit 10 that determines the reliability of occurrence of an event such as an accident or traffic congestion, the output of the tracking means 14 and the output of the reliability determination unit 19
An event determination unit that determines an event such as an accident or traffic jam.

In the road monitoring system configured as described above, an image sensor such as a TV camera or an infrared camera is used as a first sensor, and a radar sensor using an electromagnetic wave in a millimeter wave band is used as a second sensor. Will be described in detail. First, based on the image data of the vehicle 1 and the vehicle 2 that have entered the first sensor monitoring area obtained by the first sensor 8, the first signal processor processes the vehicles 1 and 2
The information such as the traveling lane, the type of the vehicle, and the relative speed of the vehicle is calculated. The number of vehicles that have entered the monitoring area within a unit time is counted by the entry counter using the output of the first signal processor. Next, the second sensor
The distance, relative speed, and lane of the vehicle 1 and the vehicle 2 from the second sensor are obtained by the second signal processor 14 from the reception signals obtained from the reflected waves from the vehicle 1 and the vehicle 2 that have entered the sensor monitoring area of FIG. Is calculated. The first
The output of the signal processor 9 and the output of the second signal processor 13 are made to correspond to each other, and the track of the vehicle in the second monitoring area is measured by the tracking means 14. In addition, the number of vehicles passing outside the monitoring area within a unit time is counted by the passage number counter 17 by the output of the tracking means 14. Here, the comparator 1 is calculated based on the output of the entry number counter and the output of the passage number counter.
At 8, the difference is calculated. In the reliability judgment unit 19, the comparator 18
Based on the output, the reliability of occurrence of an event occurring in the monitoring area such as occurrence of an accident or traffic jam is determined and output to the event determination unit 10. The event determination unit 10 can improve the reliability of the event occurrence determination by using the output of the tracking means 14 and the output of the reliability determination unit 19.

[0016]

According to the first aspect of the present invention, the second sensor which is not affected by the environmental change as compared with the first sensor and the first sensor.
By using the above sensors together and determining the type of the vehicle on the road and tracking the traveling locus, it is possible to detect the occurrence of an event such as an accident or traffic jam in various road environments.

According to the second aspect of the present invention, the first sensor is used together with the second sensor which is not affected by environmental changes as compared with the first sensor, and is detected by the first sensor. By detecting or interpolating a target other than the vehicle detected by the second sensor by associating the vehicle data with the vehicle data detected by the second sensor, the vehicle detection by the second sensor is performed. Accuracy can be improved.

According to the third aspect of the present invention, the first sensor and the second sensor, which are not affected by environmental changes as compared with the first sensor, are used together to determine the type of the vehicle on the road and By tracking the running trajectory and measuring the number of vehicles entering the monitoring area and the number of vehicles passing outside the monitoring area within a unit time, the accuracy of the event occurrence determination such as accidents and traffic jams can be improved. Can be improved.

[Brief description of the drawings]

FIG. 1 is an operation diagram showing Embodiments 1, 2, and 3 of the present invention.

FIG. 2 is a block diagram illustrating a configuration of a road monitoring system according to the first embodiment of the present invention.

FIG. 3 is a block diagram illustrating a configuration of a road monitoring system according to a second embodiment of the present invention.

FIG. 4 is a block diagram illustrating a configuration of a road monitoring system according to a third embodiment of the present invention.

FIG. 5 is an operation diagram showing a conventional road monitoring system.

FIG. 6 is a block diagram showing a configuration of a conventional road monitoring system.

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 1 Vehicle 1, 2 Vehicle 2, 3 Vehicle 3, 4 First sensor, 5 First sensor monitoring area, 6 Controller, 7 Display, 8 First signal processor, 9 Traffic flow meter, 10
Event determination unit, 11 second sensor, 12 second sensor monitoring area, 13 second signal processor, 14 tracking means, 1
5 Correction means, 16 ingress counter, 17 pass counter, 18 comparator, 19 reliability judgment unit.

Claims (3)

[Claims] 1. A first sensor which is provided at an appropriate position on a road and monitors an abnormal event such as an accident or traffic congestion occurring on the road, and is more affected by changes in the natural environment than the first sensor. A second sensor that is difficult to detect, a first processing device that detects the presence or absence of a vehicle entering the monitoring area of the first sensor on the road from the output of the first sensor, and a type of the vehicle; The presence or absence of a vehicle entering the monitoring area of the second sensor on the road from the output of the second sensor;
The distance from the sensor to the vehicle, and the second processing device for detecting the relative speed of the vehicle, the output of the first processing device and the output of the second processing device correspond to each other, the distance of each vehicle, Tracking means for tracking the traveling trajectory of the vehicle by measuring the temporal change using relative speed data, and the output of the tracking means allows the following vehicle such as an accident or a traffic jam to be detected in the vehicle data being tracked. When a dangerous abnormal condition occurs, an event determining unit that determines the abnormal event by using the change in the distance and speed data of the vehicle being tracked is different, and the abnormality that occurs in front of the following vehicle A road monitoring system, comprising: an indicator for transmitting an event. 2. A first sensor which is provided at an appropriate place on a road and monitors an abnormal event such as an accident or traffic congestion occurring on the road, and has a lower influence on changes in the natural environment than the first sensor. In a road monitoring system using a second sensor that is hardly affected by the second sensor, the information on the presence or absence of a vehicle existing in the monitoring area of the first sensor is compared with the output of the second sensor. The road monitoring system according to claim 1, further comprising a correction unit that removes a target other than the detected vehicle. 3. A first sensor which is provided at an appropriate position on a road and monitors an abnormal event such as an accident or traffic congestion occurring on the road, and has a greater influence on changes in the natural environment than the first sensor. In a road monitoring system using a second sensor that is less susceptible to intrusion, an approach counter that counts the number of vehicles that have entered the monitoring area in a unit time, and a number of vehicles that have passed out of the monitoring area in a unit time. Compare the number of passing counters to count, the number of entering number counter and the number of passing number counter, and use the number of entering and passing numbers within a certain time and the number of vehicles existing in the monitoring area to detect abnormal events such as accidents and traffic jams. The road monitoring system according to claim 1, further comprising a reliability determination unit configured to determine a reliability of the road.