JP7519928B2 - Vehicle tracking system and vehicle tracking method - Google Patents

Description

This disclosure relates to a system for tracking the trajectory of vehicle traffic.

Patent Document 1 discloses a merging assistance system for expressways.
This system works by installing surveillance cameras at multiple locations to observe passing vehicles and communicating dangers at merging points based on the observation results at each location.

JP 2018-81358 A

The system of Patent Document 1 is effective in daytime when visibility is good, but is unable to fully support safe driving at night or in bad weather because the detection performance of the camera drops.
In addition, predictions based on observational results at each point cannot keep up with sudden changes in movement, such as lane changes or motorcycles passing by, and there may be a delay in transmitting hazard predictions to vehicles traveling in the merging lane at merging points.

The purpose of this disclosure is to enable more accurate tracking of vehicle traffic trajectories.

The vehicle tracking system of the present disclosure includes:
A vehicle detection sensor is provided on a road to detect a vehicle traveling toward a vehicle tracking section of the road as a target vehicle;
A first tracking sensor provided on the road for tracking a travel trajectory of the target vehicle traveling through the vehicle tracking section;
and a second tracking sensor, the type of which is different from that of the first tracking sensor, that is provided on the road and for tracking the travel trajectory of the target vehicle passing through the vehicle tracking section.

According to the present disclosure, a vehicle can be detected using a vehicle detection sensor, and the path of the detected vehicle can be tracked using two types of tracking sensors. This makes it possible to track the path of the vehicle more accurately.

FIG. 1 is a configuration diagram of a vehicle tracking system 100 according to a first embodiment. FIG. 2 is a diagram showing a specific example of the configuration of the vehicle tracking system 100 according to the first embodiment. FIG. 2 is a configuration diagram of a vehicle tracking device 200 according to the first embodiment. 4 is a flowchart of a vehicle tracking method in the first embodiment.

In the embodiments and drawings, the same or corresponding elements are given the same reference numerals. Explanations of elements given the same reference numerals as previously described elements are omitted or simplified as appropriate. Arrows in the drawings primarily indicate data flow or processing flow.

Embodiment 1.
The vehicle tracking system 100 will be described with reference to FIGS. 1 to 4. FIG.

***Configuration Description***
The configuration of a vehicle tracking system 100 will be described with reference to FIG.
The vehicle tracking system 100 includes one or more vehicle detection sensors 110, one or more first tracking sensors 120, one or more second tracking sensors 130, and a vehicle tracking device 200.
The vehicle tracking device 200 communicates with each vehicle detection sensor 110 , each first tracking sensor 120 , and each second tracking sensor 130 via a network 109 .

The vehicle detection sensors 110, the first tracking sensors 120, the second tracking sensors 130, and the vehicle tracking device 200 are time-synchronized.
Specifically, the time synchronization is achieved by communication with a time server connected to the network 109 .
A time server is a device that provides time. The time source of a time server is, for example, GNSS.
For communication with the time server, for example, NTP is used.
GNSS is an abbreviation for Global Navigation Satellite System.
NTP is an abbreviation for Network Time Protocol.

The vehicle detection sensor 110, the first tracking sensor 120, and the second tracking sensor 130 are provided for each vehicle tracking section.
The vehicle tracking section is a section of a road on which a vehicle travels that is a target for tracking the travel trajectory of the vehicle. For example, the vehicle tracking section is a section before (upstream) a junction on an expressway or a section before (upstream) an intersection on a general road.

The vehicle detection sensor 110 is a sensor that is installed on a road and detects a vehicle traveling toward the vehicle tracking section as a "target vehicle."
A "target vehicle" is a vehicle that is the subject of tracking, which travels toward the vehicle tracking section and then passes through the vehicle tracking section.
A specific example of the vehicle detection sensor 110 is a laser sensor.

The first tracking sensor 120 and the second tracking sensor 130 are sensors provided on a road for tracking the travel trajectory of a target vehicle passing through a vehicle tracking section.
The first tracking sensor 120 and the second tracking sensor 130 are different in type from each other. A specific example of the first tracking sensor 120 is a millimeter wave radar, and a specific example of the second tracking sensor 130 is a camera or a three-dimensional lidar.

A specific example of the configuration of the vehicle tracking system 100 will be described with reference to Fig. 2. However, a description of the vehicle tracking device 200 will be omitted.
On a highway, the vehicle tracking system 100 is equipped with a laser sensor 111 as a vehicle detection sensor 110.
The vehicle tracking system 100 also includes a millimeter wave radar 121 as the first tracking sensor 120 .
The vehicle tracking system 100 also includes a camera 131 as a second tracking sensor 130 .

On expressways, the main lane just before a junction is a vehicle tracking section.

The laser sensor 111 is disposed above the road upstream of the vehicle tracking section. Specifically, the laser sensor 111 is installed on a gatepost provided just before the vehicle tracking section.
The laser sensor 111 is used to detect a target vehicle passing underneath.
The thick solid line drawn from the laser sensor 111 represents the irradiation range of the laser from the laser sensor 111. In other words, the thick solid line represents the detection range of the target vehicle by the laser sensor 111.

The millimeter wave radar 121 and the camera 131 are disposed upstream of the vehicle tracking section and facing the vehicle tracking section. Specifically, these sensors are installed on a gatepost provided just before the vehicle tracking section.
The millimeter wave radar 121 and the camera 131 are used to track the travel trajectory of a target vehicle passing through the vehicle tracking section.
The thick dashed line drawn from the millimeter wave radar 121 represents the irradiation range of millimeter waves from the millimeter wave radar 121. In other words, the thick dashed line represents the tracking range of the target vehicle by the millimeter wave radar 121.
The thick dashed dotted line drawn from the camera 131 represents the imaging range of the camera 131. In other words, the thick dashed dotted line represents the tracking range of the target vehicle by the camera 131.

Along with these sensors, a satellite positioning receiver 141 is provided. The satellite positioning receiver 141 is a receiver for a satellite positioning system.
The satellite positioning receiver 141 uses a satellite positioning system to determine its own position, thereby obtaining the absolute coordinate values of the satellite positioning receiver 141.
The absolute coordinate values indicating the respective positions of the laser sensor 111 , the millimeter wave radar 121 , and the camera 131 are calculated by adding the relative coordinate values with respect to the satellite positioning receiver 141 to the absolute coordinate values of the satellite positioning receiver 141 .
Each relative coordinate value is pre-stored in the storage unit 290. Also, each absolute coordinate value is stored in the storage unit 290.

An electronic signboard 132 is provided on the roadside near the merging point so that it can be seen by vehicles (merging vehicles) traveling in the merging lane toward the main lane.

The configuration of the vehicle tracking device 200 will be described with reference to FIG.
The vehicle tracking device 200 is a computer including hardware such as a processor 201, a memory 202, an auxiliary storage device 203, a communication device 204, and an input/output interface 205. These pieces of hardware are connected to each other via signal lines.

The processor 201 is an IC that performs arithmetic processing and controls other hardware. For example, the processor 201 is a CPU, a DSP, or a GPU.
IC is an abbreviation for Integrated Circuit.
CPU is an abbreviation for Central Processing Unit.
DSP is an abbreviation for Digital Signal Processor.
GPU is an abbreviation for Graphics Processing Unit.

The memory 202 is a volatile or non-volatile storage device. The memory 202 is also called a primary storage device or a main memory. For example, the memory 202 is a RAM. Data stored in the memory 202 is saved in the secondary storage device 203 as necessary.
RAM is an abbreviation for Random Access Memory.

The auxiliary storage device 203 is a non-volatile storage device. For example, the auxiliary storage device 203 is a ROM, a HDD, or a flash memory. Data stored in the auxiliary storage device 203 is loaded into the memory 202 as needed.
ROM is an abbreviation for Read Only Memory.
HDD is an abbreviation for Hard Disk Drive.

The communication device 204 is a receiver and a transmitter. For example, the communication device 204 is a communication chip or a NIC. The communication of the vehicle tracking device 200 is performed using the communication device 204.
NIC is an abbreviation for Network Interface Card.

The input/output interface 205 is a port to which an input device and an output device are connected. For example, the input/output interface 205 is a USB terminal, the input device is a keyboard and a mouse, and the output device is a display. Input and output of the vehicle tracking device 200 is performed using the input/output interface 205.
USB is an abbreviation for Universal Serial Bus.

The vehicle tracking device 200 includes elements such as a vehicle detection unit 211, a first tracking unit 212, a second tracking unit 213, an integrated tracking unit 214, and an information notification unit 215. These elements are realized by software.

The auxiliary storage device 203 stores a vehicle tracking program for causing a computer to function as a vehicle detection unit 211, a first tracking unit 212, a second tracking unit 213, an integrated tracking unit 214, and an information notification unit 215. The vehicle tracking program is loaded into the memory 202 and executed by the processor 201.
The auxiliary storage device 203 further stores an OS. At least a part of the OS is loaded into the memory 202 and executed by the processor 201.
The processor 201 executes a vehicle tracking program while executing the OS.
OS is an abbreviation for Operating System.

Input and output data of the vehicle tracking program are stored in memory unit 290.
The memory 202 functions as the storage unit 290. However, a storage device such as the auxiliary storage device 203, a register in the processor 201, or a cache memory in the processor 201 may function as the storage unit 290 instead of the memory 202 or together with the memory 202.

The vehicle tracking device 200 may be equipped with multiple processors replacing the processor 201.

The vehicle tracking program can be recorded (stored) in a computer-readable manner on a non-volatile recording medium such as an optical disk or flash memory.

*** Operation Description ***
The operation procedure of the vehicle tracking system 100 corresponds to a vehicle tracking method, and the operation procedure of the vehicle tracking device 200 corresponds to a processing procedure according to a vehicle tracking program.

The vehicle tracking method will be described with reference to FIG.
Steps S110 to S160 are performed for each of the one or more target vehicles.

In step S110, the vehicle detection unit 211 detects the target vehicle using the vehicle detection sensor 110.

Specifically, step S110 is as follows.
The laser sensor 111 irradiates a laser beam from above the road toward the road and scans perpendicularly to the traffic direction of the road. This produces laser sensor data indicating a distance direction point cloud. The distance direction point cloud indicates the distance and direction from the laser sensor 111 to each irradiation point at each time. The irradiation points are the locations where the laser beam is irradiated and reflected.
The laser sensor 111 transmits laser sensor data to the vehicle tracking device 200 .
The vehicle detection unit 211 receives laser sensor data from the laser sensor 111 .
The vehicle detection unit 211 detects a target vehicle based on the laser sensor data. If the distance indicated by the laser sensor data is shorter than the distance from the laser sensor 111 to the road surface, the target vehicle is detected. The distance from the laser sensor 111 to the road surface is measured in advance and stored in the storage unit 290.

Furthermore, the vehicle detection unit 211 detects the approach speed, vehicle dimensions, and vehicle type based on the laser sensor data.

The approach speed is detected as follows:
When the laser sensor 111 is a two-dimensional laser sensor, another laser sensor 111 is provided upstream of the laser sensor 111. Then, the vehicle detection unit 211 divides the distance from the upstream laser sensor 111 to the downstream laser sensor 111 by the time from when the target vehicle is detected by the upstream laser sensor 111 to when the target vehicle is detected by the downstream laser sensor 111. In this way, the approach speed of the target vehicle is calculated.
When the laser sensor 111 is a three-dimensional laser sensor, the vehicle detection unit 211 divides the distance in the travel direction of the irradiation area of the laser light on the road surface by the time from when the target vehicle is detected at the most upstream of the irradiation area to when the target vehicle is detected at the most downstream of the irradiation area, thereby calculating the approach speed of the target vehicle.

Vehicle dimensions (width, length and height) are detected as follows:
The vehicle detection unit 211 calculates the length in the width direction of the road within which the target vehicle is detected. The calculated length is the vehicle width.
The vehicle detection unit 211 calculates the vehicle length by multiplying the time when the target vehicle is detected by the approach speed. Alternatively, the vehicle detection unit 211 calculates the vehicle length by multiplying the approach speed by the measurement interval and the number of measurement lines. The measurement interval means the time interval of scanning by the laser sensor 111, and the number of measurement lines means the number of measurements. For example, if the approach speed is 10 meters per second, the measurement interval is 0.1 seconds, and the number of measurements is 7, the vehicle length is 7 meters (=10 x 7 x 0.1).
The vehicle detection unit 211 subtracts the height from the laser sensor 111 to the target vehicle from the height from the laser sensor 111 to the road surface. In this way, the vehicle height is calculated. The height from the laser sensor 111 to the road surface is measured in advance and stored in the storage unit 290.

The vehicle type is detected as in (1) or (2). Specific examples of vehicle type classification include classification into regular cars, motorcycles, and large vehicles, or classification into motorcycles, regular cars, trucks, and buses.
(1) A vehicle model dimension pattern indicating the vehicle dimensions for each vehicle model is stored in advance in the storage unit 290, and the vehicle detection unit 211 detects the vehicle model using the vehicle model dimension pattern. In other words, the vehicle detection unit 211 compares the vehicle dimensions of the target vehicle with the vehicle dimensions of each vehicle model, and finds a vehicle model whose vehicle dimensions match the vehicle.
(2) A vehicle model contour pattern indicating the contour of each vehicle model is stored in advance in the storage unit 290, and the vehicle detection unit 211 detects the vehicle model using the vehicle model contour pattern. In other words, the vehicle detection unit 211 compares the contour of the target vehicle represented by the distance direction point cloud indicated by the laser sensor data with the contour of each vehicle model, and finds a vehicle model whose contour matches the contour of the target vehicle.

In step S120, the first tracking unit 212 uses the first tracking sensor 120 to track the travel trajectory of the target vehicle.
In other words, the first tracking unit 212 uses the first tracking sensor 120 to calculate the position (current position and predicted position) of the target vehicle at each time.

Specifically, step S120 is as follows.
The millimeter wave radar 121 irradiates millimeter waves toward the entire vehicle tracking section and scans the entire vehicle tracking section. This produces millimeter wave radar data indicating a distance direction point cloud. The distance direction point cloud indicates the distance and direction from the millimeter wave radar 121 to each irradiation point at each time. The irradiation point is a location where the millimeter wave is irradiated and reflected.
The millimeter wave radar 121 transmits millimeter wave radar data at each time to the vehicle tracking device 200 .
The first tracking unit 212 receives millimeter wave radar data at each time from the millimeter wave radar 121.
The first tracking unit 212 tracks the travel trajectory of the target vehicle by using the millimeter wave radar data at each time.

For example, the first tracking unit 212 divides the advance distance from the detection point by the laser sensor 111 to the vehicle tracking section by the entry speed of the target vehicle to calculate the required time from the detection time when the target vehicle is detected by the laser sensor 111 to the entry time when the target vehicle enters the vehicle tracking section. The advance distance is measured in advance and stored in the memory unit 290. Next, the first tracking unit 212 calculates the entry time by adding the required time to the detection time. Then, the first tracking unit 212 tracks the travel trajectory of the target vehicle using millimeter wave radar data for each time after the entry time.

For example, the first tracking unit 212 tracks the travel trajectory of the target vehicle as follows: The time when the current data (millimeter wave radar data and image data) is obtained is referred to as the "current time", the time when the previous data is obtained is referred to as the "previous time", and the time when the next data is obtained is referred to as the "next time".
The first tracking unit 212 detects the target vehicle within a prediction area based on the target vehicle's position (predicted position) predicted at the previous time within the entire vehicle tracking section, and calculates the target vehicle's position (current position) at the current time. The prediction area is, for example, an area having a specific size centered on the predicted position.
Then, the first tracking unit 212 calculates a movement vector from the detection position at the previous time to the detection position at the current time, and predicts the position of the target vehicle at the next time based on the calculated movement vector. For example, the first tracking unit 212 calculates the predicted position of the target vehicle at the next time by adding the movement vector to the coordinate value indicating the detection position at the current time.

In tracking the target vehicle, the first tracking unit 212 may distinguish the target vehicle from the other vehicles by comparing the vehicle model of the target vehicle with the vehicle model of the other vehicles. The other vehicles refer to target vehicles other than the target vehicle of interest.
The type of each vehicle is detected in a manner similar to the detection method based on the laser sensor data (see step S110).

In step S130, the second tracking unit 213 uses the second tracking sensor 130 to track the travel trajectory of the target vehicle.
In other words, the second tracking unit 213 uses the second tracking sensor 130 to calculate the position (current position and predicted position) of the target vehicle at each time.

Specifically, step S130 is as follows.
The camera 122 captures an image of the entire vehicle tracking section, thereby obtaining image data showing an image capturing the entire vehicle tracking section.
The camera 122 transmits image data at each time to the vehicle tracking device 200 .
The second tracking unit 213 receives image data at each time from the camera 122 .
The second tracking unit 213 tracks the travel trajectory of the target vehicle by using the image data at each time.

For example, the second tracking unit 213 calculates the entry time in the same manner as the first tracking unit 212. Then, the second tracking unit 213 tracks the travel trajectory of the target vehicle using image data at each time after the entry time.

For example, the second tracking unit 213 tracks the travel trajectory of the target vehicle, similar to the first tracking unit 212. That is, the second tracking unit 213 calculates the position of the target vehicle at the current time (current position). The second tracking unit 213 also calculates the position of the target vehicle at the next time (predicted position).

When tracking a target vehicle, the second tracking unit 213 may distinguish the target vehicle from other vehicles by comparing the vehicle model of the target vehicle with the vehicle models of other vehicles.
The type of each vehicle is detected by image processing of the image data.

The tracking results (current position and predicted position) obtained in step S120 are referred to as a “first tracking result.” In other words, the first tracking result is a tracking result obtained by the millimeter wave radar 121 (an example of the first tracking sensor 120).
The tracking results (current position and predicted position) obtained in step S130 are referred to as “second tracking results.” In other words, the second tracking results are tracking results obtained by camera 131 (an example of second tracking sensor 130).

In step S140, the integrated tracking unit 214 integrates the first tracking result and the second tracking result to determine a final tracking result.
That is, the integrated tracking unit 214 determines the current position of the target vehicle by integrating the current position of the first tracking result and the current position of the second tracking result.
Furthermore, the integrated tracking unit 214 integrates the predicted position of the first tracking result and the predicted position of the second tracking result to determine the predicted position of the target vehicle.

Specifically, the integrated tracking unit 214 assigns importance to each of the first and second tracking results according to the conditions shown below, and determines the final tracking result based on the first and second tracking results and their respective importance.

In bad weather, tracking by the millimeter wave radar 121 is less affected, but tracking by the camera 131 is more affected.
Therefore, the joint tracking unit 214 places importance on the first tracking result in bad weather.

In bad weather, the road becomes wet with rain or snow, so the joint tracking unit 214 can determine whether the weather is bad based on the reflection intensity of the laser light reflected by the road and measured by the laser sensor 111.
A weather sensor may also be provided. The integrated tracking unit 214 can use the weather sensor to determine whether the weather is bad. For example, the integrated tracking unit 214 measures the amount of rain or snowfall using the weather sensor, and determines that the weather is bad if the measured amount exceeds a threshold.

At night, tracking by the millimeter wave radar 121 is less affected, but tracking by the camera 131 is more affected.
Therefore, the joint tracking unit 214 places importance on the first tracking result during the nighttime.

The camera 131 is not a distance measurement sensor.
Therefore, the joint tracking unit 214 places importance on the first tracking result regarding the position in the traffic direction of the road.

The millimeter wave radar 121 has a lower angular resolution than the camera 131.
Therefore, the joint tracking unit 214 places importance on the second tracking result regarding the position in the width direction of the road.

The farther the target vehicle is located, the greater the distance error in detection by the camera 131. On the other hand, even if the target vehicle is located farther, the distance error in detection by the millimeter wave radar 121 is small.
Therefore, the more the target vehicle's position is farther from the camera 131, the more importance the joint tracking unit 214 places on the first tracking result.
In addition, the closer the position of the target vehicle is to the camera 131, the more importance the joint tracking unit 214 places on the second tracking result.

The joint tracking unit 214 may select, as the final tracking result, the tracking result having the greater importance between the first tracking result and the second tracking result.
The integrated tracking unit 214 may calculate an intermediate result between the first tracking result and the second tracking result as the final tracking result. For example, the integrated tracking unit 214 may multiply the first tracking result by the first importance to calculate a first correction result, multiply the second tracking result by the second importance to calculate a second correction result, and calculate the sum of the first correction result and the second correction result as the final tracking result. The first importance is the importance of the first tracking result, and the second importance is the importance of the second tracking result. In addition, the first importance and the second importance are each equal to or greater than 0 and equal to or less than 1, and the sum of the first importance and the second importance is 1.

In step S150, the information notification unit 215 determines whether to notify the target vehicle's traffic information based on the final tracking result.
For example, the traffic information is a message notifying that the target vehicle is passing near a junction.
For example, when the distance from the junction to the predicted position of the target vehicle is less than a threshold, the information notification unit 215 determines to notify the traffic information.
If the traffic information is to be notified, the process proceeds to step S160.
If the passage information is not to be notified, the process returns to step S120 and step S130.

In step S160, the information notifying unit 215 notifies the passage information.
For example, the information notification unit 215 transmits the traffic information to an on-board device of the merging vehicle via a roadside device installed in the merging lane. The on-board device of the merging vehicle receives the traffic information and outputs the traffic information in the form of at least one of a sound and an image.
For example, the information notification unit 215 transmits the passage information to the electronic bulletin board 142 provided near the junction. Then, the electronic bulletin board 142 displays the passage information.

***Advantages of First Embodiment***
According to the first embodiment, it becomes possible to stably track the path of a vehicle even at night or during rainy hours.

The vehicle detection sensor 110, the first tracking sensor 120, and the second tracking sensor 130 are installed at appropriate locations on a road. These sensors are used to detect vehicles traveling on the main line of a highway, etc., and to track the trajectory of the vehicles to a junction, intersection, or other location where there is a risk of collision.
This makes it possible to monitor in advance the situation of vehicles approaching from blind spots for the merging vehicle, enabling the merging vehicle to take measures to avoid danger.

A laser sensor 111 is used to detect vehicles.
Detection by the laser sensor 111 is not easily affected even at night or during rain. The laser sensor 111 is more suitable than a camera in an outdoor installation environment because it can identify situations in which motorcycles are traveling side by side or large vehicles are being towed, and is not easily affected by external disturbances such as day and night or rain and snow.

A millimeter wave radar 121 and a camera 131 are used in combination to track the vehicle.
Using the millimeter wave radar 121, it is possible to track a vehicle. However, tracking using the millimeter wave radar 121 has a problem in that multiple distant vehicles are detected overlapping each other. Therefore, tracking using the camera 131 is also used. Tracking using the camera 131 makes it possible to detect multiple distant vehicles separately.
The camera 131 can be used to track a vehicle. However, tracking using the camera 131 has poor detection performance in bad weather such as rain. Therefore, tracking using the millimeter wave radar 121 is also used. Tracking using the millimeter wave radar 121 is less affected by bad weather.
By using the millimeter wave radar 121 and the camera 131 in combination, the weaknesses of each of the millimeter wave radar 121 and the camera 131 can be compensated for.

By installing the laser sensor 111 at an appropriate location on the road and observing the cross section, it becomes possible to detect passing vehicles, calculate the approach speed, and obtain vehicle shape information, and it becomes possible to realize the passing time of passing vehicles and individual identification of passing vehicles. It also becomes possible to manage the passing trajectory of each passing vehicle.
By using the millimeter wave radar 121 and the camera 131 in combination to track the trajectory of traffic, the advantage of the millimeter wave radar 121, that is, weather resistance, can be made up for the weakness of the camera 131, that is, weather resistance. Also, the advantage of the camera 131, that is, high resolution, can be made up for the weakness of the millimeter wave radar 121, that is, low separation performance.

***Additional Information on the Implementation ***
Each embodiment is an example of a preferred embodiment, and is not intended to limit the technical scope of the present disclosure. Each embodiment may be implemented in part or in combination with other embodiments. The procedures described using flow charts, etc. may be modified as appropriate.

The vehicle tracking device 200 may be realized by multiple devices.
The "part" which is an element of the vehicle tracking device 200 may be read as a "process," a "step," a "circuit," or a "circuitry."

100 Vehicle tracking system, 109 Network, 110 Vehicle detection sensor, 111 Laser sensor, 120 First tracking sensor, 121 Millimeter wave radar, 130 Second tracking sensor, 131 Camera, 141 Satellite positioning receiver, 142 Electronic bulletin board, 200 Vehicle tracking device, 201 Processor, 202 Memory, 203 Auxiliary storage device, 204 Communication device, 205 Input/output interface, 211 Vehicle detection unit, 212 First tracking unit, 213 Second tracking unit, 214 Integrated tracking unit, 215 Information notification unit, 290 Storage unit.

Claims (8)

a vehicle detection sensor which is a laser sensor provided on a road and disposed above the road upstream of a vehicle tracking section of the road, irradiating a laser beam from above the road toward the road, scanning the road perpendicularly to the traffic direction, and detecting a vehicle traveling toward the vehicle tracking section of the road and passing below as a target vehicle;
a first tracking sensor that is a millimeter wave radar provided on the road and arranged upstream of the vehicle tracking section toward the vehicle tracking section, for tracking a travel trajectory of the target vehicle passing through the vehicle tracking section ;
a second tracking sensor that is a camera provided on the road and arranged upstream of the vehicle tracking section toward the vehicle tracking section, for tracking a travel trajectory of the target vehicle passing through the vehicle tracking section;
A vehicle tracking device;
Equipped with
The vehicle tracking device includes:
a vehicle detection unit that detects the target vehicle using the vehicle detection sensor and detects the entry speed of the target vehicle ;
a first tracking unit that calculates an entry time of the target vehicle into the vehicle tracking section based on a detection time of the target vehicle and a detected entry speed, tracks the travel trajectory of the target vehicle using millimeter wave radar data of the millimeter wave radar at each time after the calculated entry time, and calculates the position of the target vehicle at each time as a first tracking result;
a second tracking unit that calculates an entry time when the target vehicle enters the vehicle tracking section based on the detection time and the entry speed, tracks the travel trajectory of the target vehicle using image data of the camera at each time after the calculated entry time, and calculates the position of the target vehicle at each time as a second tracking result;
an integrated tracking unit that integrates the first tracking result and the second tracking result to determine a position of the target vehicle at each time as a final tracking result;
Equipped with
The integrated tracking unit determines whether the weather is bad based on the reflection intensity of laser light measured by the laser sensor, which is the vehicle detection sensor, and in the event of bad weather, places emphasis on the first tracking result to determine the final tracking result. The vehicle tracking system according to claim 1 , wherein the integrated tracking unit determines the final tracking result by placing importance on the first tracking result during nighttime. The vehicle tracking system according to claim 1 or 2 , wherein the integrated tracking unit determines the final tracking result by placing importance on the second tracking result with respect to a position in a width direction of the road. The vehicle tracking system according to any one of claims 1 to 3, wherein the integrated tracking unit determines the final tracking result by placing more importance on the second tracking result the closer the position of the target vehicle is to the second tracking sensor, and by placing more importance on the first tracking result the farther the position of the target vehicle is from the second tracking sensor. a vehicle detection sensor which is a laser sensor provided on a road and disposed above the road upstream of a vehicle tracking section of the road, irradiating a laser beam from above the road toward the road, scanning the road perpendicularly to the traffic direction, and detecting a vehicle traveling toward the vehicle tracking section of the road and passing below as a target vehicle;
a first tracking sensor that is a millimeter wave radar provided on the road and arranged upstream of the vehicle tracking section toward the vehicle tracking section, for tracking a travel trajectory of the target vehicle passing through the vehicle tracking section;
a second tracking sensor that is a camera provided on the road and arranged upstream of the vehicle tracking section toward the vehicle tracking section, for tracking a travel trajectory of the target vehicle passing through the vehicle tracking section;
A vehicle tracking device;
Equipped with
The vehicle tracking device includes:
a vehicle detection unit that detects the target vehicle using the vehicle detection sensor and detects the entry speed of the target vehicle ;
a first tracking unit that calculates an entry time of the target vehicle into the vehicle tracking section based on a detection time of the target vehicle and a detected entry speed, tracks the travel trajectory of the target vehicle using millimeter wave radar data of the millimeter wave radar at each time after the calculated entry time, and calculates the position of the target vehicle at each time as a first tracking result;
a second tracking unit that calculates an entry time when the target vehicle enters the vehicle tracking section based on the detection time and the entry speed, tracks the travel trajectory of the target vehicle using image data of the camera at each time after the calculated entry time, and calculates the position of the target vehicle at each time as a second tracking result;
an integrated tracking unit that prioritizes the second tracking result as the position of the target vehicle is closer to the camera and prioritizes the first tracking result as the position of the target vehicle is farther from the camera, and integrates the first tracking result and the second tracking result to determine the position of the target vehicle at each time as a final tracking result;
Equipped with
The integrated tracking unit determines the final tracking result by placing emphasis on the first tracking result calculated using the millimeter wave radar data for a position in the traffic direction of the road, and determines the final tracking result by placing emphasis on the second tracking result calculated using the image data for a position in the width direction of the road. The vehicle tracking system according to claim 5 , wherein the integrated tracking unit determines the final tracking result by placing importance on the first tracking result during nighttime. A vehicle detection unit provided in the vehicle tracking device detects, as a target vehicle, a vehicle traveling toward the vehicle tracking section of the road and passing under the laser sensor , using a vehicle detection sensor which is a laser sensor that is provided on a road and arranged above the road upstream of the vehicle tracking section of the road, and irradiates a laser light from above the road toward the road to scan perpendicularly to the traffic direction of the road,
a first tracking unit provided in the vehicle tracking device calculates, as a first tracking result, the position of the target vehicle passing through the vehicle tracking section at each time using a first tracking sensor that is a millimeter wave radar provided on the road and arranged upstream of the vehicle tracking section toward the vehicle tracking section;
a second tracking unit provided in the vehicle tracking device calculates, as a second tracking result, the position of the target vehicle passing through the vehicle tracking section at each time using a second tracking sensor which is a camera provided on the road and arranged upstream of the vehicle tracking section toward the vehicle tracking section;
A vehicle tracking method in which an integrated tracking unit provided in the vehicle tracking device integrates the first tracking result and the second tracking result to determine a position of the target vehicle at each time as a final tracking result,
The vehicle detection unit detects the target vehicle using the vehicle detection sensor and detects an approach speed of the target vehicle;
the first tracking unit calculates an entry time at which the target vehicle enters the vehicle tracking section based on a detection time at which the target vehicle is detected and a detected entry speed, and tracks a travel trajectory of the target vehicle using millimeter wave radar data of the millimeter wave radar at each time after the calculated entry time to calculate the first tracking result;
the second tracking unit calculates an entry time at which the target vehicle enters the vehicle tracking section based on the detection time and the entry speed, tracks a travel trajectory of the target vehicle using image data of the camera at each time after the calculated entry time, and calculates the second tracking result;
A vehicle tracking method in which the integrated tracking unit determines whether the weather is bad based on the reflection intensity of laser light measured by the laser sensor, which is the vehicle detection sensor, and when the weather is bad, determines the final tracking result by placing importance on the first tracking result. A vehicle detection unit provided in the vehicle tracking device detects, as a target vehicle, a vehicle that travels toward the vehicle tracking section of the road and passes below the laser sensor, using a vehicle detection sensor that is a laser sensor that is provided on a road and arranged above the road upstream of the vehicle tracking section of the road, and that irradiates laser light from above the road toward the road and scans perpendicularly to the traffic direction of the road,
a first tracking unit provided in the vehicle tracking device calculates, as a first tracking result, the position of the target vehicle passing through the vehicle tracking section at each time using a first tracking sensor that is a millimeter wave radar provided on the road and arranged upstream of the vehicle tracking section toward the vehicle tracking section;
a second tracking unit provided in the vehicle tracking device calculates, as a second tracking result, the position of the target vehicle passing through the vehicle tracking section at each time using a second tracking sensor which is a camera provided on the road and arranged upstream of the vehicle tracking section toward the vehicle tracking section;
A vehicle tracking method in which an integrated tracking unit provided in the vehicle tracking device integrates the first tracking result and the second tracking result by placing more importance on the second tracking result as the position of the target vehicle is closer to the camera and placing more importance on the first tracking result as the position of the target vehicle is farther from the camera, and determines the position of the target vehicle at each time as a final tracking result,
The vehicle detection unit detects the target vehicle using the vehicle detection sensor and detects an approach speed of the target vehicle;
the first tracking unit calculates an entry time at which the target vehicle enters the vehicle tracking section based on a detection time at which the target vehicle is detected and a detected entry speed, and tracks a travel trajectory of the target vehicle using millimeter wave radar data of the millimeter wave radar at each time after the calculated entry time to calculate the first tracking result;
the second tracking unit calculates an entry time at which the target vehicle enters the vehicle tracking section based on the detection time and the entry speed, tracks a travel trajectory of the target vehicle using image data of the camera at each time after the calculated entry time, and calculates the second tracking result;
The vehicle tracking method, in which the integrated tracking unit determines the final tracking result by placing emphasis on the first tracking result calculated using the millimeter wave radar data for a position in the traffic direction of the road, and determines the final tracking result by placing emphasis on the second tracking result calculated using the image data for a position in the width direction of the road.

Images