JP2021167770A - Target tracking device - Google Patents

Abstract

To improve tracking accuracy of a target in the vicinity of a detection area limit of a sensor.SOLUTION: In S110, a server acquires sensor information and target information from a plurality of sensors. In S130, the server sets a connecting area whose detection accuracy is lower than that of other parts of a detection area. In S140, the reliability of a predicted value and an observed value is set, respectively. In S180, the server adjusts the reliability of the predicted value forming a pair of the observed value and the corresponding value when the observed value is in the connecting area. In S190, the server updates the estimated value of the target associated with the corresponding value pair using the corresponding value pair and the reliability set for the corresponding value pair.SELECTED DRAWING: Figure 5

Description

The present disclosure relates to a technique for tracking a target using the position information of the target obtained from a plurality of sensors.

By intelligently combining the detection results of a plurality of types of sensors that detect a target, the performance of the system that uses the detected target information is improved and the functions are realized. In such a system, when tracking a target, the time-series observation information of the instantaneous value of the target position detected by the sensor is used to improve the estimation accuracy of the target position. However, it is known that in the vicinity of the limit of the detection area of the sensor, the tracking accuracy of the target is lowered due to the increase in observation error and false detection.

In Patent Document 1, in order to suppress such a decrease in tracking accuracy, a plurality of sensors are arranged so that a part of each other's detection area overlaps, so that the observation can be performed near the boundary of the detection area of the sensor. A technique for providing redundancy has been proposed.

Special Table 2019-519051

However, as a result of detailed examination by the inventor, it has been found that the above-mentioned prior art has the following problems. That is, when a plurality of sensors constituting the system include a sensor such as an in-vehicle sensor whose detection area moves, it is not always possible to provide redundancy in the vicinity of the boundary of the detection area, resulting in an observation error. There was a problem that the suppressive effect could not be sufficiently obtained.

In one aspect of the present disclosure, there is provided a technique for improving the tracking accuracy of a target near the limit of the detection area of the sensor.

One aspect of the present disclosure is a target tracking device, which includes an information acquisition unit (5: S110), a reliability setting unit (5: S140), an estimated value updating unit (5: S190), and an area setting unit. (5: S130) and a reliability adjusting unit (5: S180) are provided.

The information acquisition unit acquires the position information of the sensor, the sensor information including the detection area of the sensor, and the target information including the position of the detected target from the plurality of sensors. The reliability setting unit uses the position of the target estimated for each processing cycle as the estimated value, and the position of the target predicted from the estimated value in the previous processing cycle as the predicted value, and is acquired by the information acquisition unit. The position of the target indicated in the target information is used as the observed value, and the predicted value and the reliability of the observed value are set respectively. The estimated value update unit is associated with the corresponding value pair, which is the predicted value and the observed value representing the same target, and the reliability set by the reliability setting unit for the corresponding value pair. Update the target estimate. The area setting unit includes at least a part of the boundary of the detection area shown in the sensor information, and sets a connecting area in which the detection accuracy is lower than other areas in the detection area. When the observed value is in the connecting area, the reliability adjusting unit adjusts the reliability of the predicted value forming a pair of the observed value and the corresponding value so that the reliability is high.

According to such a configuration, it is possible to suppress a decrease in the estimation accuracy of the target position and, by extension, the tracking accuracy of the target due to an increase in the detection error of the sensor, that is, the error of the observed value.

It is a block diagram which shows the structure of the traffic control system. It is a block diagram which shows the structure of an in-vehicle terminal. It is a block diagram which shows the structure of an infrastructure sensor. It is a block diagram which shows the structure of a server. It is a flowchart of the tracking process executed by the server. It is explanatory drawing about setting of a connecting area. It is explanatory drawing which shows the relationship of the observed value, the predicted value, and the estimated value in a connecting area. It is a graph which shows the result of having calculated the estimated value by the simulation with and without the connecting area. It is explanatory drawing which shows the other setting method of the connection area. It is explanatory drawing which shows the simple setting method of the connection area.

Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.
[1. overall structure]
The traffic control system 1 shown in FIG. 1 integrates observation information acquired from a plurality of sensors existing in a traffic environment to estimate a target position, motion, etc., and notifies each terminal in the traffic environment of the estimation result. This will improve the accuracy of automatic driving and driving support.

The traffic control system 1 includes an in-vehicle terminal 2, an infrastructure sensor 3, and a server 5. The server 5 corresponds to a target tracking device.
[1-1. In-vehicle terminal]
The in-vehicle terminal 2 is mounted on the vehicle. As shown in FIG. 2, the in-vehicle terminal 2 includes an in-vehicle communication device 21, an out-of-vehicle communication device 22, and a processing unit 23. The in-vehicle communication device 21 acquires various information via the in-vehicle network of the vehicle (hereinafter, own vehicle) on which the in-vehicle terminal 2 is mounted. The out-of-vehicle communication device 22 executes communication with the server 5 by wireless communication. The processing unit 23 includes a microcomputer having a CPU and a memory such as a ROM and a RAM, and executes processing for realizing various functions.

The in-vehicle terminal 2 includes an information collecting unit 231 and an integrated information providing unit 232 as functional blocks representing functions realized by processing executed by the processing unit 23.
The information collecting unit 231 repeatedly collects the target information, the sensor information, and the vehicle state information via the in-vehicle communication device 21, and transmits the target information, the sensor information, and the vehicle state information to the server 5 via the out-of-vehicle communication device 22.

The target information is observation information related to the target detected by the peripheral monitoring sensor group 100 mounted on the vehicle. Peripheral monitoring sensor group 100 may include millimeter wave radar 101, lidar 102, ultrasonic sensor 103, camera 104, and the like. Hereinafter, these configurations belonging to the peripheral monitoring sensor group 100 are also simply referred to as sensors 101 to 104. The target information includes different information depending on the sensors 101 to 104 that are information generation sources, but in each case, at least the position of the detected target is included. In addition to the position of the target, the target information may include the distance to the target, the moving speed and direction of the target, the size of the target, the type of the target, and the like. The position of the target, the distance to the target, the moving speed of the target, and the moving direction may be represented by relative values with respect to the in-vehicle terminal 2.

The sensor information includes performance information relating to the performance of the individual sensors 101 to 104, and mounting information indicating the mounting state with respect to the own vehicle. The mounting information includes the height from the road surface, the mounting angle with respect to the straight direction and the horizontal direction of the vehicle. Performance information includes sensor type, detection distance range, and detection angle range. The detection distance range is a range of distances at which a target can be detected with an allowable accuracy under certain conditions. The detection angle range is a range of angles at which the target can be detected with an allowable accuracy under certain conditions. For certain conditions, for example, an illuminance value, a reflectance, or the like may be used. Further, as the permissible accuracy, it may be used that the detection probability is a certain value (for example, 95%) or more. Here, the center direction of the detection area A determined by the detection distance range and the detection angle range is the sensor front direction, and the mounting angle represents the sensor front direction. Further, the detection angle range is expressed with the front direction of the sensor as a reference (that is, 0 °).

The vehicle state information includes at least the position and the traveling direction of the vehicle detected by the position sensor 110 mounted on the vehicle. The position sensor 110 may be a device that obtains information by using GNSS (that is, a global navigation satellite system). That is, by combining the vehicle state information and the mounting information included in the sensor information, it is possible to specify the sensor position and the direction in the front direction of the sensor in the global coordinate system.

The integrated information providing unit 232 receives integrated information about targets and the like existing in the vicinity of the own vehicle from the server 5 via the external communication device 22, and automatically receives the received integrated information via the in-vehicle communication device 21. It is provided to each ECU that executes vehicle control related to driving and driving support.

[1-2. Infrastructure sensor]
The infrastructure sensor 3 is installed not only in traffic infrastructure such as road signs and traffic lights, but also in buildings on the side of the road. As shown in FIG. 3, the infrastructure sensor 3 includes a sensor main body 31, a communication device 32, and a processing unit 33.

The sensor body 31 includes, for example, a camera 311 and a radar 312. The sensor main body 31 is configured so that the orientation of the camera 311 and the radar 312 in the front direction of the sensor (that is, the posture of the sensor main body 31) can be changed by an instruction from the processing unit 33. Hereinafter, the camera 311 and the radar 312 are also simply referred to as sensors 311, 312.

The communication device 32 executes communication with the server 5 via a wired communication network or a wireless communication network.
The processing unit 33 includes a microcomputer having a CPU and memories such as ROM and RAM, and executes processing for realizing various functions. The infrastructure sensor 3 includes an information collecting unit 331 and a posture control unit 332 as functional blocks representing functions realized by processing executed by the processing unit 33.

The information collecting unit 331 repeatedly collects the target target information from the sensor main body 31, and transmits the collected target target information together with the sensor information and the attitude information to the server 5 via the communication device 32.
The target information and the sensor information are basically the same as the target information and the sensor information collected by the information collecting unit 231 of the in-vehicle terminal 2. However, the mounting information included in the sensor information includes the orientation in the front direction of the sensor (hereinafter, the reference front direction) when the sensor is in the preset reference posture. The attitude information includes the attitude of the sensor body 31 determined by the attitude control unit 332, that is, the orientation of the sensor in the front direction with respect to the reference front direction. That is, by combining the mounting information included in the sensor information and the attitude information, it is possible to specify the sensor position in the global coordinate system and the orientation in the front direction of the sensor.

If the infrastructure sensor 3 is configured so that the posture of the sensor main body 31 cannot be changed, the posture control unit 332 and the posture information may be omitted.
Here, the case where the infrastructure sensor 3 generates the target information and provides it to the server 5 has been described, but instead of the target information, the raw data obtained from the sensor main body 31 is provided to the server 5. You may. In this case, the server 5 needs a function of generating target information from the raw data acquired from the infrastructure sensor 3.

In the following, the sensors 101 to 104 belonging to the peripheral monitoring sensor group 100 and the sensors 311, 312 belonging to the sensor main body 31 are collectively referred to as a field sensor S, and when it is necessary to identify each field sensor S, Si is used. show. i is a positive integer. In FIG. 1, any of the sensors 101 to 104 belonging to the peripheral monitoring sensor group 100 mounted on the vehicle is referred to as S1 and S2, and any of the sensors 311, 312 belonging to the sensor main body 31 of the infrastructure sensor 3 is referred to as S3. .. Further, the detection areas of the field sensors S1 to S3 are represented by A1 to A3.

[1-3. server]
The server 5 acquires information from a plurality of field sensors Si existing in a traffic environment and integrates the acquired information to realize highly accurate and robust detection as compared with the detection of a single sensor. The integrated information which is the detection result is provided to the in-vehicle terminal 2.

As shown in FIG. 4, the server 5 includes a communication device 51, a processing unit 52, and a storage unit 53.
The communication device 51 executes communication with the vehicle-mounted terminal 2 and the infrastructure sensor 3.

The processing unit 52 includes a microcomputer having a CPU and a memory such as a ROM and a RAM, and executes processing for realizing various functions.
The server 5 includes an information generation unit 521 and an information distribution unit 522 as functional blocks representing functions realized by processing executed by the processing unit 52.

The information generation unit 521 uses the sensor information and the target information acquired from the plurality of field sensors S via the communication device 51 to generate integrated information that integrates the target information existing in the target area. The target area is an area to be processed by the server 5, and is allocated to the server 5 in advance. The integrated information includes at least the position information of the target. The details of the tracking process of tracking the target and sequentially updating the position information will be described later.

The information distribution unit 522 distributes the integrated information generated by the information generation unit 521 to the in-vehicle terminal 2 existing in the target area via the communication device 51.
The storage unit 53 stores at least a map of the target area and time-series information of the positions of the targets detected in the target area within a certain period in the past.

[2. Tracking process]
Next, the tracking process executed by the server 5 in order to realize a part of the function as the information generation unit 521 will be described with reference to the flowchart of FIG.

This process is repeatedly executed at regular intervals while the server 5 is running.
In S110, the server 5 acquires the target information and the sensor information received via the communication device 51 between the previous processing cycle and the current processing cycle.

In the following S120, the server 5 generates a sensor map showing the position of the field sensor S and the detection area on the map showing the target area based on the sensor information acquired in S110.

In the subsequent S130, the server 5 sets a connecting area CX in which the detection performance of the field sensor S deteriorates based on the detection area A of the field sensor S shown in the sensor map. For example, as shown in FIG. 6, the range from the inner side X [m] to the outer side Y [m] may be connected as the area CX with reference to the boundary of the detection area. Further, when the connecting area CX overlaps with the non-connecting area of the detection area of the other field sensor S, the overlapping portion is regarded as the non-connecting area. The non-connecting area here means a range excluding the connecting area CX from the detection area A.

In the following S140, the server 5 uses the predicted value for the target detected up to the previous processing cycle (hereinafter, tracking target) and the target indicated in the target information acquired in S110 (hereinafter, observation). Set the reliability for each of the observed values that are the positions of the target). The reliability is set based on at least one factor such as the type of sensor used for position detection, specifications, external environment (that is, the environment of the target area), type of tracking target, and speed.

For example, when the field sensor S from which the observed value is generated is the rider 102, which is easily affected by the weather, the reliability of the observed value is set high in the case of sunny weather and low in the case of rain or snow. May be good. Further, the higher the degree of agreement with the predicted value, the higher the reliability of the observed value may be set. Further, in the case of the predicted value, for example, the higher the elapsed time from the first recognition of the tracking target associated with the predicted value as the target, the higher the reliability may be set. Further, when the type of the tracking target associated with the predicted value is a target whose position can be easily predicted, such as a moving vehicle, the reliability of the predicted value may be set high.

In the subsequent S150, the server 5 selects one of the tracking targets, which has not yet been processed in S160 to S190 described later, as the target target.
In the following S160, the server 5 determines whether or not an observation target having a history connection with the target target exists, and if it exists, the process shifts to S170, and if it does not exist, the process shifts to S180. The presence or absence of the history connection can be determined by, for example, the distance between the object target and the observation target, but the present invention is not limited to this, and a known method for determining the presence or absence of the history connection is used. be able to. In the following, the combination of the predicted value and the observed value determined to have a historical connection is referred to as a corresponding value pair.

In S170, the server 5 determines whether or not the observed value is in the connecting area CX based on the predicted value of the target object and the observed value constituting the corresponding value pair, and if it is in the connecting area CX, the server 5 determines in S180. If it is not within the connection area CX, the process is transferred to S190.

In S180, the server 5 adjusts the reliability so that the reliability of the predicted value of the target object becomes high, and proceeds to the process in S190.
In S190, the server 5 sets the position (that is, the estimated value) of the target target according to the corresponding value pair and the reliability set in S140 or the reliability adjusted in S180 for the corresponding value pair. Update. Specifically, for example, the estimated value may be calculated by weighting addition of a corresponding value pair whose weight is reliability. Further, of the corresponding value pairs, the value having the higher reliability may be used as the estimated value as it is. When the predicted value of the target object and the observed value constituting the corresponding value pair are not extracted, the predicted value may be used as the estimated value as it is. It should be noted that an object target for which an observation target with a history connection has not been extracted consecutively up to a preset upper limit may be deleted from the tracking target as if it was lost.

Subsequently, in S200, the server 5 determines whether or not all the tracking targets have been selected as the target targets in the previous S150. When the server 5 determines that there is an unselected tracking target, it returns the process to S150, and when it determines that all the tracking targets have been selected, the server 5 shifts the process to S210.

In S210, the server 5 updates the tracking target and ends the process. Specifically, for the tracked target that has already been registered, the predicted value to be used in the next processing cycle is calculated using the estimated value updated in S190. Observatory targets for which no historical connection has been confirmed with any of the tracking targets are registered as new tracking targets, and the predicted values to be used in the next processing cycle are calculated based on the observed values.

In the tracking process, S110 corresponds to the information acquisition unit, S130 corresponds to the area setting unit, S140 corresponds to the reliability setting unit, S180 corresponds to the reliability adjustment unit, and S190 corresponds to the estimated value updating unit. Corresponds to.

[3. Operation example]
FIG. 7 shows a case where the detection areas A1 and A2 of the field sensors S1 and S2 do not overlap. When the target moves from the detection area A1 to the detection area A2, the accuracy of the observed value is lowered in the vicinity of the boundary between the detection areas A1 and A2 and in the range not belonging to any of the detection areas A1 and A2. Such an area becomes a connecting area CX. In FIG. 7, for convenience, the connecting area CX is shown as a rectangle.

In the connecting area CX, the predicted value of the tracking target indicated by the white triangle mark in FIG. 7 is higher than the observed value of the target target indicated by the black square mark in FIG. 7. The reliability is set higher than the observed value of the object target indicated by the black square mark. Therefore, in the connecting area CX, the estimated value is calculated with more emphasis on the predicted value than the observed value whose position accuracy is lowered.

As shown in FIG. 8, when the connecting area CX is not set, when the target moves across the detection areas A1 and A2, the detection error of the observed value near the boundary of the detection area increases. The estimated value calculated by using various observed values deviates greatly from the actual position. As a result, when the target straddles the detection areas A1 and A2, the last observed value detected by the field sensor S1 and the first observed value detected by the field sensor S2 are significantly different. May become. As a result, although the targets detected in both detection areas A1 and A2 are the same, they are recognized as different targets. On the other hand, when the connecting area CX is set, the reliability is adjusted in the connecting area CX so that the predicted value is emphasized. Therefore, as long as the way of moving the target does not change significantly, the estimated value does not deviate significantly from the true value, and the tracking accuracy of the target is maintained.

[4. effect]
According to the embodiment described in detail above, the following effects are obtained.
(4a) In the present embodiment, the connecting area CX, which is an area where the accuracy of the observed value is lowered, is set, and the connecting area CX is adjusted so that the reliability of the predicted value is high. Therefore, in the connecting area CX, it is possible to suppress a decrease in the estimation accuracy of the target position due to an increase in the detection error of the sensor, and eventually a decrease in the tracking accuracy of the target. Further, it is possible to suppress the occurrence of false detection and non-detection of the target in the connecting area CX.

[5. Other embodiments]
Although the embodiments of the present disclosure have been described above, the present disclosure is not limited to the above-described embodiments, and can be implemented in various modifications.

(5a) In the above embodiment, a predetermined range near the boundary of the detection area A of the field sensor S is set as the connecting area CX, but the present disclosure is not limited to this. For example, as shown in FIG. 9, all of the detection area A other than the non-connecting area set in the above embodiment may be set as the connecting area CX.

(5b) In the above embodiment, the connecting area CX is individually set for each detection area A, but the present disclosure is not limited to this. For example, as shown in FIG. 10, the connecting area CX may be set on a straight line connecting the two field sensors S1 and S2. In this case, as the connecting area CX, a rectangular shape having an area center on the straight line and formed by a side parallel to the vector V12 and having a side length of E1 and a side orthogonal to the vector AB and having a side length of E2. You may set the area. If the center of the connecting area CX is separated from the field sensor S1 by a distance D1, the distance D1 may be set so as to satisfy the equation (1). However, D is the distance between the field sensors S1 and S2, R1 is the detection distance of the field sensor S1, and R2 is the detection distance of the field sensor S2.

D1 / D = R1 / (R1 + R2) (1)
(5c) In the above embodiment, the connecting area CX is set regardless of the state of the tracking target, but the present disclosure is not limited to this. For example, when there is a tracking target that may move across the detection areas A1 and A2 of two adjacent field sensors S1 and S2, the connecting area CX is provided only between the two field sensors S1 and S2. May be set. For example, when the movement vector of the vector indicating the moving direction of the tracking target and the position vector indicating the direction of viewing the field sensor S2 from the field sensor S1 have a certain degree of parallelism, the tracking target has the detection area A1. , It may be determined that there is a possibility of moving across A2. The parallelism between the movement vector and the position vector may be determined, for example, by whether or not the inner product of the two normalized vectors is equal to or greater than a certain value.

(5d) The processing units 23, 33, 52 and methods thereof described in the present disclosure are by configuring a processor and memory programmed to perform one or more functions embodied by a computer program. It may be realized by the provided dedicated computer. Alternatively, the processing units 23, 33, 52 and methods thereof described in the present disclosure may be realized by a dedicated computer provided by configuring the processor with one or more dedicated hardware logic circuits. Alternatively, the processing units 23, 33, 52 and methods thereof described in the present disclosure consist of a processor and memory programmed to perform one or more functions and one or more hardware logic circuits. It may be realized by one or more dedicated computers configured in combination with a processor. The computer program may also be stored on a computer-readable non-transitional tangible recording medium as an instruction executed by the computer. The method of realizing the functions of each part included in the processing units 23, 33, and 52 does not necessarily include software, and all the functions are realized by using one or more hardware. May be good.

(5e) A plurality of functions possessed by one component in the above embodiment may be realized by a plurality of components, or one function possessed by one component may be realized by a plurality of components. .. Further, a plurality of functions possessed by the plurality of components may be realized by one component, or one function realized by the plurality of components may be realized by one component. Further, a part of the configuration of the above embodiment may be omitted. In addition, at least a part of the configuration of the above embodiment may be added or replaced with the configuration of the other above embodiment.

(5f) In addition to the server 5 as the target tracking device described above, a system having the target tracking device as a component, a program for operating a computer as the target tracking device, a semiconductor memory recording this program, and the like. The present disclosure can also be realized in various forms such as a non-transitional substantive recording medium and a position estimation method.

1 ... Traffic control system, 2 ... In-vehicle terminal, 3 ... Infrastructure sensor, 5 ... Server, 51 ... Communication device, 52 ... Processing unit, 53 ... Storage unit, 521 ... Information generation unit, 522 ... Information distribution unit, A ... Detection Area, CX ... Connecting area, S ... Field sensor.

Claims (4)

An information acquisition unit (5: S110) configured to acquire the position information of the sensor, the sensor information including the detection area of the sensor, and the target information including the detected position of the target from the plurality of sensors. ,
The target position estimated for each processing cycle is used as an estimated value, the target position predicted from the estimated value in the previous processing cycle is used as a predicted value, and the target acquired by the information acquisition unit is used as a predicted value. A reliability setting unit (5: S140) configured to set the predicted value and the reliability of the observed value, respectively, using the position of the target indicated in the target information as the observed value.
The predicted value representing the same target, the corresponding value pair which is the observed value, and the reliability set in the reliability setting unit for the corresponding value pair are used to associate the corresponding value pair with the corresponding value pair. An estimated value updating unit (5: S190) configured to update the estimated value of the target, and
An area setting unit (5: S130) that includes at least a part of the boundary of the detection area shown in the sensor information and is configured to set a connecting area whose detection accuracy is lower than that of other areas in the detection area. When,
When the observed value is in the connecting area, the reliability adjusting unit (reliability adjusting unit) configured to adjust the reliability of the predicted value forming the corresponding value pair with the observed value so as to increase the reliability. 5: S180) and
A target tracking device equipped with. The target tracking device according to claim 1.
The reliability adjusting unit is a target tracking device configured to adjust the reliability of the predicted value in which the observed value forming the corresponding value pair does not exist so that the reliability becomes high. The target tracking device according to claim 1 or 2.
The reliability setting unit includes the position of the observed value in the connecting area, the degree of agreement between the observed value and the predicted value, the type and speed of the target associated with the predicted value, and the target. The reliability is determined using at least one of the elapsed time since the first detection, the type and specifications of the sensor from which the observed value was generated, and the external environment when the observed value was acquired. A target tracking device configured to set. The target tracking device according to any one of claims 1 to 3.
The area setting unit is configured to set the connecting area between the detection areas of two adjacent sensors.
Target tracking device.

Images