Target detection device and target detection method
The target detection device adjusts radar sensor thresholds based on exterior component paint color information to address attenuation issues, improving object detection accuracy and driver assistance.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- TOYOTA JIDOSHA KK
- Filing Date
- 2023-03-22
- Publication Date
- 2026-07-29
AI Technical Summary
Radar sensors mounted inside vehicle exterior components face attenuation issues due to varying radio wave absorption by different materials, leading to inconsistent object detection thresholds.
A target detection device that adjusts the threshold value based on paint color information of the exterior components using a radar sensor, either during manufacturing or through real-time updates via a camera, to ensure accurate object detection.
Ensures appropriate threshold settings for radar sensors mounted inside vehicle exterior parts, enhancing the accuracy of object detection and providing reliable driver assistance.
Smart Images

Figure 0007896526000001 
Figure 0007896526000002 
Figure 0007896526000003
Abstract
Description
Technical Field
[0001] The present invention relates to an object detection device and an object detection method.
Background Art
[0002] Patent Document 1 describes that when a vehicle changes lanes, a peripheral monitoring mechanism provided on the vehicle detects an object behind and to the side of the vehicle, and notifies a warning to the driver of the vehicle as necessary.
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0004] As an example of such a peripheral monitoring mechanism, a radar sensor mounted inside an exterior component of a vehicle can be mentioned. The radar sensor transmits radio waves around the vehicle and receives the reflected waves of the transmitted radio waves. Based on the information of the reflected waves received by the radar sensor, an object around the vehicle can be detected.
[0005] However, when radio waves pass through an exterior component, attenuation of the radio waves occurs, and the amount of attenuation of the radio waves changes according to the characteristics of the exterior component. Therefore, if a threshold value used for object detection is set uniformly, there is a possibility that an object around the vehicle cannot be appropriately recognized.
[0006] Therefore, in view of the above problems, an object of the present invention is to set a threshold value used for object detection by a radar sensor to an appropriate value when the radar sensor is mounted inside an exterior component of a vehicle.
Means for Solving the Problems
[0007] The gist of the present disclosure is as follows.
[0008] (1) A target detection device comprising: a target determination unit that acquires the intensity of reflected waves generated by radio waves transmitted to the surrounding area of the vehicle from a radar sensor mounted inside the exterior parts of the vehicle, and determines that a target exists around the vehicle when the intensity of the reflected waves is equal to or greater than a threshold; and a threshold setting unit that sets the threshold based on the paint color information of the exterior parts.
[0009] (2) The target detection device described in (1) above, wherein the paint color information is written to the storage device of the vehicle during the manufacturing process of the vehicle.
[0010] (3) The target detection device according to (1) or (2) above, wherein the threshold setting unit acquires the paint color information based on an image of the exterior part generated by a camera provided on the vehicle.
[0011] (4) The target detection device according to any one of (1) to (3) above, wherein the threshold setting unit sets the threshold based on the paint color information and the shape information of the exterior parts.
[0012] (5) A computer-based target detection method, comprising: acquiring the intensity of reflected waves generated by radio waves transmitted to the surrounding area of a vehicle from a radar sensor mounted inside an exterior part of the vehicle; determining that a target exists around the vehicle when the intensity of the reflected waves is equal to or greater than a threshold; and setting the threshold based on paint color information of the exterior part. [Effects of the Invention]
[0013] According to the present invention, when a radar sensor is mounted inside a vehicle's exterior component, the threshold value used for target detection by the radar sensor can be set to an appropriate value. [Brief explanation of the drawing]
[0014] [Figure 1]This figure schematically shows a part of the configuration of a vehicle equipped with a target detection device according to the first embodiment of the present invention. [Figure 2] This figure shows the rear of a vehicle equipped with a target detection device according to the first embodiment of the present invention. [Figure 3] This is a functional block diagram of the ECU processor. [Figure 4] This is a flowchart showing the control routine for threshold setting processing in the first embodiment. [Figure 5] This figure shows the rear of a vehicle equipped with a target detection device according to the second embodiment of the present invention. [Figure 6] This is a flowchart showing the control routine for threshold setting processing in the second embodiment. [Modes for carrying out the invention]
[0015] Embodiments of the present invention will be described in detail below with reference to the drawings. In the following description, similar components will be given the same reference numerals.
[0016] <First Embodiment> The first embodiment of the present invention will be described below with reference to Figures 1 to 4. Figure 1 is a schematic diagram showing a part of the configuration of a vehicle 1 equipped with a target detection device according to the first embodiment of the present invention.
[0017] As shown in Figure 1, Vehicle 1 (the vehicle itself) is equipped with a radar sensor 2, an indicator 3, a buzzer 4, a brake actuator 5, and an electronic control unit (ECU) 10. The radar sensor 2, indicator 3, buzzer 4, and brake actuator 5 are electrically connected to the ECU 10 via an in-vehicle network compliant with standards such as CAN (Controller Area Network).
[0018] The radar sensor 2 transmits radio waves around the vehicle 1 and receives the reflected waves of the transmitted radio waves. The radar sensor 2 is, for example, a millimeter-wave radar in the 24 GHz band, 60 GHz band, 76 GHz band, or 79 GHz band. The radar sensor 2 uses the FMCW (Frequency Modulated Continuous Wave) method as the ranging method and transmits radio waves with a frequency that changes over time. Note that the radar sensor 2 may use the pulse method as the ranging method and transmit pulsed radio waves.
[0019] The output of the radar sensor 2, that is, the information on the reflected wave received by the radar sensor 2, is transmitted to the ECU 10. The information on the reflected wave includes the intensity, frequency, delay time, etc. of the reflected wave. The ECU 10 detects the presence or absence of a target, the distance from the vehicle 1 to the target, the relative speed between the vehicle 1 and the target, etc. based on the information on the reflected wave.
[0020] FIG. 2 is a view showing the rear part of the vehicle 1 provided with the target detection device according to the first embodiment of the present invention. In the present embodiment, the radar sensor 2 is provided inside the rear bumper 20 of the vehicle 1 and detects a target existing in the rear side area of the vehicle 1. In the example of FIG. 2, the radar sensor 2 includes a left radar sensor 2a disposed at the left end of the rear bumper 20 and a right radar sensor 2b disposed at the right end of the rear bumper 20. The left radar sensor 2a detects a target existing in the left rear area of the vehicle 1. The right radar sensor 2b detects a target existing in the right rear area of the vehicle 1.
[0021] The indicator 3 is a display lamp, for example, a light-emitting diode (LED). The indicator 3 is built into the door mirror of the vehicle 1 so as to be visible to the driver of the vehicle 1 and lights up according to the detection result of the target. In the present embodiment, as shown in FIG. 2, the indicator 3 includes a left indicator 3a built into the left door mirror 21 and a right indicator 3b built into the right door mirror 22. The ECU 10 controls the indicator 3 to control the lighting state of the indicator 3.
[0022] Buzzer 4 is located inside the vehicle and emits a buzzer sound to the driver of vehicle 1. The ECU 10 notifies the driver of vehicle 1 of the buzzer sound via buzzer 4.
[0023] The brake actuator 5 activates the brakes installed on the vehicle 1. The ECU 10 controls the braking of the vehicle 1 by controlling the brake actuator 5.
[0024] The ECU 10 performs various controls on the vehicle 1. As shown in Figure 1, the ECU 10 includes a communication interface 11, a memory 12, and a processor 13. The communication interface 11 and the memory 12 are connected to the processor 13 via signal lines. In this embodiment, one ECU 10 is provided, but multiple ECUs may be provided for each function.
[0025] The communication interface 11 has an interface circuit for connecting the ECU 10 to the in-vehicle network. The ECU 10 is connected to other in-vehicle equipment via the communication interface 11.
[0026] Memory 12 includes, for example, volatile semiconductor memory and non-volatile semiconductor memory. Memory 12 stores computer programs, data, etc., that are used when various processes are executed by the processor 13.
[0027] The processor 13 has one or more CPUs (Central Processing Units) and their peripheral circuits. The processor 13 may also have other arithmetic circuits such as a logic unit, a numerical unit, or a graphics processing unit.
[0028] In this embodiment, the ECU 10 functions as a target detection device that detects targets (surrounding vehicles, bicycles, pedestrians, etc.) around the vehicle 1. The target detection device detects targets around the vehicle 1 based on the output of the radar sensor 2.
[0029] Figure 3 is a functional block diagram of the processor 13 of the ECU 10. The processor 13 includes a target determination unit 14, a threshold setting unit 15, and a driving support unit 16. The target determination unit 14, the threshold setting unit 15, and the driving support unit 16 are functional modules that are realized by the execution of computer programs stored in the memory 12 of the ECU 10 by the processor 13 of the ECU 10. These functional modules may each be realized by dedicated arithmetic circuits provided in the processor 13.
[0030] The target determination unit 14 acquires the intensity of the reflected waves generated by the radio waves transmitted from the radar sensor 2 to the area around the vehicle 1, that is, the intensity of the reflected waves received by the radar sensor 2, and determines whether or not a target exists around the vehicle 1 based on the intensity of the reflected waves. Specifically, the target determination unit 14 determines that a target exists around the vehicle 1 when the intensity of the reflected waves is above a threshold, and determines that no target exists around the vehicle 1 when the intensity of the reflected waves is below the threshold.
[0031] However, when radio waves are transmitted from the radar sensor 2 toward the surroundings of the vehicle 1, and when radio waves reflected by targets around the vehicle 1 return to the radar sensor 2, the radio waves penetrate the exterior parts of the vehicle 1 on which the radar sensor 2 is mounted. When radio waves penetrate the exterior parts of the vehicle 1, attenuation occurs, and the amount of attenuation varies depending on the characteristics of the exterior parts. For example, if a metal such as indium is included in the paint color of the exterior parts, the amount of attenuation of radio waves will increase, and the intensity of the reflected waves will decrease.
[0032] Therefore, in this embodiment, the threshold setting unit 15 sets a threshold based on the paint color information of the exterior parts of the vehicle 1 on which the radar sensor 2 is mounted. This makes it possible to set an appropriate threshold value for target detection by the radar sensor 2 when the radar sensor 2 is mounted inside the exterior parts of the vehicle 1.
[0033] In this embodiment, as shown in Figure 2, the radar sensor 2 is mounted inside the rear bumper 20 of the vehicle 1. Therefore, the threshold setting unit 15 sets the threshold based on the paint color information of the rear bumper 20. The paint color information is written to the storage device of the vehicle 1 (for example, the memory 12 of the ECU 10) as part of the vehicle information during the manufacturing process (assembly process) of the vehicle 1. This allows the threshold setting unit 15 to refer to the paint color information when setting the threshold.
[0034] The driver assistance unit 16 performs processing to assist the driver of vehicle 1 based on the detection results of objects around vehicle 1. For example, if the object detection unit 14 determines that an object exists around vehicle 1, the driver assistance unit 16 notifies the driver of vehicle 1 of a warning via an output device of vehicle 1, such as an indicator 3 or a buzzer 4.
[0035] As a specific example, the driver assistance unit 16 illuminates the left indicator 3a when it determines that there is a vehicle to the left rear of vehicle 1, and illuminates the right indicator 3b when it determines that there is a vehicle to the right rear of vehicle 1. In addition, if the driver assistance unit 16 determines that there is a target (for example, a vehicle, pedestrian, or bicycle) around vehicle 1, it emits a buzzer sound from the buzzer 4 to indicate the presence of the target. The driver assistance unit 16 may also display an image or text indicating the presence of the target on a display installed in vehicle 1 (for example, an instrument panel or a head-up display (HUD)). Furthermore, if there is a risk that vehicle 1 will collide with a target around vehicle 1, the driver assistance unit 16 activates the brakes using the brake actuator 5.
[0036] The following describes the processing flow for setting the threshold used for target detection, with reference to Figure 4. Figure 4 is a flowchart of the control routine for the threshold setting process in the first embodiment. This control routine is executed only once by the processor 13 of the ECU 10, for example, after the paint color information has been written to the storage device of the vehicle 1.
[0037] First, in step S101, the threshold setting unit 15 of the processor 13 obtains paint color information of the rear bumper 20 from the vehicle 1's storage device (for example, the memory 12 of the ECU 10).
[0038] Next, in step S102, the threshold setting unit 15 sets a threshold based on the paint color information of the rear bumper 20. For example, the threshold setting unit 15 sets the threshold using a table that shows the relationship between the paint color of the rear bumper 20 and the threshold. The table is created in advance based on experimental results using the radar sensor 2, etc. For paint colors with a large amount of radio wave attenuation, the threshold is set lower compared to paint colors with a small amount of radio wave attenuation. After step S102, this control routine ends.
[0039] <Second Embodiment> The target detection device according to the second embodiment is basically the same as the target detection device according to the first embodiment in terms of configuration and control, except for the points described below. Therefore, the second embodiment of the present invention will be described below focusing on the parts that differ from the first embodiment.
[0040] In the first embodiment, paint color information written to the storage device of vehicle 1 during the manufacturing process is acquired in order to set a threshold used for target detection. However, the exterior parts of vehicle 1 may be replaced according to the preferences of the vehicle owner, etc. If the paint color of the exterior parts is changed due to the replacement of exterior parts, it is desirable to adjust the threshold to match the changed paint color.
[0041] Therefore, in the second embodiment, the threshold setting unit 15 acquires paint color information of the exterior parts of the vehicle 1 based on images of the exterior parts of the vehicle 1 generated by a camera installed on the vehicle 1. This makes it possible to optimize the threshold even when the paint color of the exterior parts is changed.
[0042] Figure 5 shows the rear of a vehicle 1' equipped with a target detection device according to a second embodiment of the present invention. In the second embodiment, the vehicle 1' is equipped with a side camera 6. In the example of Figure 5, the side camera 6 is positioned below the left door mirror 21 and captures the left side area of the vehicle 1'. The shooting range of the side camera 6 includes a portion of the rear bumper 20, and the side camera 6 generates an image of the rear bumper 20.
[0043] Figure 6 is a flowchart of the control routine for threshold setting processing in the second embodiment. This control routine is executed by the processor 13 of the ECU 10 each time the ignition switch of the vehicle 1' is turned on, for example, after the initial value of the threshold has been set by the control routine in Figure 4.
[0044] First, in step S201, the threshold setting unit 15 of the processor 13 acquires an image of the rear bumper 20 generated by the side camera 6.
[0045] Next, in step S202, the threshold setting unit 15 acquires paint color information of the rear bumper 20 based on the image of the rear bumper 20. For example, the threshold setting unit 15 acquires paint color information of the rear bumper 20 using a classifier that has been pre-trained to output the paint color of the rear bumper 20 from the image data of the rear bumper 20. Examples of such classifiers include machine learning models such as neural networks, support vector machines, and random forests.
[0046] Next, in step S203, the threshold setting unit 15 determines whether or not the paint color of the rear bumper 20 has been changed. For example, the threshold setting unit 15 determines that the paint color of the rear bumper 20 has been changed if the paint color information written to the storage device of the vehicle 1' is different from the paint color information obtained from the image of the rear bumper 20. The threshold setting unit 15 also determines that the paint color of the rear bumper 20 has been changed if the paint color information obtained from the image of the rear bumper 20 has been updated. If it is determined in step S203 that the paint color of the rear bumper 20 has not been changed, this control routine terminates.
[0047] On the other hand, if it is determined in step S203 that the paint color of the rear bumper 20 has been changed, the control routine proceeds to step S204. In step S204, the threshold setting unit 15 updates the threshold by setting the threshold based on the changed paint color of the rear bumper 20. For example, similar to step S102 in Figure 4, the threshold setting unit 15 sets the threshold using a table that shows the relationship between the paint color of the rear bumper 20 and the threshold. After step S204, the control routine terminates.
[0048] Furthermore, the camera that generates images of the exterior parts of the vehicle 1' equipped with the radar sensor 2 may be located at other locations on the vehicle 1', as long as at least a portion of the exterior parts is included in its shooting range. Also, the step of writing paint color information to the vehicle 1's storage device may be omitted, and the control routine in Figure 4 may not be executed. In this case, if the initial value of the threshold has not yet been set, step S203 is skipped after step S202, and the initial value of the threshold is set in step S204.
[0049] Although preferred embodiments of the present invention have been described above, the present invention is not limited to these embodiments, and various modifications and changes can be made within the scope of the claims.
[0050] For example, the radar sensor 2 may be mounted on the front of vehicles 1 and 1' to detect targets in front of the vehicles 1 and 1'. Alternatively, the radar sensor 2 may be mounted inside the front bumper, emblem, grille cover, etc., of vehicles 1 and 1'.
[0051] Furthermore, when radio waves pass through the exterior parts of vehicles 1 and 1', the amount of attenuation of the radio waves is also affected by the shape of the exterior parts. For this reason, the threshold setting unit 15 may set the threshold based on the paint color information and shape information of the exterior parts. This makes it possible to set the threshold to a more appropriate value that also takes into account the shape of the exterior parts. In this case, the shape information is written to the storage device of vehicle 1 (for example, the memory 12 of the ECU 10) as one of the vehicle information during the manufacturing process of vehicle 1.
[0052] Furthermore, the computer program that enables the computer to implement the functions of each part of the processor 13 of the ECU 10 may be provided in the form of a recording medium that can be read by the computer. The recording medium that can be read by the computer may be, for example, a magnetic recording medium, an optical recording medium, or a semiconductor memory. [Explanation of Symbols]
[0053] 1, 1' Vehicle 10. Electronic Control Unit (ECU) 13 processors 14 Target object determination section 15. Threshold setting section 20 Rear Bumper
Claims
1. A target determination unit acquires the intensity of reflected waves generated by radio waves transmitted to the surrounding area of the vehicle from a radar sensor mounted inside the exterior parts of the vehicle, and determines that a target exists around the vehicle when the intensity of the reflected waves is above a threshold. A threshold setting unit sets the threshold based on the paint color of the exterior parts. Equipped with, The threshold setting unit acquires the paint color based on an image of the exterior part generated by a camera installed on the vehicle, and updates the threshold if the paint color written to the vehicle's storage device during the vehicle's manufacturing process differs from the paint color acquired based on the image.
2. The target detection device according to claim 1, wherein the threshold setting unit sets the threshold based on the paint color and the shape information of the exterior parts.
3. A computer-based target detection method, This involves obtaining the intensity of reflected waves generated by radio waves transmitted to the surrounding area of the vehicle from a radar sensor mounted inside the exterior parts of the vehicle, When the intensity of the reflected wave is above a threshold, it is determined that a target exists around the vehicle. Setting the threshold based on the paint color of the exterior parts, The paint color is obtained based on an image of the exterior part generated by a camera installed on the vehicle, In the manufacturing process of the vehicle, if the paint color written to the vehicle's storage device differs from the paint color obtained based on the image, the threshold is updated. A target detection method, including the following.