Object detection device

Abstract

The object detection device (100) includes a radar signal processor (3) that processes a signal received from a radar transmitter / receiver (1) to detect the position, speed, and size of an object; a camera image processor (4) that detects the position, type, and size of an object based on image data captured by a camera image capturer (2); and a fusion processor (5) that performs identity determination processing between the object detected by the radar signal processor (3) and the object detected by the camera image processor (4) based on the position and size of the object detected by the radar signal processor (3) and the position and size of the object detected by the camera image processor (4), and uses the result of the identity determination processing for vehicle control.

Description

[Technical Field]

[0001] The present disclosure relates to an object detection device mounted on a vehicle. [Background technology]

[0002] Vehicle-mounted object detection devices have the function of quickly detecting objects in the vehicle's environment and controlling the vehicle and issuing warning notifications, contributing to safe vehicle driving. Object detection devices use various types of sensors, such as radar, cameras, LiDAR (Light Detection And Ranging), and ultrasonic sensors. In recent years, fusion-type object detection devices, which combine multiple sensors to improve performance, have become widely used.

[0003] In such a fusion-type object detection device, when the sensor is composed of a radar and a camera, since radar is excellent at detecting position and speed and a camera is excellent at recognizing objects, it is common to use radar detection data for position and speed and camera recognition data for object recognition (for example, Patent Document 1).

[0004] In recent years, object detection devices have become increasingly common in specialized vehicles such as excavators, wheel loaders, bulldozers, and dump trucks used at construction and civil engineering sites, and expectations are high for the effectiveness of fusion-type object detection devices that combine radar and cameras. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] International Publication No. 2022 / 254610 Summary of the Invention [Problem to be solved by the invention]

[0006] However, in a fusion-type object detection device using radar and a camera, an identity determination process that links object detection information is essential, but various obstacles such as traffic cones and containers exist at construction or civil engineering work sites. Therefore, if obstacles such as special vehicles other than the vehicle, traffic cones, and containers exist near the desired detection target object (e.g., a person), the identity determination process fails, resulting in a problem of reduced position accuracy. Failure of the identity determination process can cause erroneous control or false alarms in operations such as vehicle control or warning notification.

[0007] The present disclosure has been made in consideration of the above, and aims to provide an object detection device that can improve the matching accuracy of the identity determination process for detected objects, suppress a decrease in positional accuracy, and reduce the occurrence of erroneous control and false alarms in operations such as vehicle control and alarm notification. [Means for solving the problem]

[0008] In order to solve the above-mentioned problems and achieve the object, the object detection device of the present disclosure processes a received signal from a radar transmitter and receiver to detect the position and velocity of an object. , and the reception strength is detected, and based on the position of the detected object and the reception strength of the object, a radar signal processor that detects the size of an object; a camera image processor that detects the position, type and size of an object based on image data captured by a camera image capturer; and a camera image processor that processes the position of the object detected by the radar signal processor. The first object position is and object size The first object size is and the position of the object detected by the camera image processor. The second object position is and object size The second object size is Based on A first absolute value, which is the absolute value of the difference between the first object position and the second object position, and a second absolute value, which is the absolute value of the difference between the first object size and the second object size, are calculated, and a weighted average of the first absolute value and the second absolute value is calculated. The system is provided with a fusion processor that executes identity determination processing between the object detected by the radar signal processor and the object detected by the camera image processor, and uses the result of the identity determination processing for vehicle control. [Effects of the Invention]

[0009] The object detection device disclosed herein has the effect of improving the matching accuracy of the identity determination process for detected objects, suppressing a decrease in positional accuracy, and reducing the occurrence of erroneous control and false alarms in operations such as vehicle control and warning notifications. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a block diagram illustrating a configuration of an object detection device according to a first embodiment. [Figure 2] 1 is a flowchart showing an object detection process performed by the object detection device according to the first embodiment; [Figure 3] FIG. 10 is a block diagram illustrating a configuration of an object detection device according to a second embodiment. [Figure 4] 10 is a flowchart showing an object detection process performed by an object detection device according to a second embodiment. [Figure 5] FIG. 1 is a block diagram showing a configuration example of a processing circuit included in an object detection device according to first and second embodiments. DETAILED DESCRIPTION OF THE INVENTION

[0011] An object detection device according to an embodiment will be described below with reference to the drawings.

[0012] Embodiment 1 FIG. 1 is a block diagram showing the configuration of an object detection device 100 according to a first embodiment. The object detection device 100 is a fusion-type object detection device that combines radar and a camera, and calculates object detection data based on data obtained from the radar and the camera. The detection data output by the object detection device 100 is used for vehicle control, etc. The object detection device 100 includes a radar transceiver 1, a camera image capturer 2, a radar signal processor 3, a camera image processor 4, and a fusion processor 5. The output of the object detection device 100 is input to a vehicle control unit 30 mounted on the vehicle and used for vehicle control. In the following description, the term "object" refers to a detection target object that is desired to be detected when controlling the vehicle, and includes a person, a vehicle, an obstacle, etc. Examples of obstacles include special vehicles other than the host vehicle, traffic cones, containers, etc.

[0013] The radar transceiver 1 emits electromagnetic waves toward an object and receives the reflected signal from the object. The radar signal processor 3 processes the received signal from the radar transceiver 1 to detect the object's position, speed, and size. For vehicle-mounted applications, the radar transceiver 1 generally uses the FMCW (Frequency Modulated Continuous Wave) method or the FCM (Fast Chirp Modulation) method, and is composed of high-frequency semiconductor components, power semiconductor components, substrates, crystal devices, chip components, antennas, etc.

[0014] The radar signal processor 3 typically includes an MCU (Micro Control Unit), a CPU (Central Processing Unit), etc. The radar signal processor 3 includes a distance detector 6, a speed detector 7, a horizontal angle detector 8, a reception intensity detector 9, an object size detector 10, and a radar detection data storage unit 12. The distance detector 6, the speed detector 7, and the horizontal angle detector 8 detect the distance, speed, and horizontal angle of an object by performing Fast Fourier Transform (FFT) calculations in the distance direction, speed direction, and horizontal angle direction, respectively. The horizontal angle detector 8 calculates the object's position, which is the object's position relative to the vehicle, based on the horizontal angle and distance. The radar detection data storage unit 12 stores the position and speed data of the object detected by the radar transceiver 1.

[0015] The reception intensity detection unit 9 detects the intensity of the reflected signal of the electromagnetic wave from the object. Specifically, the reception intensity detection unit 9 performs FFT processing in the distance direction and the velocity direction, and treats the peak level as the reflected signal intensity of the electromagnetic wave. The object size detection unit 10 detects the object size based on the reception intensity detected by the reception intensity detection unit 9 and the object position stored in the radar detection data storage unit 12. The radar detection data storage unit 12 stores the object size data detected by the object size detection unit 10.

[0016] The camera image capturer 2 captures an image of the surroundings including the area ahead of the vehicle to obtain image data. The camera image capturer 2 is composed of components such as a lens, a holder, a CMOS (Complementary Metal Oxide Semiconductor) sensor, power semiconductor components, and a quartz device. The camera image processor 4 detects the position, size, and type of object (recognized object type) based on the image data captured by the camera image capturer 2.

[0017] An MCU, a CPU, a GPU (Graphics Processing Unit), or the like is used as the camera image processor 4. The camera image processor 4 has an object recognition unit 13, a position detection unit 14, a detection frame assignment unit 15, an object size detection unit 16, and a camera detection data storage unit 17.

[0018] The object recognition unit 13 recognizes objects such as people and vehicles from image data captured by the camera image capturer 2 using feature quantities obtained by deep learning as an object recognition database. For object recognition in the object recognition unit 13, a deep learning network algorithm such as YOLO (You Only Look Once) or SSD (Single Shot multibox Detector) is used. The object recognition unit 13 may also recognize objects using a method other than deep learning. For example, this can be achieved by processing such as machine learning or the HOG (Histograms of Oriented Gradients) method. The object recognition unit 13 obtains a recognition result including a recognized object type indicating the type of object.

[0019] The position detection unit 14 detects the position of an object based on the pixel coordinates of the object recognized by the object recognition unit 13. The detection frame assignment unit 15 assigns a detection frame to the area in which the object is recognized by the object recognition unit 13. In other words, only the desired object is extracted from the image, and this extracted area becomes the recognized object. The detection frame assignment unit 15 assigns a detection frame to the extracted area. The object size detection unit 16 calculates the object size based on the detection frame size of the detection frame assigned by the detection frame assignment unit 15. The camera detection data storage unit 17 stores data on the object position, object size, and recognized object type, and outputs this data to the subsequent fusion processor 5.

[0020] The fusion processor 5 includes an object identity determination unit 18 and a detection data storage unit 19. The object identity determination unit 18 executes identity determination processing to determine whether the object detected by the radar signal processor 3 is the same as the object detected by the camera image processor 4, based on the position and size of the object detected by the radar signal processor 3 and the position and size of the object detected by the camera image processor 4. The object identity determination unit 18 includes a position identity detection unit 18a, an object size identity detection unit 18b, and an identity determination unit 18c.

[0021] The position identity detection unit 18a determines whether the positions of the two detected objects are the same based on the position of the object detected by the radar signal processor 3 and the position of the object detected by the camera image processor 4, and inputs the determination result to the identity determination unit 18c. The object size identity detection unit 18b determines whether the sizes of the two detected objects are the same based on the object size detected by the radar signal processor 3 and the object size detected by the camera image processor 4, and inputs the determination result to the identity determination unit 18c. The identity determination unit 18c determines whether the object detected by the radar signal processor 3 is the same as the object detected by the camera image processor 4, based on the determination results of the position identity detection unit 18a and the object size identity detection unit 18b. If the identity determination fails, the identity determination unit 18c discards the data on the position, speed, and object size of the object detected by the radar signal processor 3 and the data on the position, object size, and recognized object type of the object detected by the camera image processor 4. If the identity determination is successful, the identity determination unit 18c links the position and speed data detected by the radar signal processor 3 with the recognized object type data detected by the camera image processor 4, and transfers and stores the linked position and speed data detected by the radar signal processor 3 and the recognized object type data detected by the camera image processor 4 to the detection data storage unit 19. The detection data storage unit 19 stores the position and speed data detected by the radar signal processor 3 and the recognized object type data detected by the camera image processor 4. The object position and speed data and the recognized object type data stored in the detection data storage unit 19 are transferred to the vehicle control unit 30 and used for vehicle control.

[0022] 2 is a flowchart showing an object detection processing procedure performed by object detection device 100 according to the first embodiment. The operation of object detection device 100 according to the first embodiment will be described with reference to FIG.

[0023] First, when object detection processing for the current frame is started (step S1), received data acquired by the radar transceiver 1 is output to the radar signal processor 3 (step S2). The distance detector 6, speed detector 7, and horizontal angle detector 8 of the radar signal processor 3 detect the position and speed of the object, respectively (step S3). The reception intensity detector 9 of the radar signal processor 3 detects the radar reflection intensity (reception intensity) (step S4). Next, the object size detector 10 detects the object size S radar based on the reception intensity detected by the reception intensity detector 9 and the object position (step S5).

[0024] The object size S radar is calculated as shown in equation (1) using the distance to the object R radar, the reception strength Pr, and constants α radar and β radar. Sradar = αradar × Pr × Rradar 4 +βradar (1)

[0025] According to the radar equation, the reception strength of electromagnetic waves received by radar attenuates as the fourth power of the distance, and equation (1) utilizes this characteristic. The distance to the object, Rradar, is calculated as in equation (2) using the position coordinates xr, yr of the radar detection data. xr indicates position information in the direction perpendicular to the optical axis of the object detection device 100, and yr indicates position information in the direction horizontal to the optical axis of the object detection device 100. xr, yr are defined on a plane parallel to the ground. √(A) means the square root of A. Note that the radar range r is detected directly, so the range r may also be used as the distance Rradar to the object. R radar = √(xr 2 +yr 2 ) ···(2)

[0026] The constants α radar and β radar are adjustment parameters set to account for variations in individual performance of the object detection device 100 and to align the object size detected by the radar signal processor 3 in the object identity determination unit 18 with the object size detected by the camera image processor 4.

[0027] The radar detection data storage unit 12 stores data on the position and speed of the detected object, and data on the size of the object detected by the object size detection unit 10 (step S6).

[0028] On the other hand, when object detection processing for the current frame is started (step S1), image data captured by the camera image capturer 2 is output to the camera image processor 4 (step S7). The object recognition unit 13 of the camera image processor 4 recognizes an object based on the captured image data and the object recognition feature database (step S8). The object recognition unit 13 outputs a recognition result including the recognized object type. The position detection unit 14 detects the position of the object based on the pixel coordinates of the recognized object (step S9). Furthermore, the detection frame attachment unit 15 adds a frame surrounding the recognized object to the image data (step S10). The object size detection unit 16 detects the object size Scamera based on the size of the attached frame (step S11).

[0029] The object size Scamera is calculated using the frame size Sf and constants αcamera and βcamera as in equation (3). As the frame size Sf, for example, the total number of pixels contained in the frame is used. Scamera=αcamera×Sf+βcamera (3)

[0030] The constants αcamera and βcamera are adjustment parameters set to account for variations in individual performance of the object detection device 100 and to align the object size detected by the camera image processor 4 in the object identity determination unit 18 with the object size detected by the radar signal processor 3.

[0031] The camera detection data storage unit 17 stores data on the position and size of the detected object, and data on the type of the recognized object (step S12).

[0032] The object identity determination unit 18 of the fusion processor 5 determines whether the object detected by the radar signal processor 3 and the object detected by the camera image processor 4 are the same based on the position and object size data transferred from the radar detection data memory unit 12 and the position and object size data transferred from the camera detection data memory unit 17 (step S13).

[0033] Specifically, the position identity detection unit 18a calculates the difference between the position of the object detected by the radar signal processor 3 and the position of the object detected by the camera image processor 4, and inputs the calculated difference to the identity determination unit 18c. For example, the position identity detection unit 18a calculates the absolute value |(Rradar-Rcamera)| of the difference between the distance Rradar to the object detected by the radar and the distance Rcamera to the object detected by the camera, and inputs the result to the identity determination unit 18c.

[0034] The distance Rcamera to the object detected by the camera is calculated as shown in equation (4) using xc and yc, which are positions stored in camera detection data storage unit 17. xc indicates position information in the direction perpendicular to the optical axis of object detection device 100, and yc indicates position information in the direction horizontal to the optical axis of object detection device 100. xc and yc are defined on a plane parallel to the ground. Rcamera=√(xc 2 +yc 2 ) (4)

[0035] The object size identity detection unit 18b calculates the difference between the object size Sradar detected by the radar signal processor 3 and the object size Scamera detected by the camera image processor 4, and inputs the absolute value of the calculated difference |(Sradar-Scamera)| to the identity determination unit 18c.

[0036] The identity determination unit 18c calculates the identity determination parameter Jrc as shown in equation (5) by calculating the weighted average of the absolute value |(Rradar-Rcamera)| of the difference between the distance to the object detected by the radar Rradar and the distance to the object detected by the camera Rcamera, and the absolute value |(Sradar-Scamera)| of the difference between the object size Sradar detected by the radar signal processor 3 and the object size Scamera detected by the camera image processor 4. Jrc=Wr×|(Rradar-Rcamera)|+Ws×|(Sradar-Scamera)| ···(5)

[0037] Wr and Ws are weighting coefficients, and decimal values ​​whose sum is 1 are used.

[0038] The identity determination unit 18c compares the identity determination parameter Jrc with a threshold value Th and determines whether the identity determination was successful or unsuccessful. If the parameter Jrc is greater than the threshold value Th, it is determined that the object detected by the radar and the object detected by the camera are not the same, and it is determined that the identity determination has failed (step S14: No). If the identity determination has failed, the radar detection data storage unit 12 discards the stored data of the speed, position, and object size for which the identity determination has failed, and the camera detection data storage unit 17 discards the stored data of the position, object size, and recognized object type for which the identity determination has failed (step S15).

[0039] On the other hand, if the parameter Jrc is equal to or less than the threshold value Th, the identity determination unit 18c determines that the object detected by the radar and the object detected by the camera are the same, and determines that the identity determination has been successful (step S14: Yes). If the identity determination has been successful, the identity determination unit 18c transfers the position and speed data detected by the radar and the data on the recognized object type detected by the camera to the detection data storage unit 19, and stores these data in the detection data storage unit 19 (step S16).

[0040] The object position and speed data and the recognized object type data stored in the detection data storage unit 19 are output to the vehicle control unit 30 (step S17). The vehicle control unit 30 uses the object position, speed, and recognized object type data acquired in step S17 for vehicle control (step S18). This completes the object detection process. Thereafter, the object detection process proceeds to the next frame (step S19), and the same process is repeatedly executed from step S1.

[0041] As described above, in the first embodiment, the object size is calculated from the radar detection information and the camera detection information, and these object sizes are used in the identity determination process. This improves the accuracy of the matching in the identity determination process of a fusion-type object detection device that combines radar and a camera. As a result, it is possible to suppress a decrease in position accuracy and reduce the occurrence of erroneous control and false alarms in operations such as vehicle control and warning notifications. Therefore, even at construction or civil engineering sites where various obstacles such as special vehicles, traffic cones, and containers are present, it is possible to improve the accuracy of the matching in the identity determination process and reduce the occurrence of erroneous control and false alarms.

[0042] Embodiment 2 FIG. 3 is a block diagram showing the configuration of an object detection device 100 according to a second embodiment. In the second embodiment, the speed of an object is added to the parameters for identity determination. For this reason, in the second embodiment, a speed detection unit 20 is provided in the camera image processor 4, and the speed of the object detected by the camera is stored in the camera detection data storage unit 17. In addition, in the second embodiment, a speed identity detection unit 18d is provided in the object identity determination unit 18. Other configurations in the second embodiment are the same as those in the first embodiment, and the same reference numerals are used to omit redundant explanations.

[0043] The speed detection unit 20 of the camera image processor 4 calculates the speed of the object based on the image data captured by the camera image capturer 2, and stores the calculated speed in the camera detection data storage unit 17.

[0044] The velocity identity detection unit 18d of the object identity determination unit 18 calculates the difference between the velocity Vradar of the object detected by the radar signal processor 3 and the velocity Vcamera of the object detected by the camera image processor 4, and inputs the absolute value of the calculated difference |(Vradar-Vcamera)| to the identity determination unit 18c. The identity determination unit 18c calculates a weighted average of three absolute values ​​based on the absolute value |(Rradar-Rcamera)| of the difference between the distance Rradar to the object detected by the radar and the distance Rcamera to the object detected by the camera, the absolute value |(Sradar-Scamera)| of the difference between the object size Sradar detected by the radar signal processor 3 and the object size Scamera detected by the camera image processor 4, and the absolute value |(Vradar-Vcamera)| of the difference between the velocity Vradar of the object detected by the radar signal processor 3 and the velocity Vcamera of the object detected by the camera image processor 4, thereby calculating a parameter Jrc for identity determination. Specifically, the identity determination unit 18c calculates the identity determination parameter Jrc as shown in equation (6): Wr, Wv, and Ws are weighting coefficients, and decimal values ​​whose sum is 1 are used. Jrc=Wr×|(Rradar-Rcamera)|+Wv×|(Vradar-Vcamera)| +Ws×|(Sradar-Scamera)| ···(6)

[0045] The identity determination unit 18c compares the identity determination parameter Jrc with a threshold value Th to determine whether the identity determination was successful or unsuccessful. If the parameter Jrc is greater than the threshold value Th, it determines that the object detected by the radar and the object detected by the camera are not the same, and if the parameter Jrc is equal to or less than the threshold value Th, it determines that the object detected by the radar and the object detected by the camera are the same.

[0046] Fig. 4 is a flowchart showing an object detection processing procedure performed by object detection device 100 according to embodiment 2. The operation of object detection device 100 according to embodiment 2 will be described with reference to Fig. 4. In Fig. 4, steps that perform the same operations as those in Fig. 2 are assigned the same step numbers, and duplicated explanations will be omitted.

[0047] In step S9', the position detection unit 14 detects the position of the recognized object based on the pixel coordinates of the recognized object, and the speed detection unit 20 detects the speed of the object based on the image of the recognized object. In step S12', the camera detection data storage unit 17 stores data on the position, speed, and size of the detected object, as well as data on the recognized object type.

[0048] In step S13', the identity determination unit 18c calculates the identity determination parameter Jrc according to equation (6). The identity determination unit 18c compares the identity determination parameter Jrc with a threshold value Th, and determines whether the identity determination has succeeded or failed (step S14).

[0049] If the parameter Jrc is greater than the threshold value Th, the identity determination unit 18c determines that the object detected by the radar and the object detected by the camera are not the same, and determines that the identity determination has failed (step S14: No). If the identity determination has failed, the radar detection data storage unit 12 discards the stored data of the speed, position, and object size for which the identity determination has failed, and the camera detection data storage unit 17 discards the stored data of the position, object size, and recognized object type for which the identity determination has failed (step S15).

[0050] On the other hand, if the parameter Jrc is equal to or less than the threshold value Th, the identity determination unit 18c determines that the object detected by the radar and the object detected by the camera are the same, and determines that the identity determination has been successful (step S14: Yes). If the identity determination has been successful, the identity determination unit 18c transfers the position and speed data detected by the radar and the data on the recognized object type detected by the camera to the detection data storage unit 19, and stores these data in the detection data storage unit 19 (step S16).

[0051] The object position and speed data and the recognized object type data stored in the detection data storage unit 19 are output to the vehicle control unit 30 (step S17). The vehicle control unit 30 uses the object position, speed, and recognized object type data acquired in step S17 for vehicle control (step S18). This completes the object detection process. Thereafter, the object detection process proceeds to the next frame (step S19), and the same process is repeatedly executed from step S1.

[0052] As described above, in the second embodiment, the object size and object speed are calculated from the radar detection information and the camera detection information, and the object size and object speed are used in the identity determination process. This further improves the accuracy of the matching in the identity determination process of a fusion-type object detection device that combines radar and a camera. As a result, it is possible to suppress a decrease in position accuracy and reduce the occurrence of erroneous control and false alarms in operations such as vehicle control and warning notification. Therefore, even at construction or civil engineering sites where various obstacles such as special vehicles, traffic cones, and containers are present, it is possible to improve the accuracy of the matching in the identity determination process and reduce the occurrence of erroneous control and false alarms.

[0053] Here, the hardware configuration of object detection device 100 will be described. Object detection device 100 is realized by a processing circuit. The processing circuit may be a processor and memory that executes a program stored in memory, or may be dedicated hardware such as a dedicated circuit. The processing circuit is also called a control circuit.

[0054] FIG. 5 is a block diagram showing an example of the configuration of a processing circuit included in the object detection device 100 according to the first and second embodiments. The processing circuit 90 shown in FIG. 5 is a control circuit and includes a processor 91 and a memory 92. When the processing circuit 90 includes the processor 91 and the memory 92, each function of the processing circuit 90 is implemented by software, firmware, or a combination of software and firmware. The software or firmware is written as a program and stored in the memory 92. The processor 91 reads and executes the program stored in the memory 92 to implement each function of the processing circuit 90. That is, the processing circuit 90 includes the memory 92 for storing a program that results in the processing of the object detection device 100 being executed. This program can also be considered a program that causes the object detection device 100 to execute each function implemented by the processing circuit 90. This program can be provided by a storage medium on which the program is stored or by other means such as a communication medium. The above program can also be considered a program that causes the object detection device 100 to execute an object detection process.

[0055] The processor 91 is, for example, a CPU (also called a central processing unit, processing unit, arithmetic unit, microprocessor, microcomputer, or DSP (Digital Signal Processor)) or a system LSI (Large Scale Integration).

[0056] The memory 92 may be, for example, a non-volatile or volatile semiconductor memory such as RAM (Random Access Memory), ROM (Read Only Memory), flash memory, EPROM (Erasable Programmable ROM), EEPROM (registered trademark) (Electrically EPROM), a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, or a DVD (Digital Versatile Disc).

[0057] The configurations shown in the above embodiments are examples of the contents of the present disclosure, and can be combined with other known technologies, or the configurations of each embodiment can be combined. Parts of the configurations can also be omitted or modified within the scope of the gist of the present disclosure. [Explanation of symbols]

[0058] 1 radar transceiver, 2 camera image capturer, 3 radar signal processor, 4 camera image processor, 5 fusion processor, 6 distance detection unit, 7 speed detection unit, 8 horizontal angle detection unit, 9 reception intensity detection unit, 10, 16 object size detection unit, 12 radar detection data storage unit, 13 object recognition unit, 14 position detection unit, 15 detection frame assignment unit, 17 camera detection data storage unit, 18 object identity determination unit, 18a position identity detection unit, 18b object size identity detection unit, 18c identity determination unit, 18d speed identity detection unit, 19 detection data storage unit, 20 speed detection unit, 30 vehicle control unit, 90 processing circuit, 91 processor, 92 memory, 100 object detection device.

Claims

1. a radar signal processor that processes a signal received from the radar transmitter and receiver to detect the position, speed, and reception strength of an object, and detects the size of the object based on the detected position and reception strength of the object; a camera image processor that detects the position, type, and size of the object based on image data captured by the camera image capturer; a fusion processor that calculates a first absolute value that is the absolute value of a difference between the first object position and the second object position and a second absolute value that is the absolute value of a difference between the first object size and the second object size, based on a first object position that is the position of the object and a first object size that is the object size detected by the radar signal processor, and a second object position that is the position of the object and a second object size that is the object size detected by the camera image processor, performs identity determination processing between the object detected by the radar signal processor and the object detected by the camera image processor based on a weighted average of the first absolute value and the second absolute value, and uses a result of the identity determination processing for vehicle control; An object detection device comprising:

2. The camera image processor further detects the speed of the object, The fusion processor calculates a third absolute value, which is an absolute value of a difference between a first object velocity detected by the radar signal processor and a second object velocity detected by the camera image processor, and performs the identity determination process based on a weighted average of the first absolute value, the second absolute value, and the third absolute value.

2. The object detection device according to claim 1.

3. The fusion processor detects people, vehicles, and obstacles as the objects, and the obstacles include special vehicles other than the vehicle itself, traffic cones, and containers.

3. The object detection device according to claim 1 or 2.

4. The radar signal processor detects the object size S radar according to the following formula, where R radar is the distance to the object, Pr is the reception intensity, and α radar and β radar are constants:

3. The object detection device according to claim 1 or 2. Sradar=αradar×Pr×Rradar 4 +βradar

Images