Object detection apparatus

Abstract

An object detection apparatus (100) comprises: a radar signal processor (3) that performs signal processing on a reception signal from a radar transceiver (1) to detect the position, speed, and object size of an object; a camera image processor (4) that detects the position, type, and object size of an object on the basis of captured image data from a camera image capturing device (2); and a fusion processor (5) that, on the basis of the position and object size of the object detected by the radar signal processor (3) and the position and object size of the object detected by the camera image processor (4), executes identity determination processing between the object detected by the radar signal processor (3) and the object detected by the camera image processor (4), and uses the result of the identity determination processing for vehicular control.

Description

Object detection device

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

[0002] An object detection device for vehicle mounting has a function of detecting an object existing in the vehicle use environment in a short time and performing vehicle control and alarm notification, which contributes to the safe driving of the vehicle. The object detection device uses sensors such as radar, camera, LiDAR (Light Detection And Ranging), ultrasonic sensor, etc. In recent years, a fusion-type object detection device that realizes performance improvement by combining a plurality of sensors has been widely used.

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

[0004] In recent years, the spread of object detection devices has also advanced in special vehicles such as excavators, wheel loaders, bulldozers, dump trucks, etc. used at construction and civil engineering sites, and the effectiveness of a fusion-type object detection device combining a radar and a camera has been expected.

[0005] International Publication No. 2022 / 254610

[0006] However, in a fusion-type object detection device using a radar and a camera, the same determination process for linking the detection information of an object is essential. However, at a construction or civil engineering site, there are various obstacles such as triangular cones and containers. Therefore, when there are obstacles including special vehicles other than the host vehicle, triangular cones, containers, etc. near a desired detection target object (for example, a person), there is a problem that the same determination process fails and the position accuracy decreases. The failure of the same determination process causes miscontrol or false alarm in operations such as vehicle control or alarm notification.

[0007] This disclosure has been made in view of the above, and aims to provide an object detection device that can improve the accuracy of matching in the process of determining the same object as the object being detected, suppress the decrease in positional accuracy, and reduce the occurrence of erroneous control and false alarms in operations such as vehicle control and alarm notification.

[0008] To solve the above-mentioned problems and achieve the objective, the object detection device of this disclosure comprises: a radar signal processor that processes received signals from a radar transceiver to detect the position, speed, and size of an object; a camera image processor that detects the position, type, and size of an object based on captured image data from a camera image capture device; and a fusion processor that performs a determination process to determine whether an object detected by the radar signal processor and an object detected by the camera image processor are identical, based on the position and size of the object detected by the radar signal processor and the position and size of the object detected by the camera image processor, and uses the result of the determination process for vehicle control.

[0009] The object detection device of this disclosure improves the accuracy of matching the determination process for identical objects, suppresses a decrease in positional accuracy, and reduces the occurrence of erroneous control and false alarms in operations such as vehicle control and alarm notification.

[0010] Block diagram showing the configuration of the object detection device according to Embodiment 1. Flowchart showing the object detection processing procedure by the object detection device according to Embodiment 1. Block diagram showing the configuration of the object detection device according to Embodiment 2. Flowchart showing the object detection processing procedure by the object detection device according to Embodiment 2. Block diagram showing an example of the configuration of the processing circuit included in the object detection devices according to Embodiments 1 and 2.

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

[0012] Embodiment 1. Figure 1 is a block diagram showing the configuration of the object detection device 100 according to Embodiment 1. 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 camera. The detection data output by the object detection device 100 is used for vehicle control and the like. The object detection device 100 comprises a radar transceiver 1, a camera image capture device 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, "object" refers to an object to be detected that is desired for detection when controlling the vehicle, and includes people, vehicles, obstacles, etc. Examples of obstacles include special vehicles other than the vehicle itself, traffic cones, containers, etc.

[0013] The radar transceiver 1 emits electromagnetic waves at 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, velocity, and size. In 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 supply semiconductor components, a substrate, a crystal device, chip components, an antenna, etc.

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

[0015] The received signal strength detection unit 9 detects the intensity of the reflected electromagnetic wave signal from an object. Specifically, the received signal strength detection unit 9 performs FFT processing in the distance and velocity directions and treats the peak level as the reflected electromagnetic wave signal strength. The object size detection unit 10 detects the object size based on the received signal strength detected by the received signal strength detection unit 9 and the object's 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 capture device 2 captures images of the surroundings, including the area in front of the vehicle, and acquires image data. The camera image capture device 2 consists of components such as a lens, holder, CMOS (Complementary Metal Oxide Semiconductor) sensor, power supply semiconductor components, and crystal device. The camera image processor 4 detects the position, size, and type of object (type of recognized object) of an object based on the image data captured by the camera image capture device 2.

[0017] The camera image processor 4 can be an MCU, CPU, or GPU (Graphics Processing Unit). The camera image processor 4 includes 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 uses the features obtained through deep learning as an object recognition database to recognize objects such as people and vehicles from image data captured by the camera image capturer 2. For object recognition in the object recognition unit 13, network algorithms based on deep learning, such as YOLO (You Only Look Once) and SSD (Single Shot Multibox Detector), are used. The object recognition unit 13 may also recognize objects using methods other than deep learning. For example, it can be implemented using machine learning or the HOG (Histograms of Oriented Gradients) method. The object recognition unit 13 obtains recognition results, including the type of object, which indicates 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 recognized by the object recognition unit 13. That is, it extracts only the desired object from the image, and the 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 assigned by the detection frame assignment unit 15. The camera detection data storage unit 17 stores data on the object's position, object size, and recognized object type, respectively, and outputs them to the subsequent fusion processor 5.

[0020] The fusion processor 5 comprises an object identity determination unit 18 and a detection data storage unit 19. The object identity determination unit 18 performs an identity determination process to determine 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 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 has 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 and the object detected by the camera image processor 4 are the same based on the determination result of the position identity detection unit 18a and the determination result of the object size identity detection unit 18b. If the identity determination unit 18c fails to determine identity, it discards the data on the position, speed, and size of the object detected by the radar signal processor 3 and the data on the position, size, and type of recognized object of the object detected by the camera image processor 4. If the identity determination unit 18c successfully determines identity, it 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 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 for storage. 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] Figure 2 is a flowchart showing the object detection process procedure by the object detection device 100 according to Embodiment 1. The operation of the object detection device 100 of Embodiment 1 will be explained using Figure 2.

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

[0024] The object size Sradar is calculated using the distance to the object Rradar, the received signal strength Pr, and the constants αradar and βradar, as shown in equation (1): Sradar = αradar × Pr × Rradar ４ +βradar...(1)

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

[0026] The constants αradar and βradar are adjustment parameters provided in the object detection device 100 to compensate for variations in individual performance and to ensure consistency between the object size detected by the radar signal processor 3 and the object size detected by the camera image processor 4 in the object identity determination unit 18.

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

[0028] Meanwhile, 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 the recognition result, including the type of recognized object. The position detection unit 14 detects the position of the recognized object based on the pixel coordinates of the recognized object (step S9). The detection frame assignment 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 assigned frame (step S11).

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

[0030] The constants αcamera and βcamera are adjustment parameters provided in the object detection device 100 to compensate for variations in individual performance and to ensure consistency between the object size detected by the camera image processor 4 and the object size detected by the radar signal processor 3 in the object identity determination unit 18.

[0031] The camera detection data storage unit 17 stores data on the position and size of the detected object, as well as data on the type of 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 storage unit 12 and the position and object size data transferred from the camera detection data storage 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 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) (|(Rradar - Rcamera)|) and inputs it to the identity determination unit 18c.

[0034] The distance Rcamera to the object detected by the camera is calculated using the positions xc and yc stored in the camera detection data storage unit 17, as shown in equation (4). xc represents the position information perpendicular to the optical axis of the object detection device 100, and yc represents the position information horizontal to the optical axis of the object detection device 100. xc and yc are defined as planes 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 a weighted average of the absolute values ​​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) |(Rradar - Rcamera)| and the absolute value 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 |(Sradar - Scamera)|. Jrc = Wr × |(Rradar - Rcamera)| + Ws × |(Sradar - Scamera)| ... (5)

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

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

[0039] On the other hand, if the parameter Jrc is less than or equal to the threshold 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 was successful (Step S14: Yes). If the identity determination is successful, the identity determination unit 18c transfers the position and velocity data detected by the radar and the recognition object type data detected by the camera to the detection data storage unit 19, and stores this data in the detection data storage unit 19 (Step S16).

[0040] The object's position and velocity data, along with 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's position, velocity, and recognized object type data acquired in step S17 for vehicle control (step S18). This completes the object detection process. Subsequently, the object detection process moves to the next frame (step S19), and the same process is repeated from step S1.

[0041] In the first embodiment, the object size is calculated from the detection information of the radar and the detection information of the camera, and these object sizes are used for the identity determination process. Therefore, the matching accuracy of the identity determination process of the fusion type object detection device combining the radar and the camera can be improved. As a result, the decrease in the position accuracy can be suppressed, and the occurrence of miscontrol and false alarms can be reduced for operations such as vehicle control and warning notification. Therefore, even at the site of construction or civil engineering work where various obstacles such as special vehicles, warning triangles, and containers exist, the matching accuracy of the identity determination process can be improved, and the occurrence of miscontrol and false alarms can be reduced.

[0042] Embodiment 2. FIG. 3 is a block diagram showing the configuration of the object detection device 100 according to the second embodiment. In the second embodiment, the speed of the object is added to the parameters for identity determination. For this purpose, 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. Also, in the second embodiment, a speed identity detection unit 18d is provided in the object identity determination unit 18. The other configurations in the second embodiment are the same as those in the first embodiment, and the same reference numerals are used and repeated descriptions are omitted.

[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 capture device 2, and stores the calculated speed in the camera detection data storage unit 17.

[0044] The speed identity detector 18d of the object identity determination unit 18 calculates the difference between the speed Vradar of the object detected by the radar signal processor 3 and the speed Vcamera of the object detected by the camera image processor 4, and inputs the absolute value |(Vradar - Vcamera)| of the calculated difference to the identity determination unit 18c. The identity determination unit 18c calculates the weighted average of the 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 speed Vradar of the object detected by the radar signal processor 3 and the speed Vcamera of the object detected by the camera image processor 4, thereby calculating the identity determination parameter Jrc. 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 small numerical values that sum to 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 the threshold Th and determines whether the identity determination was successful or failed. If the parameter Jrc is greater than the threshold Th, it is determined that the object detected by the radar and the object detected by the camera are not the same. If the parameter Jrc is less than or equal to the threshold Th, it is determined that the object detected by the radar and the object detected by the camera are the same.

[0046] Figure 4 is a flowchart showing the object detection processing procedure by the object detection device 100 according to the second embodiment. Using Figure 4, the operation of the object detection device 100 of the second embodiment will be described. In Figure 4, steps that perform the same operation as in Figure 2 are assigned the same step numbers, and duplicate explanations are omitted.

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

[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 the threshold Th to determine whether the identity determination was successful or unsuccessful (step S14).

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

[0050] On the other hand, if the parameter Jrc is less than or equal to the threshold 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 was successful (Step S14: Yes). If the identity determination is successful, the identity determination unit 18c transfers the position and velocity data detected by the radar and the recognition object type data detected by the camera to the detection data storage unit 19, and stores this data in the detection data storage unit 19 (Step S16).

[0051] The object's position and velocity data, along with 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's position, velocity, and recognized object type data acquired in step S17 for vehicle control (step S18). This completes the object detection process. Subsequently, the object detection process moves to the next frame (step S19), and the same process is repeated from step S1.

[0052] In this embodiment 2, the object size and velocity are calculated from the radar detection information and the camera detection information, and the object size and velocity are used in the same determination process. As a result, the accuracy of the same determination process in a fusion-type object detection device combining radar and a camera can be further improved. Consequently, a decrease in positional accuracy can be suppressed, and the occurrence of erroneous control and false alarms can be reduced in operations such as vehicle control and alarm notification. Therefore, even in construction or civil engineering sites where various obstacles such as special vehicles, traffic cones, and containers exist, the accuracy of the same determination process can be improved, and the occurrence of erroneous control and false alarms can be reduced.

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

[0054] Figure 5 is a block diagram showing an example configuration of a processing circuit included in the object detection device 100 according to Embodiments 1 and 2. The processing circuit 90 shown in Figure 5 is a control circuit and includes a processor 91 and a memory 92. When the processing circuit 90 is composed of a processor 91 and a memory 92, each function of the processing circuit 90 is realized 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. In the processing circuit 90, each function is realized by the processor 91 reading and executing the program stored in the memory 92. That is, the processing circuit 90 includes a memory 92 for storing a program that will result in the processing of the object detection device 100 being executed. This program can also be said to be a program that causes the object detection device 100 to execute each function realized by the processing circuit 90. This program may 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 said to be a program that causes the object detection device 100 to execute object detection processing.

[0055] The processor 91 is, for example, a CPU (Central Processing Unit, Processing Unit, Arithmetic Unit, Microprocessor, Microcomputer, DSP (Digital Signal Processor)) or a system LSI (Large Scale Integration).

[0056] Furthermore, memory 92 includes, for example, 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), magnetic disks, flexible disks, optical disks, compact disks, minidiscs, or DVDs (Digital Versatile Discs).

[0057] The configurations shown in the embodiments described above are merely examples of the content of this disclosure, and can be combined with other known technologies, and the configurations of each embodiment can be combined. It is also possible to omit or modify parts of the configuration without departing from the gist of this disclosure.

[0058] 1 Radar transceiver, 2 Camera image capture device, 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 Received 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. An object detection device comprising: a radar signal processor that processes received signals from a radar transceiver to detect the position, speed, and size of an object; a camera image processor that detects the position, type, and size of an object based on captured image data from a camera image processor; and a fusion processor that performs a determination process to determine if an object detected by the radar signal processor and an object detected by the camera image processor are identical, based on the position and size of the object detected by the radar signal processor and the position and size of the object detected by the camera image processor, and uses the result of the determination process to control the vehicle.

2. The object detection device according to claim 1, wherein the camera image processor further detects the velocity of the object, and the fusion processor performs the same determination process based on the position, velocity, and size of the object detected by the radar signal processor and the position, velocity, and size of the object detected by the camera image processor.

3. The object detection device according to claim 1 or 2, characterized in that the fusion processor detects people, vehicles, and obstacles as objects, and the obstacles include special vehicles other than the vehicle itself, traffic cones, or containers.

Images