OBJECT DETECTION DEVICE, OBJECT DETECTION METHOD, AND COMPUTER PROGRAM FOR OBJECT DETECTION

Abstract

To provide an object detection device capable of properly detect an object present in the periphery of a vehicle.SOLUTION: An object detection device is configured to: detect an object in the periphery of a vehicle from periphery data generated in time series by each of periphery sensors mounted on the vehicle; specify a dead angle area represented by none of periphery data generated by the plurality of periphery sensors respectively; select periphery sensors generating periphery data for which detection on an object can be omitted among the plurality of periphery sensors based upon a travel state of the vehicle; request dead angle data representing the dead angle area from external equipment mounted with an external sensor capable of generating the dead angle data; and stop detecting an object from periphery data generated by the selected periphery sensor and also detect an object in the dead angle area from the acquired dead angle data when dead angle data is acquired from the external equipment.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present disclosure relates to an object detection device, an object detection method, and an object detection computer program that detect objects around a vehicle. [Background technology]

[0002] An object detection device is known that detects an object from surrounding data representing the vehicle's surrounding environment. A driving control device controls the vehicle's driving so that the distance to the detected object is equal to or greater than a predetermined distance.

[0003] The surrounding environment of a vehicle may include blind spots that are not represented by surrounding data generated by surrounding sensors mounted on the vehicle. Patent Document 1 describes that a vehicle control system requests information from external devices such as other vehicles in the vicinity to supplement information on blind spots. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2020 / 183892 Summary of the Invention [Problem to be solved by the invention]

[0005] In some cases, a vehicle does not have sufficient computing resources to perform a process for detecting surrounding objects from surrounding data generated by surrounding sensors mounted on the vehicle. In such cases, the object detection device cannot properly detect objects from information about blind spots acquired from an external device.

[0006] An object of the present disclosure is to provide an object detection device that can appropriately detect objects present around a vehicle. [Means for solving the problem]

[0007] The gist of the present disclosure is as follows.

[0008] (1) A detection unit that detects objects around the vehicle from surrounding data representing a situation around the vehicle, the surrounding data being generated in time series by each of a plurality of surrounding sensors mounted on the vehicle; an identification unit that identifies a blind spot area around the vehicle that is not represented by any of the surrounding data generated by the plurality of surrounding sensors; a selection unit that selects, from the plurality of peripheral sensors, a peripheral sensor that generates peripheral data that allows the detection of the object to be omitted based on a traveling situation of the vehicle; a request unit that includes an external sensor capable of generating blind spot data representing the blind spot area and that requests the blind spot data from an external device that is communicably connected to the vehicle; a stop unit that stops the detection of the object from the surrounding data generated by the selected surrounding sensor when the blind spot data is acquired from the external device; The object detection device, when the detection unit acquires the blind spot data from the external device, detects an object in the blind spot area from the acquired blind spot data.

[0009] (2) The object detection device described in (1) above, wherein the request unit requests the external device to provide the blind spot data having a number of pixels equal to or less than the number of pixels of the peripheral data generated by the selected peripheral sensor.

[0010] (3) the identification unit determines whether the blind spot area is displayed by any of the plurality of peripheral sensors; When the blind spot area is represented by any of the plurality of surrounding sensors, the request unit terminates the request for the blind spot data to the external device, the stopping unit resumes detecting the object from the surrounding data generated by the selected surrounding sensor; The object detection device according to (1) or (2) above.

[0011] (4) An object detection device that detects objects around the vehicle, detecting an object around the vehicle from each of surrounding data representing a situation around the vehicle, the surrounding data being generated in time series by each of a plurality of surrounding sensors mounted on the vehicle; Identifying a blind spot area around the vehicle that is not represented by any of the surrounding data generated by the plurality of surrounding sensors; selecting, from the plurality of peripheral sensors, a peripheral sensor that generates peripheral data that allows the detection of the object to be omitted based on a traveling situation of the vehicle; an external sensor capable of generating blind spot data representing the blind spot area is mounted on the vehicle, and the external device is communicably connected to the vehicle to request the blind spot data; When the blind spot data is acquired from the external device, the detection of the object from the surrounding data generated by the selected surrounding sensor is stopped; When the blind spot data is acquired from the external device in the object detection, an object in the blind spot area is detected from the acquired blind spot data. The object detection method includes:

[0012] (5) For each of a plurality of surrounding sensors mounted on the vehicle, detecting an object around the vehicle from each of surrounding data representing a situation around the vehicle, the surrounding data being generated in time series by the surrounding sensors; Identifying a blind spot area around the vehicle that is not represented by any of the surrounding data generated by each of the plurality of surrounding sensors; selecting, from the plurality of peripheral sensors, a peripheral sensor that generates peripheral data that allows the detection of the object to be omitted based on a traveling situation of the vehicle; a request for the blind spot data from an external device that is equipped with an external sensor capable of generating blind spot data representing the blind spot area and is communicably connected to the vehicle; When the blind spot data is acquired from the external device, stopping detection of the object from the surrounding data generated by the selected surrounding sensor; When the blind spot data is acquired from the external device in the object detection, an object in the blind spot area is detected from the acquired blind spot data; a computer program for object detection that causes a computer installed in the vehicle to execute the above-mentioned program;

[0013] According to the object detection device according to the present disclosure, it is possible to appropriately detect objects present around a vehicle. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a schematic configuration diagram of a vehicle in which an object detection device is implemented. [Figure 2] FIG. 1 is a hardware schematic diagram of an object detection device. [Figure 3] FIG. 2 is a functional block diagram of a processor included in the object detection device. [Figure 4] FIG. 2 is a schematic diagram illustrating a first example of object detection. [Figure 5] FIG. 10 is a schematic diagram illustrating a second example of object detection. [Figure 6] 10 is a flowchart of an object detection process. DETAILED DESCRIPTION OF THE INVENTION

[0015] An object detection device capable of appropriately detecting objects present around a vehicle will be described in detail below with reference to the drawings. The object detection device detects objects around the vehicle from surrounding data representing the vehicle's surrounding environment, which is generated in time series by each of multiple surrounding sensors mounted on the vehicle. The object detection device also identifies blind spot areas in the surrounding environment that are not represented by any of the surrounding data generated by the multiple surrounding sensors. The object detection device also selects, based on the vehicle's driving conditions, one of the multiple surrounding sensors that generates surrounding data that allows object detection to be omitted. The object detection device then includes an external sensor that can generate blind spot data representing the identified blind spot area and requests the blind spot data from an external device that can communicate with the vehicle via a communication network. When the blind spot data is acquired from the external device, the object detection device stops detecting objects from the surrounding data generated by the selected surrounding sensor. The object detection device also detects objects in the blind spot area from the acquired blind spot data.

[0016] FIG. 1 is a schematic diagram of a vehicle in which an object detection device is implemented.

[0017] The vehicle 1 includes a peripheral camera 2, a GNSS (Global Navigation Satellite System) receiver 3, a data communication module 4 (DCM, Data Communication Module), a storage device 5, and an object detection device 6. The peripheral camera 2, the GNSS receiver 3, the data communication module 4, the storage device 5, and the object detection device 6 are communicably connected via an in-vehicle network that complies with a standard such as a controller area network.

[0018] The peripheral camera 2 is an example of a peripheral sensor for generating peripheral data that represents the situation around the vehicle 1. The peripheral camera 2 has a two-dimensional detector configured with an array of photoelectric conversion elements that are sensitive to visible light, such as a CCD or C-MOS, and an imaging optical system that forms an image of the area to be photographed on the two-dimensional detector.

[0019] The peripheral camera 2 includes a first front peripheral camera 2-1, a second front peripheral camera 2-2, and a rear peripheral camera 2-3. The first front peripheral camera 2-1 and the second front peripheral camera 2-2 are disposed, for example, at the upper front part of the vehicle interior, facing forward, and the rear peripheral camera 2-3 is disposed, for example, at the upper rear part of the vehicle interior, facing backward.

[0020] The first front periphery camera 2-1, the second front periphery camera 2-2, and the rear periphery camera 2-3 capture images of the situation around the vehicle 1 through the windshield and rear windshield, respectively, at predetermined capture intervals (for example, 1 / 30 to 1 / 10 seconds). The first front periphery camera 2-1, the second front periphery camera 2-2, and the rear periphery camera 2-3 output first front data, second front data, and rear data, which represent the situation in front or rear, respectively, as surrounding data in chronological order.

[0021] The first front peripheral camera 2-1 and the rear peripheral camera 2-3 each have a field of view of approximately 120 degrees. The field of view of the first front peripheral camera 2-1 and the field of view of the rear peripheral camera 2-3 may be different. The second front peripheral camera 2-2 has a field of view of approximately 45 degrees.

[0022] The first forward data output by the first front surroundings camera 2-1 represents a wide area in front of the vehicle 1 and is used for driving control of the vehicle 1 in various situations. The second forward data output by the second front surroundings camera 2-2 represents an area in front of the vehicle 1 that is relatively far from the vehicle 1 and is used for driving control of the vehicle 1, particularly when the vehicle 1 is traveling at high speed. The rearward data output by the rear surroundings camera 2-3 represents a wide area behind the vehicle 1 and is used for driving control of the vehicle 1 in various situations.

[0023] The vehicle 1 may have, as a peripheral sensor, a sensor other than the peripheral camera 2, for example, a LiDAR (Light Detection and Ranging) sensor that generates, as peripheral data, a distance image in which each pixel has a value corresponding to the distance to an object represented by that pixel, based on the situation around the vehicle 1. The vehicle 1 may also have, as a peripheral sensor, an ultrasonic sensor that emits ultrasonic waves in a predetermined direction, such as the front right, front left, rear right, or rear left of the vehicle 1, and measures the distance from the time it takes for the ultrasonic waves to be reflected by an object and return.

[0024] The GNSS receiver 3 receives GNSS signals from GNSS satellites at predetermined intervals and, based on the received GNSS signals, determines the self-position of the vehicle 1. The GNSS receiver 3 outputs, at predetermined intervals, a positioning signal representing the result of determining the self-position of the vehicle 1 based on the GNSS signals to the object detection device 6 via the in-vehicle network.

[0025] The data communication module 4 is an example of a communication unit, and is a device that performs wireless communication processing in accordance with wireless communication standards such as Bluetooth (registered trademark) Low Energy and V2X (Vehicle to X). The data communication module 4 operates, for example, as a broadcaster in Bluetooth (registered trademark) Low Energy communication, and can transmit data received from the object detection device 6 by including it in an advertising packet. The data communication module 4 can also transmit data received from the object detection device 6 by including it in an uplink wireless signal and pass the data included in the received wireless signal to the object detection device 6. The data communication module 4 may be implemented as part of the object detection device 6. The data communication module 4 may also perform wireless communication processing in accordance with wide-area wireless communication standards such as so-called 4th Generation (4G) or 5th Generation (5G).

[0026] The storage device 5 is an example of a storage unit and includes, for example, a hard disk drive or a non-volatile semiconductor memory. The storage device 5 stores a high-precision map. The high-precision map includes, for example, information representing lane lines that separate lanes in a predetermined area depicted on the high-precision map, and information representing parking space lines that separate each parking space in a parking area having multiple parking spaces where vehicles can be parked.

[0027] The object detection device 6 uses the surrounding data generated by the surrounding camera 2 and the blind spot data acquired via the data communication module 4 to detect objects around the vehicle.

[0028] 2 is a hardware schematic diagram of the object detection device 6. The object detection device 6 is an ECU (Electronic Control Unit) including a communication interface 61, a memory 62, and a processor 63.

[0029] The communication interface 61 is an example of a communication unit, and has a communication interface circuit for connecting the object detection device 6 to an in-vehicle network. The communication interface 61 supplies received data to the processor 63. The communication interface 61 also outputs data supplied from the processor 63 to the outside.

[0030] The memory 62 includes a volatile semiconductor memory and a non-volatile semiconductor memory, and stores various data used in processing by the processor 63, such as a peripheral sensor selection rule for selecting a peripheral sensor that generates peripheral data that can omit object detection based on the driving conditions of the vehicle 1.

[0031] In the peripheral sensor selection rule, for example, when an object detected from peripheral data generated by a peripheral sensor in a predetermined driving situation is not an avoidance target in driving control to avoid approach of the vehicle 1 to the object, the driving situation is associated with the peripheral sensor. For example, when the speed of the vehicle 1 is 10 km / h or less, an object detected only from the second forward data generated by the second forward peripheral camera 2-2 is at a sufficiently large distance from the vehicle 1. Driving control to avoid approach of such an object is sufficiently possible even after the object is detected from the first forward data generated by the first forward peripheral camera 2-1. Therefore, in the peripheral sensor selection rule, a driving situation in which the speed is 10 km / h or less may be associated with the second forward peripheral camera 2-2. Furthermore, when the speed of the vehicle 1 is 80 km / h or more and it is difficult to appropriately execute driving control to avoid approach of the object detected from the first forward data within a predetermined time, a driving situation in which the speed is 80 km / h or more may be associated with the first forward peripheral camera 2-1.

[0032] The memory 62 also stores various application programs, such as an object detection program that executes object detection processing.

[0033] The processor 63 is an example of a control unit and includes one or more processors and their peripheral circuits. The processor 63 may further include other arithmetic circuits such as a logic unit, a numerical calculation unit, or a graphics processing unit.

[0034] Fig. 3 is a functional block diagram of the processor 63 included in the object detection device 6. Fig. 4 is a diagram illustrating a first example of object detection, and Fig. 5 is a diagram illustrating a second example of object detection.

[0035] The processor 63 of the object detection device 6 has, as functional blocks, a detection unit 631, an identification unit 632, a selection unit 633, a request unit 634, and a stopping unit 635. Each of these units in the processor 63 is a functional module implemented by a program executed on the processor 63. A computer program that realizes the functions of each unit in the processor 63 may be provided in a form recorded on a computer-readable portable recording medium such as a semiconductor memory, a magnetic recording medium, or an optical recording medium. Alternatively, each of these units in the processor 63 may be implemented in the object detection device 6 as an independent integrated circuit, microprocessor, or firmware.

[0036] The detection unit 631 acquires surrounding data representing the situation around the vehicle 1 from the surrounding cameras 2 (the first front surrounding camera 2-1, the second front surrounding camera 2-2, and the rear surrounding camera 2-3) via the communication interface 61. Then, the detection unit 631 detects objects around the vehicle 1 from the time-series surrounding data acquired for each of the surrounding cameras 2.

[0037] The detection unit 631 detects objects and their types present around the vehicle 1 by inputting each piece of peripheral data generated in time series from each of the peripheral cameras 2 into a classifier that has been trained in advance to detect objects such as other vehicles and pedestrians.

[0038] The classifier can be, for example, a convolutional neural network (CNN) having multiple convolution layers connected in series from the input side to the output side. A large amount of data containing various types of objects, such as pedestrians and vehicles, is used as training data in advance, and the CNN is trained according to a predetermined learning method, such as backpropagation. The classifier can also use machine learning algorithms, such as a support vector machine (SVM) or AdaBoost. When the classifier is an SVM, the SVM is trained to determine support vectors for identifying whether various regions in the surrounding data contain objects, and the SVM then functions as a classifier for detecting objects.

[0039] The detection unit 631 may also detect features around the vehicle 1 by inputting the received surrounding data into a classifier that has been trained in advance to detect features such as road signs, road markings, and roadside trees. The classifier may be a CNN that has been trained using training data that includes features. The detection unit 631 may detect traffic participants and features from the surrounding data using a CNN that has been trained using training data that includes traffic participants and training data that includes features as a classifier.

[0040] The detection unit 631 estimates the direction in which the object exists relative to the vehicle 1, using the position of the area in which the object is represented in the peripheral data and imaging parameters such as the focal length, imaging direction, and pixel size of the optical system of the peripheral camera 2 stored in the memory 62. The detection unit 631 also estimates the distance from the vehicle 1 to the object, using the size of the area in which the object is represented in the peripheral data and the standard size for each type of object stored in the memory 62.

[0041] The detection unit 631 uses the position and orientation of the vehicle 1, the direction in which the object exists relative to the vehicle 1, and the distance of the object from the vehicle 1 to determine the position in the world coordinate system of the detected object from the surrounding data.

[0042] When the detection unit 631 acquires blind spot data (described later), it detects an object in the blind spot area from the acquired blind spot data. As described later, the blind spot data includes external sensor information of the external sensor that generated the blind spot data. The detection unit 631 can calculate the coordinates in the world coordinate system of the object detected from the blind spot data using the external sensor information.

[0043] Information about the object detected by the detection unit 631 can be used for automatic driving control of the vehicle 1 by a driving control device (not shown) mounted on the vehicle 1.

[0044] The driving control device is an ECU equipped with a communication interface, a memory, and a processor. The driving control device performs driving control processing by executing a driving control computer program stored in the memory. The driving control processing includes outputting control signals to driving mechanisms (not shown) of the vehicle 1, such as the engine or motor, brakes, and steering, so that the distance from the vehicle 1 to objects around the vehicle 1 is appropriate. The driving control device may be implemented in the same ECU as the object detection device.

[0045] The identification unit 632 identifies a blind spot area around the vehicle 1 that is not represented by any of the surrounding data generated by the plurality of surrounding sensors.

[0046] For example, the identification unit 632 compares features shown on a high-precision map acquired from the storage device 5 with features detected from each of the multiple pieces of peripheral data in accordance with the vehicle's own position and orientation indicated in the positioning signal received from the GNSS receiver 3. When any feature shown on the high-precision map is not included in any of the features detected from the peripheral data, the identification unit 632 identifies a predetermined range of area including the feature as a blind spot area.

[0047] 4 shows a situation in which vehicle 1 is traveling through parking area PE. Parking area PE has parking spaces PS11-PS13, each defined by parking stall lines PB11-PB14, on the left side of parking area PE relative to the direction of travel TD1 of vehicle 1. Parking area PE also has parking spaces PS21-PS23, each defined by parking stall lines PB21-PB24, on the right side of parking area PE relative to the direction of travel TD1 of vehicle 1.

[0048] Another vehicle 10 is parked in parking space PS12. Another vehicle 11 is parked in parking space PS21. Areas DR1-1, DR1-2, and DR1-3 indicate areas around vehicle 1 that are represented by the first forward data output by the first front surroundings camera 2-1, the second forward data output by the second front surroundings camera 2-2, and the rear data output by the rear surroundings camera 2-3, respectively.

[0049] Parking stall line PB22 separating parking space PS21 from parking space PS22 is included in area DR1-1, but is not included in areas DR1-2 and DR1-3. Furthermore, because another vehicle 11 parked in parking space PS21 is present between parking stall line PB22 and the first front periphery camera 2-1 of vehicle 1, parking stall line PB22 is blocked by the other vehicle 11 and is not shown in the first front data output by the first front periphery camera 2-1.

[0050] The identification unit 632 identifies a predetermined range of area including a parking stall line PB22 that is not detected from the surrounding data as a blind spot area BR. The predetermined range is, for example, a range of a predetermined distance (for example, 50 cm) from a feature that is not detected from the surrounding data.

[0051] The selection unit 633 selects, from among the plurality of peripheral sensors, a peripheral sensor that generates peripheral data that allows object detection to be omitted, based on the traveling conditions of the vehicle 1.

[0052] 4, the vehicle 1 is traveling in the parking area PE at a low speed (for example, 10 km / h or less). The selection unit 633 refers to the surrounding data selection rules stored in the memory 62 and selects the second front surrounding camera 2-2 as the surrounding sensor that generates surrounding data associated with the traveling situation of traveling at a low speed and that can omit object detection.

[0053] The request unit 634 is equipped with an external sensor capable of generating blind spot data representing the identified blind spot area, and requests the blind spot data from an external device communicably connected to the vehicle 1.

[0054] 4, the other vehicle 10 has the same hardware configuration as the vehicle 1. The object detection device 6 of the vehicle 1 is communicably connected to the object detection device of the other vehicle 10 via the data communication module 4.

[0055] The request unit 634 transmits blind spot area information that identifies blind spot areas and a blind spot data request that requests the transmission of blind spot data to the object detection device of the other vehicle 10. The blind spot area information is, for example, the coordinates in the world coordinate system of a feature that is represented on the high-precision map and not detected in the surrounding data, and the lengths in the east-west and north-south directions of a rectangle centered on the coordinates. The blind spot area information may also be the coordinates in the world coordinate system of a feature that is represented on the high-precision map and not detected in the surrounding data, and the radius of a circle centered on the coordinates. In this case, the request unit 634 does not need to know whether the external device that is the target of the blind spot data request is equipped with an external sensor that can generate blind spot data.

[0056] The object detection device of the other vehicle 10 determines whether the blind spot area identified by the received blind spot area information is represented in external data generated by an external sensor mounted on the other vehicle 10. If it is determined that the blind spot area is represented in the external data, the object detection device of the other vehicle 10 transmits the external data as blind spot data to the object detection device 6 via the data communication module. The blind spot data includes the external data generated by the external sensor and external sensor information such as the position of the external sensor, the shooting direction, the focal length of the optical system of the external sensor, and the pixel size of the image sensor of the external sensor.

[0057] When requesting blind spot data from an external device, the requesting unit 634 may request blind spot data having a number of pixels equal to or less than the number of pixels of the peripheral data generated by the peripheral sensor selected by the selecting unit 633 as the peripheral sensor that generates peripheral data for which object detection can be omitted. By the requesting unit 634 requesting such blind spot data, the processor 63 can appropriately detect objects from the blind spot data acquired from the external device.

[0058] When blind spot data is acquired from an external device, the stopping unit 635 stops detecting an object from the surrounding data generated by the selected surrounding sensor.

[0059] 4, when the stopping unit 635 acquires blind spot data from another vehicle 10, it stops inputting the second forward data generated by the selected second front surroundings camera to the classifier, thereby stopping detection of an object from the second forward data. The detection unit 631 inputs the blind spot data acquired from another vehicle 10 to the classifier and detects an object in the blind spot area.

[0060] Like Fig. 4, Fig. 5 shows a situation in which vehicle 1 is traveling in parking area PE. In Fig. 5, vehicle 1 travels along traveling direction TD1, then changes traveling direction to TD2 and backs up. Parking stall line PB22, which was included in blind spot area BR in Fig. 4, is now included in area DR1-3 and is no longer blocked by other vehicle 11 in Fig. 5 due to the change in position and traveling direction of vehicle 1. In other words, parking stall line PB22 is represented in the rear data output by rear surrounding camera 2-3.

[0061] The identification unit 632 may determine whether the blind spot area has come to be represented by any of the plurality of peripheral sensors. If the blind spot area has come to be represented by any of the plurality of peripheral sensors, the request unit 634 ends the request for blind spot data from the external device, and the stopping unit 635 resumes detecting objects from the peripheral data generated by the selected peripheral sensor.

[0062] 5, the identification unit 632 determines that a blind spot area is now represented in the rear data. In this case, the request unit 634 transmits an end request signal to the object detection device of the other vehicle 10, indicating the end of the request for blind spot data, and the stop unit 635 resumes inputting the rear data to the classifier. The detection unit 631 inputs the surrounding data, including the rear data, to the classifier to detect objects.

[0063] 6 is a flowchart of the object detection process. The processor 63 of the object detection device 6 executes the object detection process described below while the vehicle 1 is traveling.

[0064] First, the detection unit 631 of the processor 63 of the object detection device 6 detects objects around the vehicle 1 from each piece of peripheral data generated in time series by each of the multiple peripheral cameras 2 (step S1).

[0065] Next, the identifying unit 632 of the processor 63 identifies a blind spot area around the vehicle 1 that is not represented by any of the surrounding data generated by the plurality of surrounding sensors (step S2).

[0066] The identification unit 632 determines whether or not there is a blind spot area (step S3). If there is no blind spot area (step S3: N), the process of the processor 63 returns to step S1, and the detection unit 631 repeats object detection using the surrounding data.

[0067] If there is a blind spot area (step S3: Y), the selection unit 633 of the processor 63 selects, from among the multiple peripheral sensors, a peripheral camera that generates peripheral data that allows object detection to be omitted, based on the driving conditions of the vehicle 1 (step S4).

[0068] Next, the request unit 634 of the processor 63 requests blind spot data from an external device that is equipped with an external sensor capable of generating blind spot data representing blind spot areas and is communicably connected to the vehicle 1 (step S5).

[0069] The request unit 634 determines whether or not blind spot data has been acquired from the external device (step S6). If blind spot data has not been acquired (step S6: N), the process of the processor 63 returns to step S1, and the detection unit 631 repeats object detection using the surrounding data.

[0070] If blind spot data is acquired (step S6: Y), the stopping unit 635 of the processor 63 stops detecting objects from the peripheral data generated by the selected peripheral camera (step S7). Then, the processing of the processor 63 returns to step S1, and the detection unit 631 detects objects in the blind spot area from the acquired blind spot data.

[0071] By performing the object detection process in this manner, it is possible to appropriately detect objects that exist around the vehicle.

[0072] According to a modified example, the object detection device 6 and the other vehicle 10 may each be connected to a wireless base station (not shown) included in a communication network (not shown), and may be connected via a server (not shown) connected to the communication network.

[0073] For example, the other vehicle 10 repeatedly (e.g., at one-minute intervals) transmits available data information indicating an area represented in external data generated by an external sensor mounted on the other vehicle 10 to a server via a communication network. The object detection device 6 transmits information indicating a blind spot area to the server via the data communication module 4 and the communication network. The server identifies the other vehicle 10 as an external device whose area indicated in the available data information includes a blind spot area, and requests the other vehicle 10 to provide external data. The other vehicle 10 generates external data using an external sensor in response to the server's request, and transmits the data to the server via the communication network. The server transmits the external data received from the other vehicle 10 to the object detection device 6 via the communication network.

[0074] It should be understood that those skilled in the art can make various changes, substitutions, and alterations thereto without departing from the spirit and scope of the present disclosure. [Explanation of symbols]

[0075] 1 vehicle 6. Object detection device 631 Detector 632 Specific part 633 Selection Section 634 Request part 635 Stop part

Claims

1. a detection unit that detects objects around the vehicle from surrounding data that represents a situation around the vehicle and is generated in time series by each of a plurality of surrounding sensors mounted on the vehicle; an identification unit that identifies a blind spot area around the vehicle that is not represented by any of the surrounding data generated by each of the plurality of surrounding sensors; a selection unit that selects, from among the plurality of peripheral sensors, a peripheral sensor that generates peripheral data that allows the detection of the object to be omitted based on a traveling state of the vehicle; a request unit that is equipped with an external sensor capable of generating blind spot data representing the blind spot area and that requests the blind spot data from an external device that is communicably connected to the vehicle; a stop unit that stops detection of the object from the surrounding data generated by the selected surrounding sensor when the blind spot data is acquired from the external device; The object detection device, when the detection unit acquires the blind spot data from the external device, detects an object in the blind spot area from the acquired blind spot data.

2. The object detection device according to claim 1 , wherein the request unit requests the external device for the blind spot data having a number of pixels equal to or less than a number of pixels of the peripheral data generated by the selected peripheral sensor.

3. The identification unit determines whether or not the blind spot area is represented by any of the plurality of peripheral sensors; When the blind spot area is represented by any of the plurality of surrounding sensors, The request unit terminates the request for the blind spot data to the external device, The stopping unit resumes detection of the object from the surrounding data generated by the selected surrounding sensor. The object detection device according to claim 1 .

4. An object detection device that detects objects around a vehicle, Detecting objects around the vehicle from surrounding data representing a situation around the vehicle, the surrounding data being generated in time series by each of a plurality of surrounding sensors mounted on the vehicle; Identifying a blind spot area around the vehicle that is not represented by any of the surrounding data generated by each of the plurality of surrounding sensors; selecting, from among the plurality of peripheral sensors, a peripheral sensor that generates peripheral data that allows the detection of the object to be omitted based on a traveling state of the vehicle; An external sensor is mounted on the vehicle and capable of generating blind spot data representing the blind spot area, and the external device is communicatively connected to the vehicle to request the blind spot data; When the blind spot data is acquired from the external device, the detection of the object from the surrounding data generated by the selected surrounding sensor is stopped; When the blind spot data is acquired from the external device in the object detection, an object in the blind spot area is detected from the acquired blind spot data. The object detection method includes:

5. Detecting an object around the vehicle from each of surrounding data representing a situation around the vehicle, the surrounding data being generated in time series by each of a plurality of surrounding sensors mounted on the vehicle; Identifying a blind spot area around the vehicle that is not represented by any of the surrounding data generated by each of the plurality of surrounding sensors; selecting, from among the plurality of peripheral sensors, a peripheral sensor that generates peripheral data that allows the detection of the object to be omitted based on a traveling state of the vehicle; a request for the blind spot data from an external device that is equipped with an external sensor capable of generating blind spot data representing the blind spot area and is communicably connected to the vehicle; When the blind spot data is acquired from the external device, stopping detection of the object from the surrounding data generated by the selected surrounding sensor; When the blind spot data is acquired from the external device in the object detection, an object in the blind spot area is detected from the acquired blind spot data; A computer program for object detection that causes a computer mounted on the vehicle to execute the above-mentioned.

Images