In-vehicle device and sensor data transmission method

Abstract

To provide an on-vehicle unit which enables execution of processing corresponding to a compressibility ratio of sensor data, an information processing device, a sensor data transmission method, and an information processing method.SOLUTION: An on-vehicle unit comprises an acquisition section, a compression section, and a transmission section. The acquisition section acquires vehicle state information representing a state of a vehicle and sensor data measured by a sensor provided in the vehicle. The compression section compresses sensor data in a different compressibility ratio corresponding to the vehicle state information. The transmission section transmits the compressibility ratio correspondingly to the compressed sensor data.SELECTED DRAWING: Figure 5

Description

[Technical Field]

[0001] The present disclosure relates to an in-vehicle device, an information processing device, a sensor data transmission method, and an information processing method. [Background technology]

[0002] 2. Description of the Related Art Conventionally, there is known a technique for transmitting sensor data measured by various sensors provided in a vehicle from an in-vehicle device to a cloud server or an edge server. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2020-107291 Summary of the Invention [Problem to be solved by the invention]

[0004] In conventional technology, it is known to change the compression rate of sensor data depending on the vehicle's driving conditions, but it is sometimes difficult to identify the compression rate from the compressed sensor data. This makes it difficult for a cloud server or edge server that receives the compressed sensor data to perform processing according to the compression rate.

[0005] The present disclosure provides an in-vehicle device, an information processing device, a sensor data transmission method, and an information processing method that enable processing to be performed according to the compression rate of sensor data. [Means for solving the problem]

[0006] The in-vehicle device according to the present disclosure includes an acquisition unit and a determination unit; a compression section; a generation unit; The acquisition unit acquires vehicle state information representing a state of the vehicle and sensor data measured by a sensor provided in the vehicle. The determination unit determines the compression rate of the sensor data in accordance with the vehicle state information. The compression unit is configured to: It was decidedCompress the sensor data using the compression ratio. The generating unit generates compressed sensor data with a compression ratio by adding the compression ratio determined by the determining unit to the compressed sensor data. The transmitting unit is Compressed sensor data with compression ratio The vehicle state information includes at least the vehicle speed. The decision unit decides to compress the sensor data at a first compression rate when the vehicle speed is equal to or less than a first threshold, and decides to compress the sensor data at a second compression rate higher than the first compression rate when the vehicle speed is higher than the first threshold. [Effects of the Invention]

[0007] The in-vehicle device, information processing device, sensor data transmission method, and information processing method according to the present disclosure enable processing to be performed according to the compression rate of the sensor data. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information communication between a vehicle and a cloud server according to the first embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of a vehicle equipped with the on-board device according to the first embodiment. [Figure 3] FIG. 3 is a diagram showing an example of a configuration in the vicinity of the driver's seat of the vehicle according to the first embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a hardware configuration of the in-vehicle device according to the first embodiment. [Figure 5] FIG. 5 is a block diagram showing an example of functions of the in-vehicle device according to the first embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of sensor data with a header according to the first embodiment. [Figure 7] FIG. 7 is a block diagram illustrating an example of functions of the cloud server according to the first embodiment. [Figure 8] FIG. 8 is a flowchart showing an example of the flow of the sensor data transmission process according to the first embodiment. [Figure 9] FIG. 9 is a flowchart showing an example of the flow of ADAS processing executed by the cloud server according to the first embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of information communication between a vehicle, an edge server, and a cloud server according to the second embodiment. [Figure 11]FIG. 11 is a diagram illustrating an example of information communication between a vehicle, an edge server, and a cloud server according to the third embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, embodiments of an in-vehicle device and an information processing device according to the present disclosure will be described with reference to the drawings.

[0010] (First embodiment) 1 is a diagram showing an example of information communication between a vehicle 1 and a cloud server 2 according to the first embodiment. The vehicle 1 and the cloud server 2 are connected via a network such as the Internet. As shown in FIG. 1, the vehicle 1 according to this embodiment transmits metadata such as compression rate, frame rate, and resolution to the cloud server 2 along with sensor data.

[0011] The cloud server 2 is provided in a cloud environment and is an example of an information processing device in this embodiment.

[0012] The cloud server 2 executes processing such as ADAS (Advanced Driver-Assistance Systems) based on the sensor data in accordance with the metadata of the sensor data transmitted from the vehicle 1. For example, the cloud server 2 changes the threshold value used for processing, the processing algorithm, or the learning model used for learning the sensor data in accordance with the compression rate of the sensor data.

[0013] Examples of ADAS processing performed by cloud server 2 include, but are not limited to, ACC (Adaptive Cruise Control System), FCW (Forward Collision Warning), AEBS (Advanced Emergency Braking System), PD (Pedestrian Detection), TSR (Traffic Sign Recognition), LDW (Lane Departure Warning), free space detection, automatic parking, and automated valet parking (AVP).

[0014] The cloud server 2 transmits vehicle control data for controlling the driving of the vehicle 1 to the vehicle 1, for example, based on the sensor data received from the vehicle 1 and the metadata of the sensor data. In addition to the vehicle control data for controlling the driving of the vehicle 1, the cloud server 2 may also provide information to the driver of the vehicle 1.

[0015] The sensor data in this embodiment includes at least image data of the surroundings of the vehicle 1 captured by an onboard camera mounted on the vehicle 1. The frame rate included in the metadata of the sensor data is the frame rate of the image data, and the resolution is the resolution of the image data. In addition to the image data, the sensor data may also include measurement data obtained by various sensors. For example, the sensor data may include ranging data of the distance between the vehicle 1 and obstacles around the vehicle 1 measured by a sonar or radar mounted on the vehicle 1.

[0016] In this embodiment, the term "obstacle" includes objects, buildings, people such as pedestrians, bicycles, other vehicles, etc. Also, while FIG. 1 illustrates a cloud server 2, an edge server may be used instead of or in addition to the cloud server 2.

[0017] Next, the configuration of the vehicle 1 in this embodiment will be described.

[0018] Fig. 2 is a diagram showing an example of a vehicle 1 equipped with an on-vehicle device 100 according to the first embodiment. As shown in Fig. 2, the vehicle 1 includes a vehicle body 12 and two pairs of wheels 13 arranged along a predetermined direction on the vehicle body 12. The two pairs of wheels 13 include a pair of front tires 13f and a pair of rear tires 13r.

[0019] 2 includes four wheels 13, the number of wheels 13 is not limited to this. For example, the vehicle 1 may be a two-wheeled vehicle.

[0020] The vehicle body 12 is coupled to wheels 13 and can move by the wheels 13. In this case, the predetermined direction in which the two pairs of wheels 13 are arranged is the traveling direction of the vehicle 1. The vehicle 1 can move forward or backward by switching gears (not shown) or the like. The vehicle 1 can also turn right or left by steering.

[0021] The vehicle body 12 has a front end F, which is the end on the front tire 13f side, and a rear end R, which is the end on the rear tire 13r side. The vehicle body 12 has a generally rectangular shape when viewed from above, and the four corners of the generally rectangular shape are sometimes called "ends." The vehicle 1 also has a display device, a speaker, and an operation unit, which are not shown in FIG. 2.

[0022] A pair of bumpers 14 are provided at the front and rear ends F, R of the vehicle body 12 near the lower end of the vehicle body 12. Of the pair of bumpers 14, the front bumper 14f covers the entire front surface and part of the side surface near the lower end of the vehicle body 12. Of the pair of bumpers 14, the rear bumper 14r covers the entire rear surface and part of the side surface near the lower end of the vehicle body 12.

[0023] Wave transmitting and receiving units 15f, 15r that transmit and receive sound waves such as ultrasonic waves are disposed at predetermined ends of the vehicle body 12. For example, one or more wave transmitting and receiving units 15f are disposed on the front bumper 14f, and one or more wave transmitting and receiving units 15r are disposed on the rear bumper 14r. Hereinafter, unless otherwise specified, the wave transmitting and receiving units 15f, 15r will be simply referred to as the wave transmitting and receiving unit 15. Furthermore, the number and positions of the wave transmitting and receiving units 15 are not limited to the example shown in FIG. 2. For example, the vehicle 1 may be provided with wave transmitting and receiving units 15 on both the left and right sides.

[0024] In this embodiment, sonar using ultrasonic waves is used as an example of the wave transmitting and receiving unit 15, but the wave transmitting and receiving unit 15 may also be radar that transmits and receives electromagnetic waves. Alternatively, the vehicle 1 may be equipped with both sonar and radar. Furthermore, the wave transmitting and receiving unit 15 may simply be referred to as a sensor.

[0025] The wave transmitting and receiving unit 15 detects obstacles around the vehicle 1 based on the results of transmitting and receiving sound waves or electromagnetic waves. The wave transmitting and receiving unit 15 also measures the distance between the vehicle 1 and obstacles around the vehicle 1 based on the results of transmitting and receiving sound waves or electromagnetic waves.

[0026] Vehicle 1 is also equipped with a first vehicle-mounted camera 16a that takes pictures of the area in front of vehicle 1, a second vehicle-mounted camera 16b that takes pictures of the area behind vehicle 1, a third vehicle-mounted camera 16c that takes pictures of the area to the left of vehicle 1, and a fourth vehicle-mounted camera that takes pictures of the area to the right of vehicle 1. The fourth vehicle-mounted camera is not shown in the figure.

[0027] Hereinafter, when there is no need to distinguish between the first on-board camera 16a, the second on-board camera 16b, the third on-board camera 16c, and the fourth on-board camera, they will be simply referred to as on-board cameras 16. The locations and number of on-board cameras are not limited to the example shown in FIG. 2. For example, the vehicle 1 may also be equipped with only two on-board cameras, the first on-board camera 16a and the second on-board camera 16b. Alternatively, the vehicle 1 may have other on-board cameras in addition to those in the above example.

[0028] The on-board camera 16 is capable of capturing images of the surroundings of the vehicle 1, and is, for example, a camera that captures color images. The image data captured by the on-board camera 16 may be video or still images. The on-board camera 16 may be a camera built into the vehicle 1, or may be a camera of a drive recorder that is retrofitted to the vehicle 1.

[0029] The vehicle 1 is also equipped with an in-vehicle device 100. The in-vehicle device 100 is an information processing device that can be installed in the vehicle 1, and is, for example, an ECU (Electronic Control Unit) or an OBU (On Board Unit) provided inside the vehicle 1. Alternatively, the in-vehicle device 100 may be an external device installed near the dashboard of the vehicle 1. The in-vehicle device 100 may also function as a car navigation device or the like.

[0030] Next, a description will be given of the configuration of the vicinity of the driver's seat of the vehicle 1 according to this embodiment. Fig. 3 is a diagram showing an example of the configuration of the vicinity of the driver's seat 130a of the vehicle 1 according to the first embodiment.

[0031] 3, the vehicle 1 has a driver's seat 130a and a passenger's seat 130b. In front of the driver's seat 130a, a windshield 180, a dashboard 190, a steering wheel 140, a display device 120, and operation buttons 141 are provided.

[0032] The display device 120 is a display provided on a dashboard 190 of the vehicle 1. For example, the display device 120 is located in the center of the dashboard 190 as shown in FIG. 3. The display device 120 is, for example, a liquid crystal display or an organic EL (Electro Luminescence) display. The display device 120 may also function as a touch panel. The display device 120 is an example of a display unit in this embodiment.

[0033] The steering wheel 140 is provided in front of the driver's seat 130a and can be operated by the driver. The rotation angle of the steering wheel 140, i.e., the steering angle, is electrically or mechanically linked to the change in the direction of the front tires 13f, which are the steered wheels. The steered wheels may be the rear tires 13r, or both the front tires 13f and the rear tires 13r may be steered wheels.

[0034] The operation button 141 is a button that can accept an operation by a user. In this embodiment, the user is, for example, the driver of the vehicle 1. The position of the operation button 141 is not limited to the example shown in FIG. 3 , and it may be provided on the steering wheel 140, for example. The operation button 141 is an example of an operation unit in this embodiment. In addition, if the display device 120 also functions as a touch panel, the display device 120 may be an example of an operation unit. In addition, an operation terminal that can transmit a signal to the vehicle 1 from outside the vehicle 1, such as a tablet terminal, smartphone, remote controller, or electronic key (not shown), may be an example of an operation unit.

[0035] Next, the hardware configuration of the in-vehicle device 100 of this embodiment will be described.

[0036] Fig. 4 is a diagram showing an example of the hardware configuration of the in-vehicle device 100 according to the first embodiment. As shown in Fig. 4, the in-vehicle device 100 has a hardware configuration using a normal computer, in which a CPU (Central Processing Unit) 11A, a ROM 11B, a RAM 11C, a device I / F (Interface) 11D, a CAN (Controller Area Network) I / F 11E, a NW (Network) I / F 11F, an HDD 11G, etc. are interconnected via a bus 11H.

[0037] The CPU 11A is a calculation device that controls the entire in-vehicle device 100. The CPU 11A is an example of a processor in the in-vehicle device 100 of this embodiment, and another processor or processing circuit may be provided instead of the CPU 11A.

[0038] The ROM 11B, RAM 11C, and HDD 11G function as storage units. For example, the ROM 11B stores programs and the like that realize various processes by the CPU 11A. The RAM 11C is, for example, a main storage device of the in-vehicle device 100, and stores data necessary for various processes by the CPU 11A.

[0039] The device I / F 11D is an interface that can be connected to various devices. For example, the device I / F 11D is connected to a GPS device 11l and acquires, from the GPS device 11l, location information indicating the current location of the vehicle 1. The location information is, for example, latitude and longitude values ​​that indicate the absolute location of the vehicle 1.

[0040] The GPS device 11l is a device that identifies GPS coordinates that indicate the position of the vehicle 1 based on a GPS signal received by the GPS antenna 11J. The GPS antenna 11J is an antenna that can receive GPS signals.

[0041] The device I / F 11D also acquires images and detection results from the vehicle-mounted camera 16 and the wave transmitting / receiving unit 15.

[0042] The CAN I / F 11E is an interface for transmitting and receiving information to and from other ECUs mounted on the vehicle 1 via the CAN in the vehicle 1. Note that a communication standard other than CAN may also be adopted.

[0043] The NW I / F 11F is a communication device capable of communicating with an external information processing device such as the cloud server 2 via a network such as the Internet. The NW I / F 11F is capable of communication via, for example, a public line such as LTE (Long Term Evolution) (registered trademark) or short-range communication such as Wi-Fi (registered trademark) or Bluetooth (registered trademark). The NW I / F 11F of the in-vehicle device 100 may communicate directly with the cloud server 2 via the Internet, or may communicate indirectly via equipment such as another information processing device.

[0044] Next, functions of the in-vehicle device 100 of this embodiment will be described.

[0045] 5 is a block diagram showing an example of functions of the in-vehicle device 100 according to the first embodiment. As shown in FIG. 5, the in-vehicle device 100 includes an acquisition unit 101, a determination unit 102, a generation unit 103, a compression unit 104, a transmission unit 105, a reception unit 106, a vehicle control unit 107, a display control unit 108, a reception unit 109, and a storage unit 110.

[0046] The storage unit 110 is configured by, for example, a ROM 11B, a RAM 11C, or an HDD 11G. Although one storage unit 110 is included in the in-vehicle device 100 in FIG. 5, multiple storage media may function as the storage unit 110.

[0047] The acquiring unit 101, the determining unit 102, the generating unit 103, the compressing unit 104, the transmitting unit 105, the receiving unit 106, the vehicle control unit 107, the display control unit 108, and the accepting unit 109 are functions that are executed by the CPU 11A reading out a program stored in the ROM 11B or the HDD 11G, for example. Alternatively, a hardware circuit having these functions may be provided in the in-vehicle device 100.

[0048] The acquisition unit 101 acquires vehicle state information that indicates the state of the vehicle 1 and sensor data measured by sensors provided in the vehicle 1 .

[0049] In this embodiment, the sensor provided on the vehicle 1 is, for example, the in-vehicle camera 16 or the wave transmitting and receiving unit 15. More specifically, in this embodiment, an example in which the in-vehicle camera 16 is used as the sensor will be described. Also, in this embodiment, image data captured by the in-vehicle camera 16 will be described as an example of sensor data.

[0050] The acquisition unit 101 acquires image data of the surroundings of the vehicle 1 from the in-vehicle camera 16 via the device I / F 11D. The acquisition unit 101 also acquires ranging data of the distance between the vehicle 1 and obstacles around the vehicle 1 and the detection results of the obstacles from the wave transmitting and receiving unit 15 via the device I / F 11D.

[0051] The sensor may be both the in-vehicle camera 16 and the wave transmitting and receiving unit 15, or may be only the wave transmitting and receiving unit 15. The vehicle 1 may further include other sensors. If the sensor is the wave transmitting and receiving unit 15, the sensor data may be ranging data of the distance between the vehicle 1 and an obstacle around the vehicle 1 measured by the wave transmitting and receiving unit 15, or the detection result of the obstacle.

[0052] The vehicle state information in this embodiment includes at least the vehicle speed of the vehicle 1. The acquisition unit 101 acquires the vehicle speed of the vehicle 1 from another ECU via the CAN I / F 11E. The acquisition unit 101 may also acquire the wheel speed of the vehicle 1 from a wheel speed sensor or the like provided on the vehicle 1, and obtain the vehicle speed of the vehicle 1 from the wheel speed.

[0053] The vehicle state information may also include information other than vehicle speed. For example, the vehicle state information may include at least one of vehicle speed, GPS position information of the vehicle 1 measured by the GPS device 11l, peripheral information such as the gear state of the vehicle 1, steering angle, and illuminance around the vehicle 1, weather information around the vehicle 1, and the operating status of the wipers of the vehicle 1. This information is acquired by the acquisition unit 101 from each device of the vehicle 1. The GPS position information is used to identify the characteristics of the current position of the vehicle 1. For example, the acquisition unit 101 may obtain the characteristics of the current position of the vehicle 1 from map data and the GPS position information of the vehicle 1. The map data may be stored in an external device connected to the in-vehicle device 100 via the Internet or the like, or may be stored in the storage unit 110 of the in-vehicle device 100. The characteristics of the current position of the vehicle 1 may be, for example, a classification such as a parking lot, a general road, or a highway.

[0054] The determination unit 102 determines the compression rate of the sensor data according to the vehicle state information. For example, if the vehicle speed included in the vehicle state information is equal to or lower than a first threshold, the determination unit 102 determines to compress the sensor data at a low compression rate. Furthermore, if the vehicle speed included in the vehicle state information is higher than the first threshold, the determination unit 102 determines to compress the sensor data at a high compression rate. The low compression rate is an example of a first compression rate in the present application. Furthermore, the high compression rate is an example of a second compression rate in the present application. The specific numerical values ​​of the low compression rate and the high compression rate are not particularly limited, as long as the high compression rate is higher than the low compression rate. The value of the first threshold is not particularly limited.

[0055] In addition, in this embodiment, the compression rate is divided into two levels, a low compression rate and a high compression rate, but the compression rate may be divided into three or more levels. For example, the determination unit 102 may determine the compression rate in stages so that the compression rate increases as the vehicle speed increases.

[0056] When the vehicle speed is high, it is better for the in-vehicle device 100 to quickly obtain the results of ADAS processing from the cloud server 2 in order to control the driving of the vehicle 1. The higher the compression rate of the sensor data, the shorter the transmission time of the compressed sensor data between the vehicle 1 and the cloud server 2. Therefore, when the vehicle speed is high, the decision unit 102 increases the compression rate of the sensor data compared to when the vehicle speed is low, and quickly transmits the compressed sensor data to the cloud server 2.

[0057] Note that the compression method in this embodiment is not particularly limited, but is basically lossy compression. Therefore, the compressed sensor data transmitted from vehicle 1 to cloud server 2 remains smaller in data size than the data before compression even after being decompressed by cloud server 2. When cloud server 2 performs pedestrian detection processing based on image data transmitted from vehicle 1, the larger the size of the image data, the higher the accuracy of pedestrian detection becomes. For example, when vehicle 1 is traveling at a low speed, it is assumed that vehicle 1 is about to park or is traveling on a narrow road. In such cases, since there is a high possibility of a pedestrian suddenly running out into the road, cloud server 2 performs high-accuracy pedestrian detection using high-resolution image data.

[0058] Furthermore, the determination unit 102 may determine the compression rate of the sensor data according to vehicle state information other than the vehicle speed. For example, if the windshield wipers of the vehicle 1 are operating continuously, it is highly likely that it is raining. If the weather is raining, the driver's visibility around the vehicle 1 decreases. In such a case, the determination unit 102 determines the compression rate of the image data to be a low compression rate in order to improve the accuracy of pedestrian detection by the cloud server 2. Furthermore, if the current location of the vehicle 1 is in a parking lot, the determination unit 102 may determine the compression rate of the image data to be a low compression rate in order to improve the accuracy of pedestrian detection and other surrounding vehicles by the cloud server 2.

[0059] Furthermore, the determination unit 102 may determine the compression rate of the sensor data according to a combination of a plurality of pieces of information, for example, a combination of the vehicle speed and the characteristics of the current position of the vehicle 1.

[0060] Furthermore, the determination unit 102 may determine various characteristics of the sensor data in addition to the compression rate according to the vehicle state information. For example, when the image data is a moving image and the vehicle speed is equal to or less than a first threshold, the determination unit 102 determines the frame rate of the image data to be a low frame rate and the resolution of the image data to be a high resolution. Furthermore, when the vehicle speed is faster than the first threshold, the determination unit 102 determines the frame rate of the image data to be a high frame rate and the resolution of the image data to be a low resolution.

[0061] The low frame rate is an example of a first frame rate in this embodiment. The high frame rate is also an example of a second frame rate in this embodiment. The specific values ​​of the low frame rate and the high frame rate are not particularly limited, as long as the high frame rate is higher than the low frame rate. The high resolution is an example of a first resolution in this embodiment. The low resolution is an example of a second resolution in this embodiment. The specific values ​​of the high resolution and the low resolution are not particularly limited, as long as the high resolution is higher than the low resolution. The resolution determined by the determination unit 102 is the resolution in a state in which the image data is compressed and then expanded in the cloud server 2. If the image data is a still image, the determination unit 102 does not determine the frame rate, but determines the resolution.

[0062] Furthermore, although the frame rate and resolution are set to two levels in this embodiment, the frame rate and resolution may be divided into three or more levels. For example, the determination unit 102 may determine the frame rate in stages so that the frame rate increases as the vehicle speed increases. Furthermore, the determination unit 102 may determine the resolution in stages so that the resolution increases as the vehicle speed decreases. In general, the faster the vehicle speed of the vehicle 1, the more movement there is in the image data. By the determination unit 102 setting a high frame rate, it is possible to reduce the occurrence of missed detection of movement in the image data in the cloud server 2.

[0063] The generating unit 103 generates header-attached sensor data by adding the compression rate determined by the determining unit 102 to the sensor data. The header-attached sensor data is an example of sensor data with a compression rate in this embodiment.

[0064] Furthermore, when the determination unit 102 determines the frame rate and resolution of the image data in accordance with the vehicle state information, the generation unit 103 edits the image data to have the frame rate determined by the determination unit 102. Furthermore, the generation unit 103 may adjust the resolution of the image data after compressing and decompressing the image data so that the image data has the resolution determined by the determination unit 102.

[0065] Fig. 6 is a diagram showing an example of header-attached sensor data 400 according to the first embodiment. As shown in Fig. 6, the header-attached sensor data 400 is data to which a compression rate is assigned as header data 410 attached to sensor data 420, which is the main body of the data.

[0066] Note that the header-attached sensor data 400 may include data other than the compression rate in the header data 410. In the example shown in FIG. 6, the header data 410 includes the compression rate of the image data, the frame rate of the image data, and the resolution of the image data. The compression rate of the image data, the frame rate of the image data, and the resolution of the image data are examples of metadata of the image data. If the sensor data is not image data, the content of the metadata may differ from the example shown in FIG. 6.

[0067] In the header-attached sensor data 400 shown in FIG. 6, metadata such as compression rate is included in the header data 410 of the sensor data 420, which is image data. However, the metadata such as compression rate only needs to be associated with the sensor data 420, and does not necessarily need to be added to the sensor data 420 as header data 410.

[0068] 5, the compression unit 104 compresses the sensor data at different compression rates depending on the vehicle state information. More specifically, the compression unit 104 compresses the header-attached sensor data 400 generated by the generation unit 103 at the compression rate determined by the determination unit 102.

[0069] The transmission unit 105 associates the compression rate with the compressed sensor data 420 and transmits the data to the cloud server 2 via the NW I / F 11F. More specifically, the transmission unit 105 transmits the header-attached sensor data 400 compressed by the compression unit 104 to the cloud server 2.

[0070] The receiving unit 106 receives vehicle control data for controlling the traveling of the vehicle 1 from the cloud server 2 via the NW I / F 11F. The vehicle control data is, for example, a processing result by the ADAS. Specifically, the vehicle control data is a detection result of an obstacle around the vehicle 1, a signal instructing a braking operation of the vehicle 1, a signal instructing a steering operation of the vehicle 1, a signal instructing a speed of the vehicle 1, or the like.

[0071] The vehicle control unit 107 controls the traveling of the vehicle 1 based on the vehicle control data received by the receiving unit 106. For example, the vehicle control unit 107 controls the steering, braking, and acceleration / deceleration of the vehicle 1 based on the vehicle control data. In addition to the control based on the vehicle control data, the vehicle control unit 107 may also control the traveling of the vehicle 1 based on images of the surroundings of the vehicle 1 captured by the in-vehicle camera 16 and the distance to obstacles around the vehicle 1 detected by the wave transmitting and receiving unit 15.

[0072] The display control unit 108 causes the display device 120 to display various images and a GUI (Graphical User Interface). The display control unit 108 may also cause the display device 120 to display a warning of obstacle detection based on the vehicle control data received by the receiving unit 106.

[0073] The reception unit 109 receives various operations from the driver of the vehicle 1 via the operation button 141. In addition, if the display device 120 is equipped with a touch panel, the reception unit 109 receives various operations from the driver of the vehicle 1 that are input to the touch panel.

[0074] Next, the functions of the cloud server 2 will be described.

[0075] FIG. 7 is a block diagram showing an example of the functions of the cloud server 2 according to the first embodiment.

[0076] 7, the cloud server 2 includes a receiving unit 201, an ADAS processing unit 200, a transmitting unit 205, and a storage unit 210. The ADAS processing unit 200 is an example of a control processing unit in this embodiment.

[0077] The storage unit 210 is configured by, for example, a ROM, RAM, or HDD in a cloud environment.

[0078] The receiving unit 201, the ADAS processing unit 200, and the transmitting unit 205 are functions that are executed by, for example, a CPU in a cloud environment reading out a program stored in the storage unit 210.

[0079] The receiving unit 201 receives compressed sensor data 420 and the compression rate of the sensor data 420 from the in-vehicle device 100 mounted on the vehicle 1. More specifically, the receiving unit 201 receives compressed sensor data 400 with a header from the in-vehicle device 100 mounted on the vehicle 1.

[0080] The ADAS processing unit 200 performs different processing depending on the compression ratio of the sensor data 420. More specifically, the ADAS processing unit 200 performs different processing depending on the compression ratio included in the compressed sensor data 400 with a header.

[0081] 7, the ADAS processing unit 200 includes an obstacle detection unit 202, a learning unit 203, and an estimation unit 204. These functional units are examples of ADAS functions executed by the ADAS processing unit 200. Note that the functional units included in the ADAS processing unit 200 are not limited to these.

[0082] The obstacle detection unit 202 changes the threshold value for obstacle detection in the process of detecting an obstacle from the sensor data 420, depending on the compression rate of the sensor data 420. Hereinafter, the threshold value for obstacle detection will be referred to as the detection threshold value. Note that the obstacle detection unit 202 unpacks the compressed sensor data 420 and then uses it for obstacle detection.

[0083] For example, when the compression rate of the sensor data 420 is equal to or lower than the second threshold, the obstacle detection unit 202 uses the low compression rate detection threshold to perform obstacle detection based on the sensor data 420. When the compression rate of the sensor data 420 is higher than the second threshold, the obstacle detection unit 202 uses the high compression rate detection threshold to perform obstacle detection based on the sensor data 420.

[0084] The low-compression-ratio detection threshold is an example of a first detection threshold in this embodiment. The high-compression-ratio detection threshold is an example of a second detection threshold in this embodiment. The high-compression-ratio detection threshold is a value lower than the low-compression-ratio detection threshold. In other words, when the compression rate of the sensor data 420 is high, the obstacle detection unit 202 is more likely to determine that an obstacle exists around the vehicle 1 than when the compression rate of the sensor data 420 is low. When the sensor data 420 is image data, image data with a high compression rate has a lower resolution than image data with a low compression rate. Therefore, when image data with a high compression rate is used, the obstacle detection unit 202 lowers the detection threshold for obstacle detection to reduce missed detection of obstacles. The height of the detection threshold may be divided into two or more levels.

[0085] In addition, the obstacle detection unit 202 may generate a signal to instruct the braking operation of the vehicle 1 to avoid the detected obstacle, a signal to instruct the steering of the vehicle 1, or a signal to instruct the vehicle speed of the vehicle 1.

[0086] The learning unit 203 learns the sensor data transmitted from the in-vehicle device 100. The learning method is, for example, deep learning using a learning model, but is not limited to this. The learning unit 203 unpacks the compressed sensor data 420 and then uses it for learning.

[0087] The learning unit 203 uses different learning models depending on the compression rate of the sensor data 420. For example, when the compression rate of the sensor data 420 is equal to or lower than a second threshold, the learning unit 203 causes the low compression rate learning model to learn the sensor data 420. Furthermore, when the compression rate of the sensor data 420 is higher than the second threshold, the learning unit 203 causes the high compression rate learning model to learn the sensor data 420. The low compression rate learning model is an example of a first learning model in this embodiment. The high compression rate learning model is an example of a second learning model in this embodiment. The learning unit 203 stores the low compression rate learning model and the high compression rate learning model in, for example, the storage unit 210.

[0088] Standardizing the conditions of the learning data input to the learning model improves the learning accuracy of the learning model. As described above, when the sensor data 420 is image data, image data with a high compression rate has a lower resolution than image data with a low compression rate. Therefore, by the learning unit 203 using different learning models depending on the compression rate of the sensor data 420, the learning accuracy of the learning model is improved compared to inputting multiple pieces of sensor data 420 with different compression rates into one learning model. Note that the number of learning models is not limited to two, and may be three or more.

[0089] The estimation unit 204 performs estimation processing using the low compression ratio learning model and the high compression ratio learning model learned by the learning unit 203. The content of the estimation processing may be, for example, obstacle detection or forward collision warning.

[0090] For example, when the compression rate of the sensor data 420 is equal to or lower than the second threshold, the estimation unit 204 inputs the sensor data 420 to a trained learning model for a low compression rate and obtains the output from the trained learning model for a low compression rate as an estimation result. Also, when the compression rate of the sensor data 420 is higher than the second threshold, the estimation unit 204 inputs the sensor data 420 to a trained learning model for a high compression rate and obtains the output from the trained learning model for a high compression rate as an estimation result.

[0091] Note that the learning unit 203 and the estimation unit 204 do not need to function simultaneously. For example, the estimation unit 204 does not need to function until the low-compression-ratio learning model and the high-compression-ratio learning model have learned sensor data 420 equal to or greater than a specified threshold. Also, although the obstacle detection unit 202 and the estimation unit 204 are illustrated as separate functional units in FIG. 7 , the obstacle detection unit 202 may perform obstacle detection using the low-compression-ratio learning model and the high-compression-ratio learning model learned by the learning unit 203.

[0092] Note that the change in processing depending on the compression rate of the sensor data 420 is not limited to the above example. The ADAS processing unit 200 may change the processing algorithm depending on the compression rate of the sensor data 420. Furthermore, the ADAS processing unit 200 may execute different processing depending on metadata other than the compression rate. For example, the ADAS processing unit 200 may change the detection threshold, learning model, or algorithm used for processing depending on the frame rate or resolution included in the header data 410 of the header-attached sensor data 400.

[0093] The transmission unit 205 transmits vehicle control data, which is a result of processing by the ADAS processing unit 200, to the in-vehicle device 100. For example, the transmission unit 205 transmits the result of obstacle detection by the obstacle detection unit 202 to the in-vehicle device 100. The transmission unit 205 may also transmit to the in-vehicle device 100 a signal generated by the obstacle detection unit 202 to instruct the braking operation of the vehicle 1, a signal to instruct the steering of the vehicle 1, or a signal to instruct the vehicle speed of the vehicle 1.

[0094] Next, a flow of the transmission process of the sensor data 420 executed by the in-vehicle device 100 configured as above will be described.

[0095] 8 is a flowchart showing an example of the flow of the transmission process of sensor data 420 according to the first embodiment. The process of this flowchart starts, for example, when the in-vehicle device 100 receives power from the ignition power supply of the vehicle 1 and the ignition power supply is on. Also, when the in-vehicle device 100 receives power from the accessory power supply of the vehicle 1, the process of this flowchart starts when the accessory power supply is on.

[0096] First, the acquisition unit 101 acquires vehicle state information such as the vehicle speed of the vehicle 1 (S101). The acquisition unit 101 also acquires sensor data 420 (S102).

[0097] Next, the determination unit 102 determines whether the vehicle 1 is traveling (S103). For example, the determination unit 102 determines that the vehicle 1 is traveling when the vehicle speed of the vehicle 1 acquired by the acquisition unit 101 is equal to or greater than a threshold. Note that the determination unit 102 may determine whether the vehicle 1 is traveling based on the operating state of the accelerator pedal, etc.

[0098] If the determination unit 102 determines that the vehicle 1 is not moving (S103 "No"), the process returns to S101. If the vehicle 1 has not started moving, the processes of S101 to S103 are repeatedly executed. Note that if the vehicle 1 is not moving, the acquisition unit 101 does not need to acquire the sensor data 420.

[0099] Furthermore, when it is determined that the vehicle 1 is moving (S103 "Yes"), the determination unit 102 determines the compression rate, frame rate, and resolution of the sensor data 420 according to the vehicle state information (S104).

[0100] Next, the generating unit 103 edits the sensor data 420 in accordance with the frame rate and resolution determined by the determining unit 102 (S105).

[0101] Next, the generating unit 103 writes the compression rate, frame rate, and resolution determined by the determining unit 102 in the header of the sensor data 420 (S106).

[0102] Next, the compression unit 104 compresses the header-attached sensor data 400 at the compression rate determined by the determination unit 102 (S107).

[0103] Next, the transmitting unit 105 transmits the compressed sensor data 400 with the header to the cloud server 2 (S108).

[0104] If the ignition power supply or accessory power supply of the vehicle 1 is on (S109 "No"), the process returns to S101 and the process of this flowchart is repeated. If the ignition power supply or accessory power supply of the vehicle 1 is off (S109 "Yes"), the process of this flowchart ends.

[0105] Next, the flow of the ADAS processing executed by the cloud server 2 will be described.

[0106] 9 is a flowchart showing an example of the flow of ADAS processing executed by the cloud server 2 according to the first embodiment. The ADAS processing by the cloud server 2 is basically ready to be started at any time, and waits for reception of header-attached sensor data 400 from the in-vehicle device 100.

[0107] When the receiving unit 201 of the cloud server 2 receives the header-attached sensor data 400 from the in-vehicle device 100 mounted on the vehicle 1 (S201 "Yes") and the compression rate is equal to or lower than the second threshold (S202 "Yes"), the obstacle detection unit 202, learning unit 203, and estimation unit 204 included in the ADAS processing unit 200 of the cloud server 2 apply the detection threshold for low compression rate, the learning model for low compression rate, and the algorithm for low compression rate to perform various ADAS processing (S203).

[0108] Furthermore, when the receiving unit 201 receives the header-attached sensor data 400 from the on-board device 100 mounted on the vehicle 1 (S201 "Yes") and the compression rate is higher than the second threshold (S202 "No"), the obstacle detection unit 202, learning unit 203, and estimation unit 204 included in the ADAS processing unit 200 of the cloud server 2 perform ADAS processing by applying the detection threshold for high compression rate, the learning model for high compression rate, and the algorithm for high compression rate (S204).

[0109] After the processes of S203 and S204, the transmission unit 205 of the cloud server 2 transmits the vehicle control data, which is the result of the processing by the ADAS processing unit 200, to the in-vehicle device 100 (S205).

[0110] If the ADAS processing continues without ending (S206 "No"), the process returns to S201, and the processing of this flowchart is repeated. If the ADAS processing ends (S206 "Yes"), the processing of this flowchart ends. The ADAS processing by the cloud server 2 ends when, for example, the cloud server 2 is stopped by the administrator.

[0111] In this way, the in-vehicle device 100 of this embodiment compresses the sensor data 420 at different compression rates according to the vehicle state information of the vehicle 1, and transmits the compression rates in association with the compressed sensor data 420. Therefore, the cloud server 2 or edge server that receives the compressed sensor data from the in-vehicle device 100 of this embodiment can perform processing according to the compression rate of the sensor data.

[0112] As a comparative example, if sensor data is compressed at different compression rates depending on vehicle state information and only the compressed sensor data is transmitted to a cloud server or an edge server, the cloud server or edge server that receives the compressed sensor data cannot identify the compression rate of the received compressed sensor data, making it difficult to change processing depending on the compression rate. Therefore, in the comparative example, the same processing is performed on sensor data with different data sizes due to different compression rates. In contrast, the in-vehicle device 100 of this embodiment transmits the compressed sensor data 420 in association with the compression rate. This allows the cloud server 2 or edge server that receives the compressed sensor data 420 to perform different processing depending on the compression rate, thereby improving the accuracy of the processing results.

[0113] Furthermore, the in-vehicle device 100 of this embodiment generates header-attached sensor data 400 by adding a compression rate determined according to vehicle state information to the acquired sensor data as header data, compresses the header-attached sensor data 400 at the determined compression rate, and transmits the compressed header-attached sensor data 400. Therefore, according to the in-vehicle device 100 of this embodiment, the compression rate and the sensor data 420 can be transmitted together to the cloud server 2 or the like, making it easy for the receiving side to grasp the correspondence between the compression rate and the sensor data 420.

[0114] Furthermore, in this embodiment, the vehicle state information includes at least the vehicle speed of the vehicle 1. The in-vehicle device 100 of this embodiment determines to compress the sensor data 420 at a low compression rate when the vehicle speed is equal to or lower than a first threshold, and determines to compress the sensor data 420 at a high compression rate when the vehicle speed is higher than the first threshold. Therefore, according to the in-vehicle device 100 of this embodiment, when the vehicle speed of the vehicle 1 is high, the compression rate of the sensor data 420 is increased to shorten the time required for data transmission to the cloud server 2 or the like, thereby enabling the processing results from the cloud server 2 or the like to be obtained quickly. Furthermore, according to the in-vehicle device 100 of this embodiment, when the vehicle speed of the vehicle 1 is low, the compression rate of the sensor data 420 is kept low to reduce degradation of the sensor data 420, thereby improving the accuracy of ADAS processing in the cloud server 2 or the like. In other words, the in-vehicle device 100 of this embodiment can appropriately adjust the balance between the data transmission rate and the accuracy of ADAS processing according to the vehicle speed of the vehicle 1.

[0115] Furthermore, in this embodiment, the sensor data 420 includes at least image data captured around the vehicle 1. When the vehicle speed of the vehicle 1 is equal to or lower than a first threshold, the in-vehicle device 100 of this embodiment determines the frame rate of the image data to be a low frame rate and the resolution of the image data to be a high resolution. When the vehicle speed of the vehicle 1 is higher than the first threshold, the in-vehicle device 100 of this embodiment determines the frame rate of the image data to be a high frame rate and the resolution of the image data to be a low resolution. Therefore, according to the in-vehicle device 100 of this embodiment, in addition to adjusting the balance between the data transmission rate and the accuracy of the ADAS processing using the compression rate, it is also possible to adjust the balance between the data transmission rate and the accuracy of the ADAS processing according to the vehicle speed of the vehicle 1 using the frame rate and the resolution.

[0116] Furthermore, the vehicle state information of this embodiment includes at least one of the vehicle speed of the vehicle 1, the position of the vehicle 1, the gear state of the vehicle 1, the steering angle of the vehicle 1, the illuminance around the vehicle 1, weather information around the vehicle 1, and the operation state of the wipers of the vehicle 1. Therefore, according to the on-board device 100 of this embodiment, it is possible to appropriately adjust the balance between the data transmission speed and the accuracy of the ADAS processing according to various states of the vehicle 1 as well as the vehicle speed.

[0117] Furthermore, the cloud server 2 of this embodiment receives the compressed sensor data 420 and the compression rate of the sensor data 420 from the in-vehicle device 100, and executes different processes depending on the compression rate of the sensor data 420. Therefore, the cloud server 2 of this embodiment can separate processes depending on the compression rate, thereby improving the accuracy of the processing results.

[0118] Furthermore, when the compression rate of the sensor data 420 is equal to or lower than the second threshold, the cloud server 2 of this embodiment uses a detection threshold for a low compression rate to perform obstacle detection based on the sensor data 420, and when the compression rate of the sensor data 420 is higher than the second threshold, the cloud server 2 uses a detection threshold for a high compression rate to perform obstacle detection based on the sensor data 420. Therefore, according to the cloud server 2 of this embodiment, when image data with a high compression rate is used, the detection threshold for obstacle detection can be lowered, thereby reducing missed detection of obstacles.

[0119] Furthermore, the cloud server 2 of this embodiment trains the sensor data 420 using a learning model for low compression rates when the compression rate is equal to or lower than a second threshold, and trains the sensor data 420 using a learning model for high compression rates when the compression rate is higher than the second threshold. Therefore, by using different learning models depending on the compression rate, the cloud server 2 of this embodiment can improve the learning accuracy of the learning model compared to inputting multiple pieces of sensor data 420 with different compression rates into one learning model.

[0120] (Second embodiment) In the first embodiment described above, the cloud server 2 executes the ADAS processing based on the sensor data 420 transmitted from the in-vehicle device 100, but the entity that executes the ADAS processing is not limited to the cloud server 2. For example, an edge server may execute the ADAS processing.

[0121] 10 is a diagram showing an example of information communication between a vehicle 1, an edge server 3, and a cloud server 2 according to the second embodiment. In this embodiment, the edge server 3 and the cloud server 2 are examples of information processing devices.

[0122] The edge server 3 is a computer that can store the processing of the on-vehicle device 100 using edge computing technology. The edge server 3 includes, for example, a processor such as a CPU and storage devices such as a RAM, a ROM, and an HDD. The edge server 3 is installed, for example, in a communication base station or a transportation infrastructure facility, and communicates information with the on-vehicle device 100 installed in the vehicle 1 and the cloud server 2.

[0123] For example, in this embodiment, of the ADAS processing unit 200 of the cloud server 2 in the first embodiment shown in Fig. 7, the obstacle detection unit 202 and the estimation unit 204 are provided in the edge server 3. Also, of the ADAS processing unit 200 of the cloud server 2 in the first embodiment shown in Fig. 7, the learning unit 203 is provided in the cloud server 2. Also, functional units equivalent to the receiving unit 201, transmitting unit 205, and storage unit 210 of the cloud server 2 in the first embodiment shown in Fig. 7 are provided in both the edge server 3 and the cloud server 2.

[0124] The receiving unit of the edge server 3 receives the compressed sensor data with a header 400 from the in-vehicle device 100. The obstacle detecting unit 202 and the estimating unit 204 of the edge server 3 perform processing according to the compression rate, similar to the obstacle detecting unit 202 and the estimating unit 204 of the cloud server 2 in the first embodiment. The transmitting unit of the edge server 3 transmits vehicle control data based on the processing results by the obstacle detecting unit 202 or the estimating unit 204 to the vehicle 1. The transmitting unit of the edge server 3 also transmits the compressed sensor data with a header 400 received from the in-vehicle device 100 to the cloud server 2.

[0125] The receiving unit of the cloud server 2 receives the compressed header-attached sensor data 400 from the edge server 3. As in the first embodiment, the learning unit 203 of the cloud server 2 performs learning using a learning model according to the compression rate of the header-attached sensor data 400. In addition, the transmitting unit of the cloud server 2 transmits the trained model trained by the learning unit 203 to the edge server 3. The trained model is used, for example, by the estimating unit 204 or the obstacle detecting unit 202 of the edge server 3.

[0126] By having the obstacle detection unit 202 and the learning unit 203 in the edge server 3 in this way, the vehicle control data, which is the processing result based on the header-attached sensor data 400, can be transmitted to the in-vehicle device 100 more quickly than if the processing were performed by the cloud server 2.

[0127] In addition, since the cloud server 2 generally has fewer storage capacity limitations than the edge server 3, learning processes that take time but do not affect the driving control of the vehicle 1 can be executed by the cloud server 2, making it possible to learn large amounts of sensor data 420.

[0128] 10 illustrates a case where both the edge server 3 and the cloud server 2 are used, but alternatively, a configuration may be adopted in which the cloud server 2 is not provided and processing is performed only by the edge server 3 and the in-vehicle device 100. In this case, the edge server 3 is an example of an information processing device.

[0129] (Third embodiment) In the second embodiment described above, the edge server 3 is provided outside the vehicle 1, but the edge server 3 may be provided inside the vehicle 1. Fig. 11 is a diagram showing an example of information communication between the vehicle 1, the edge server 3, and the cloud server 2 according to the third embodiment.

[0130] 11, the edge server 3 of this embodiment is mounted on the vehicle 1, similar to the in-vehicle device 100. By mounting the edge server 3 on the vehicle 1 in this manner, the in-vehicle device 100 and the edge server 3 can be connected by wire within the vehicle 1, which is expected to improve communication speed.

[0131] The functions of the in-vehicle device 100, the cloud server 2, and the edge server 3 in each of the above-described embodiments are realized, for example, by a CPU executing a program. The programs executed by the in-vehicle device 100, the cloud server 2, and the edge server 3 in each of the above-described embodiments are provided by being recorded in an installable or executable file format on a computer-readable recording medium such as a CD-ROM, a CD-R, a DVD (Digital Versatile Disk), or a flash memory.

[0132] The programs executed by the in-vehicle device 100, the cloud server 2, and the edge server 3 of each of the above-described embodiments may be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network. The programs executed by the in-vehicle device 100, the cloud server 2, and the edge server 3 of each of the above-described embodiments may be provided or distributed via a network such as the Internet.

[0133] Furthermore, the programs executed by the in-vehicle device 100, the cloud server 2, and the edge server 3 in each of the above-described embodiments may be configured to be provided by being pre-installed in a ROM or the like.

[0134] Although several embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, as well as within the scope of the invention described in the claims and their equivalents. [Explanation of symbols]

[0135] 1 vehicle 2. Cloud Server 3 Edge Server 15, 15f, 15r Transmitting and receiving unit 16, 16a~16c In-vehicle camera 100 Onboard equipment 101 Acquisition Department 102 Decision Section 103 Generation part 104 Compression section 105 Transmitter 106 Receiving unit 107 Vehicle control unit 108 Display control unit 109 Reception 110 Storage section 120 Display device 200 ADAS processing unit 201 Receiving unit 202 Obstacle detection unit 203 Learning Department 204 Estimation section 205 Transmitter 210 Storage section 400 Sensor data with header 410 Header Data 420 Sensor Data

Claims

1. an acquisition unit that acquires vehicle state information indicating a state of the vehicle and sensor data measured by a sensor provided in the vehicle; a determination unit that determines a compression rate of the sensor data in accordance with the vehicle state information; a compression unit that compresses the sensor data at a compression rate determined in accordance with the vehicle state information; a generating unit that generates compressed sensor data with a compression ratio by adding the compression ratio determined by the determining unit to the compressed sensor data; a transmission unit that transmits the compressed sensor data with the compression ratio, moreover, the vehicle state information includes at least a vehicle speed of the vehicle; The determination unit If the vehicle speed is equal to or less than a first threshold, it is determined that the sensor data is to be compressed at a first compression rate; If the vehicle speed is higher than the first threshold, it is determined that the sensor data is to be compressed at a second compression rate higher than the first compression rate. In-vehicle device.

2. The sensor data includes at least image data of an area around the vehicle, The determination unit When the vehicle speed is equal to or less than the first threshold, the frame rate of the image data is determined to be a first frame rate; When the vehicle speed is faster than the first threshold value, the frame rate of the image data is determined to be a second frame rate higher than the first frame rate; the generation unit edits the image data based on the frame rate determined by the determination unit. The in-vehicle device according to claim 1 .

3. The sensor data includes at least image data of an area around the vehicle, The determination unit When the vehicle speed is equal to or less than the first threshold, the resolution of the image data is determined to be a first resolution; If the vehicle speed is faster than the first threshold value, the resolution of the image data is determined to be a second resolution lower than the first resolution; the generation unit edits the image data based on the resolution determined by the determination unit. The in-vehicle device according to claim 1 .

4. The vehicle state information includes at least one of a position of the vehicle, a gear state of the vehicle, a steering angle of the vehicle, illumination around the vehicle, weather information around the vehicle, and an operation state of a wiper of the vehicle. The in-vehicle device according to claim 1 .

5. Acquire vehicle state information indicating a state of the vehicle and sensor data measured by a sensor provided in the vehicle; determining a compression rate of the sensor data in accordance with the vehicle state information; compressing the sensor data at a compression rate determined in accordance with the vehicle state information; generating compressed sensor data with a compression ratio by adding the determined compression ratio to the compressed sensor data; Transmitting the compressed sensor data with the compression ratio; the vehicle state information includes at least a vehicle speed of the vehicle; The compression ratio is When the vehicle speed is equal to or less than a first threshold, a first compression rate is determined for the sensor data; When the vehicle speed is faster than the first threshold, a second compression rate higher than the first compression rate is determined for the sensor data. Sensor data transmission method.

6. The sensor data includes at least image data of an area around the vehicle, When the vehicle speed is equal to or less than the first threshold, the frame rate of the image data is determined to be a first frame rate; When the vehicle speed is faster than the first threshold value, the frame rate of the image data is determined to be a second frame rate higher than the first frame rate; The image data is edited based on the determined frame rate. The sensor data transmission method according to claim 5 .

7. The sensor data includes at least image data of an area around the vehicle, When the vehicle speed is equal to or less than the first threshold, the resolution of the image data is determined to be a first resolution; If the vehicle speed is faster than the first threshold value, the resolution of the image data is determined to be a second resolution lower than the first resolution; The image data is edited based on the determined resolution. The sensor data transmission method according to claim 6 .

8. The vehicle state information includes at least one of a position of the vehicle, a gear state of the vehicle, a steering angle of the vehicle, illumination around the vehicle, weather information around the vehicle, and an operation state of a wiper of the vehicle. The sensor data transmission method according to claim 6 .

Images