Vehicle-mounted data acquisition system and vehicle

Abstract

The utility model discloses a vehicle-mounted data acquisition system and a vehicle. The vehicle-mounted data acquisition system comprises a signal triggering device; the signal triggering device comprises a voice recognition module and an event camera; the event camera is arranged on a column A of the vehicle; a vehicle-mounted data collector; and the processing unit is respectively coupled with the voice recognition module, the event camera and the vehicle-mounted data acquisition unit, and the processing unit is configured to receive a trigger signal sent by the voice recognition module and / or the event camera and control the vehicle-mounted data acquisition unit to perform vehicle-mounted data acquisition. According to the scheme, triggering of non-contact vehicle-mounted data acquisition is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle testing, in particular to a vehicle-mounted data acquisition system and a vehicle. BACKGROUND

[0002] With the gradual popularization of intelligent vehicles, it is necessary to test intelligent vehicles on the road. A vehicle-mounted data acquisition device is an instrument for collecting data during the road test of an intelligent vehicle. During data collection, the name of the triggering event (such as a false action of an automatic brake assist system or a missed action of an automatic brake assist system) and the data within a certain period of time before and after the triggering event are recorded for later analysis.

[0003] In related technologies, in order to improve the operation convenience of an operator, a vehicle-mounted data acquisition system is provided with a camera in the vehicle, which is used to obtain eye movement time sequence images, lip time sequence images or hand gesture time sequence images of the operator to obtain eye movement information, lip movement information or hand gesture information of the operator, and then determine whether a triggering event occurs. However, in a high-illumination scene, it is difficult for the camera to obtain clear eye movement images, lip movement images or hand gesture images, which reduces the accuracy of data triggering. UTILITY MODEL CONTENT

[0004] The present application provides a vehicle-mounted data acquisition system and a vehicle.

[0005] One of the technical solutions adopted by the present application is to provide a vehicle-mounted data acquisition system, which comprises:

[0006] a signal triggering device; the signal triggering device comprises a voice recognition module and an event camera; the event camera is arranged on an A-pillar of the vehicle;

[0007] a vehicle-mounted data acquisition device;

[0008] a processing unit, which is coupled to the voice recognition module, the event camera and the vehicle-mounted data acquisition device respectively, and is configured to receive a triggering signal sent by the voice recognition module and / or the event camera and control the vehicle-mounted data acquisition device to collect vehicle-mounted data.

[0009] Optionally, the signal triggering device comprises a physical button, which is coupled to the processing unit and arranged on a steering wheel of the vehicle.

[0010] Optionally, the steering wheel comprises a gas bag cover, a wheel rim and spokes, and the gas bag cover is connected to the wheel rim through the spokes.

[0011] The signal triggering device further comprises a plurality of capacitive sensors, which are coupled to the processing unit.

[0012] Optionally, the physical button is arranged on the spokes, and the plurality of capacitive sensors are arranged on the wheel rim.

[0013] Optionally, the signal triggering device further comprises at least one millimeter wave sensor, the at least one millimeter wave sensor being coupled to the processing unit and arranged on the instrument panel of the vehicle.

[0014] Optionally, the signal triggering device further comprises at least one ultrasonic sensor array, the at least one ultrasonic sensor array being coupled to the processing unit and arranged on the instrument panel of the vehicle.

[0015] Optionally, the vehicle data acquisition system further comprises a communication unit, the communication unit being coupled to the processing unit, and the communication unit being configured to send the vehicle data acquired by the vehicle data acquisition device to a cloud server.

[0016] Optionally, the vehicle data acquisition system further comprises a prompt light, the prompt light being coupled to the processing unit.

[0017] Optionally, the vehicle data acquisition system further comprises a loudspeaker, the loudspeaker being coupled to the processing unit.

[0018] Optionally, the vehicle data acquisition device comprises at least one of a camera, a laser radar, an ultrasonic radar, a millimeter wave radar, a gyroscope, and a wheel speed sensor.

[0019] Another technical solution adopted in the present application is to provide an automobile comprising the vehicle data acquisition system as described above.

[0020] The beneficial effects of the present application are that the event camera arranged on the A-pillar of the vehicle generates images only according to the brightness change of the pixels in the field of view, so that clear eye timing images, lip timing images or gesture images can still be acquired in high-illumination scenes, and thus eye movement information, lip movement information or gesture information can be effectively extracted, and the recognition accuracy of data triggering is improved. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0022] Figure 1 is a signal output schematic diagram of the event camera and the conventional CCD / CMOS camera under the rotating disc provided by the present application;

[0023] Figure 2 is a signal output schematic diagram of the event camera and the conventional CCD / CMOS camera when the disc rotates from static to rotating provided by the present application;

[0024] Figure 3is a structural schematic diagram of an embodiment of a vehicle data acquisition system provided in the present application;

[0025] Figure 4 is a structural schematic diagram of another embodiment of a vehicle data acquisition system provided in the present application;

[0026] Figure 5 is a structural schematic diagram of an embodiment of a vehicle provided in the present application. DETAILED DESCRIPTION

[0027] The technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0028] In the process of data acquisition of a vehicle, a signal triggering device is usually used to start data acquisition. The currently commonly used triggering method is a physical key switch, which needs to be manually pressed by an operator. In some scenarios, for example, when the operator needs to drive the vehicle and perform other operations at the same time, there may be a problem of inconvenience in manual triggering.

[0029] In some related technical solutions, a voice recognition module is installed in the signal triggering device. The operator can speak a related trigger word, the voice recognition module recognizes the trigger word, and sends a trigger signal to a processing unit to control the vehicle data acquisition device to perform data acquisition. In actual operation, the operator may forget to speak the related voice trigger word, resulting in a decrease in response speed of acquisition.

[0030] In another related technical solution, the signal triggering device is provided with a camera, which is used to recognize any one of eye movement information, lip movement information (lip language), and gesture information of the operator, and to more conveniently realize triggering of data acquisition in a non-contact manner. The camera in this solution uses a CCD / CMOS sensor as an image sensor, and the recognition accuracy is seriously affected by light. It should be noted that in the scenario of vehicle driving, strong light and weak light scenarios are common. For example, when the vehicle drives out of a tunnel, the brightness changes greatly. In this scenario, the recognition accuracy of eye movement information, lip movement information, or gesture information will be greatly reduced.

[0031] Exemplarily, the eye movement information can include the blinking frequency of the operator, the gaze direction of the eyes, and the like. The lip movement information can be (time sequence) action information of the lips of the operator. The gesture information can be (time sequence) action information of the hands of the operator.

[0032] Event Camera is a kind of bionic visual sensor, which contains a dynamic visual sensor completely different from CCD / CMOS sensor. Optionally, the dynamic visual sensor can include one or more of the following: Event Vision Sensor (DVS), Asynchronous Time Based Image Sensor (ATIS), Dynamic and Active Pixel Vision Sensor (DAVIS), which are not limited here.

[0033] Unlike conventional CCD / CMOS cameras that capture complete image frames at fixed time intervals, event cameras independently capture the moment when the brightness of each pixel changes. When the brightness of a pixel changes beyond a certain threshold, the pixel triggers an event and outputs the timestamp, spatial coordinates and polarity of the brightness change (increase or decrease) of the event. Therefore, the event camera outputs are not conventional image frames, but a series of asynchronous event streams.

[0034] Specifically, the event camera has the following characteristics:

[0035] (1) Low latency: Since the event camera only records events of brightness changes, it has extremely low latency and can respond to changes in dynamic scenes in real time.

[0036] (2) Low power consumption: The event camera only transmits information when the brightness changes, so the power consumption is extremely low, suitable for application scenarios that need to run for a long time.

[0037] Please refer to Figure 1 and Figure 2 , Figure 1 are the signal output schematic diagrams of conventional CCD / CMOS cameras and event cameras under rotating discs. Figure 2 are the signal output schematic diagrams of conventional CCD / CMOS cameras and event cameras when the disc rotates from static to rotating.

[0038] Figure 1 and Figure 2 The left side of each disc has a black spot, and the black spot rotates counterclockwise around the center of the disc, Figure 1 and Figure 2 The upper right of each represents a number of visible light images obtained by a conventional CCD / CMOS camera, Figure 1 and Figure 2 The lower right of each represents an image captured by an event camera.

[0039] As Figure 1As shown, the conventional CCD / CMOS camera takes several visible light images in time, including the center point of the disc, the black spot, the disc contour, etc., while the event camera takes the event sensing image containing only the motion information of the black spot.

[0040] As shown, for the same disc, the several visible light images taken in time by the conventional CCD / CMOS camera contain the center point of the disc, the black spot, the disc contour, etc., when the disc is not rotating, while the event camera does not take any image information at this time. After the disc starts to rotate, the event camera starts to take the event sensing image containing only the motion of the black spot. Figure 2

[0041] Further, the event camera outputs the visual signal in the form of a sparse event stream, and the event stream does not contain any information of the static background, thus filtering a large amount of redundant data. Further, in the process of eye movement recognition, lip reading or gesture recognition, the event camera can recognize the information related to the trigger signal (eye movement information, lip, gesture) more quickly due to the reduction of a large amount of redundant data, thus improving the speed of signal triggering.

[0042] As shown, Figure 3 The vehicle-mounted data acquisition system 10 provided by the application includes a signal triggering device 11, a vehicle-mounted data acquisition device 12 and a processing unit 13.

[0043] The signal triggering device 11 includes a voice recognition module 111 and an event camera 112. The event camera 112 is arranged on the A-pillar of the vehicle. By arranging the event camera 112 on the A-pillar of the vehicle, the event camera 112 can more easily acquire the eye movement information, lip movement information or gesture information of the operator.

[0044] In some embodiments, the voice recognition module 111 is arranged inside the vehicle. Further, the voice recognition module 111 can include a microphone, an audio decoder and a voice recognition unit. The microphone is configured to collect the voice signal in the vehicle. The audio decoder is used for AD conversion and decoding operation of the voice signal to obtain decoding information. The voice recognition unit is used for converting the decoding information into output text. Further, the voice recognition unit judges the similarity degree of the output text and the trigger word. If the similarity degree is greater than a certain threshold, the voice recognition unit sends a trigger signal to the processing unit 13.

[0045] ​In some embodiments, the event camera 112 comprises an image acquisition unit, an image processing unit and a signal triggering unit, the image acquisition unit is configured to acquire an event image, the image processing unit is configured to process the event image to obtain a target image output by the event camera, and further, the signal triggering unit is configured to calculate a similarity between the target image and a preset image (e.g., a gesture image, an eye movement image, a lip movement image), and if the similarity is greater than a certain threshold, the signal triggering unit sends a trigger signal to the processing unit.

[0046] For example, the image processing unit analyzes the event image acquired by the image acquisition unit to obtain the target image, and then performs gesture recognition on the target image. For example, the image processing unit sets the background of the target image as a first color and sets the pixel points corresponding to the dynamic event as a second color, and the first color and the second color are different.

[0047] Optionally, the event image contains a series of events to generate row and column information of the pixel points.

[0048] In some possible embodiments, the image processing unit processes the event image to obtain the target image, and the steps include:

[0049] The background of the target image is set as a first color. For example, the first color is black.

[0050] The pixel points corresponding to the dynamic event are set as a second color, and the first color and the second color are different. Optionally, the second color is the foreground color of the first color. For example, when the first color is black, the second color is white.

[0051] Optionally, the format type of the target image can be YUV, RGB, etc., which is not limited here.

[0052] The processing unit 13 is coupled with the voice recognition module 111, the event camera 112 and the vehicle-mounted data collector 12, and the processing unit 13 is configured to receive the trigger signal sent by the voice recognition module 111 and / or the event camera 112, and send a control signal to the vehicle-mounted data collector 12 to control the vehicle-mounted data collector 12 to collect vehicle-mounted data.

[0053] In some embodiments, the signal triggering device 11 comprises a physical button 113, the physical button 113 is coupled with the processing unit 13, and the physical button 113 is arranged on the steering wheel of the vehicle.

[0054] It can be understood that the processing unit 13 is configured to receive the trigger signal sent by at least one of the voice recognition module 111, the event camera 112 and the physical button 113, and control the vehicle-mounted data collector 12 to collect vehicle-mounted data.

[0055] In some embodiments, the signal triggering device 11 further comprises a plurality of capacitive sensors 114 coupled with the processing unit 13.

[0056] Further, the steering wheel comprises an airbag cover, a rim and spokes, the airbag cover being connected with the rim through the spokes.

[0057] It is to be noted that the physical button 113 is arranged on the spokes of the steering wheel, so that the data mis-collection caused by the operator's misoperation in the normal driving state can be reduced.

[0058] Specifically, the capacitive sensor 114 is an electrostatic capacitive sensor, and the capacitive sensor 114 is configured to detect the capacitance value between the operator and the capacitive sensor 114. Further, since the capacitance value can be used to represent the distance between the operator's gesture and the capacitive sensor 114, the capacitive sensor 114 can be used to obtain the distance between the operator's non-contact gesture and itself. In this embodiment, the plurality of capacitive sensors 114 arranged on the rim of the steering wheel can accurately obtain the operator's non-contact gesture.

[0059] In addition, the capacitive sensor 114 can also be used to detect the holding condition of the operator on the rim. That is, the capacitive sensor 114 can also be configured to detect the operator's contact gesture on the rim. For example, the contact gesture can include at least one of a pressing gesture, a sliding gesture, and a handwriting gesture, which is not limited herein.

[0060] In some embodiments, the signal triggering device 11 further comprises at least one millimeter wave sensor 115 coupled with the processing unit 13, and the millimeter wave sensor 115 is arranged on the instrument panel of the vehicle.

[0061] In some application scenarios, the millimeter wave sensor 115 is configured to obtain the operator's gesture, and according to the matching relationship between the operator's gesture and a preset gesture, to send a triggering signal to the processing unit 13.

[0062] In some embodiments, the signal triggering device 11 further comprises at least one ultrasonic sensor array 116 coupled with the processing unit 13, and the ultrasonic sensor array 116 is arranged on the instrument panel of the vehicle.

[0063] It can be understood that the ultrasonic sensor array 116 is composed of a plurality of ultrasonic sensors, and the ultrasonic sensor array 116 determines the gesture action of the operator by obtaining the distance and angle between the operator's gesture and each ultrasonic sensor, so as to send a triggering signal to the processing unit 13.

[0064] In some application scenarios, the illuminance of the in-vehicle environment is low, and the event camera 112 may not be able to effectively obtain an event image containing the operator's gesture. By providing the signal triggering device 11 with a millimeter wave sensor 115 and / or an ultrasonic sensor array 116, the recognition capability of the signal triggering device 11 in a low-illuminance environment is effectively improved.

[0065] In some embodiments, the vehicle data acquisition system 10 comprises a communication unit 14 coupled to the processing unit 13, and the communication unit 14 is configured to send the vehicle data acquired by the vehicle data acquisition device 12 to a cloud server.

[0066] In some possible embodiments, the communication unit 14 can be a 4G communication module.

[0067] Alternatively, the communication unit 14 can be one or a combination of a Wi-Fi module, a UWB (Ultra-Wideband) module, a ZigBee (ZigBee) module, and a 5G communication module, without limitation.

[0068] In some embodiments, the vehicle data acquisition system further comprises a prompt light 15 coupled to the processing unit 13. The prompt light 15 is configured to receive a control signal sent by the processing unit 13 and issue a light prompt to the operator. In some application scenarios, the prompt light 15 can be used to prompt the operator that the vehicle data acquisition is in progress and / or the vehicle data acquisition is complete.

[0069] In some embodiments, the vehicle data acquisition system further comprises a loudspeaker 16 coupled to the processing unit 13. The loudspeaker 16 is configured to receive a control signal sent by the processing unit 13 and issue an audible prompt to the operator. In some application scenarios, the loudspeaker 16 can be used to prompt the operator that the vehicle data acquisition is in progress and / or the vehicle data acquisition is complete.

[0070] Of course, the loudspeaker 16 can be used in combination with the prompt light 15 to prompt the operator of the current status of the vehicle data acquisition.

[0071] In some possible embodiments, considering that the operator may not be able to conveniently obtain relevant prompt information, a vibration motor (not shown in the figure) is further provided on the steering wheel, the vibration motor is coupled to the processing unit 13, and the vibration motor is configured to receive a control signal sent by the processing unit 13 and issue a vibration prompt to the operator. In this way, the operator can more conveniently know whether the vehicle data acquisition is in progress.

[0072] In some embodiments, the vehicle data acquisition device 12 comprises at least one of a camera, a laser radar, an ultrasonic radar, a millimeter wave radar, a gyroscope, and a wheel speed sensor.

[0073] Optionally, the camera can include a camera disposed outside the vehicle and a camera disposed inside the vehicle, wherein the camera disposed outside the vehicle is configured to acquire the environment information outside the vehicle, and the camera disposed inside the vehicle is configured to acquire the current state of the operator.

[0074] Optionally, the laser radar, the ultrasonic radar, and the millimeter wave radar are all disposed outside the vehicle and are respectively configured to acquire the environment information outside the vehicle.

[0075] In some embodiments, the gyroscope is configured to acquire the acceleration information of the vehicle.

[0076] In some embodiments, the wheel speed sensor is configured to acquire the speed information of the vehicle.

[0077] In some possible application scenarios, the vehicle-mounted data collector 12 can further include a GNSS (Global Navigation Satellite System) module.

[0078] In some possible application scenarios, the vehicle-mounted data collector 12 can be a domain controller of the vehicle, wherein the domain controller is connected with at least one of the camera, the laser radar, the ultrasonic radar, the millimeter wave radar, the gyroscope, the wheel speed sensor, and the GNSS module.

[0079] In the above scheme, the event camera disposed on the A-pillar of the vehicle generates an image only according to the brightness change of the pixels in the field of view, so that a clear eye timing image, lip timing image, or gesture image can still be acquired in a high-illumination scenario, and then the eye movement information, lip movement information, or gesture information can be effectively extracted, and the recognition accuracy of data triggering is improved.

[0080] Please refer to Figure 4 , Figure 4 is a structural schematic diagram of another embodiment of the vehicle-mounted data collection system provided in the present application.

[0081] In the present embodiment, the vehicle-mounted data collection system 20 includes a physical switch 21, a voice recognition module 22, an event camera 23, a signal control module 24, a data collection device 25, a loudspeaker 26, and a prompt lamp 27.

[0082] The signal control module 24 is connected with the physical switch 21, the voice recognition module 22, and the event camera 23, and the data collection device 25 is connected with the signal control module 24, the loudspeaker 26, and the prompt lamp 27.

[0083] In some embodiments, the physical switch 21 is configured to provide a switch triggering signal to the signal control module 24.

[0084] In some embodiments, the voice recognition module 22 is composed of a microphone, an audio decoder VS1053B, and a voice recognition unit, and is configured to provide a voice trigger signal to the signal control module 24.

[0085] In some embodiments, the event camera 23 is configured to acquire any one of eye movement information and gesture information of the operator, and provide a trigger signal to the signal control module 24.

[0086] Further, the signal control module 24 is configured to acquire the trigger signal provided by at least one of the physical switch 21, the voice recognition module 22, and the event camera 23, and send a control signal to the data acquisition device 25 to control the data acquisition device 25 to perform data acquisition.

[0087] In some embodiments, the data acquisition device 25 further includes a communication module configured to send the acquired data to a cloud server.

[0088] In some embodiments, when the data acquisition device 25 is configured to perform data acquisition, the data acquisition device 25 is configured to send a sound control signal to the loudspeaker 26 and / or a light control signal to the prompt light 27 to control any one of the loudspeaker 26 and the prompt light 27 to prompt information to the operator.

[0089] In the above scheme, the event camera arranged on the A-pillar of the vehicle generates an image only according to the brightness change of the pixels in the field of view, so that clear eye timing images, lip timing images, or gesture images can still be acquired in a high-illumination scene, and thus the eye movement information, lip movement information, or gesture information can be effectively extracted, and the recognition accuracy of data triggering is improved.

[0090] Referring to Figure 5 , Figure 5 is a structural schematic diagram of an embodiment of the vehicle provided in the present application.

[0091] In the present embodiment, the vehicle 30 includes a vehicle-mounted data acquisition system 31. The vehicle-mounted data acquisition system 31 can be the vehicle-mounted data acquisition system 10 and / or the vehicle-mounted data acquisition system 20 described above.

[0092] In some possible embodiments, the vehicle 30 can be a smart driving vehicle.

[0093] In the above scheme, the event camera arranged on the A-pillar of the vehicle generates an image only according to the brightness change of the pixels in the field of view, so that clear eye timing images, lip timing images, or gesture images can still be acquired in a high-illumination scene, and thus the eye movement information, lip movement information, or gesture information can be effectively extracted, and the recognition accuracy of data triggering is improved.

[0094] The above merely describes the embodiments of the present application, and does not limit the patent scope of the present application. Equivalent structures or equivalent process transformations made by the content of the present application specification and drawings, or direct or indirect application in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. An in-vehicle data acquisition system, characterized by comprising: The vehicle-mounted data acquisition system comprises: a signal triggering device; the signal triggering device comprises a voice recognition module and an event camera; the event camera is arranged on an A-pillar of the vehicle; a vehicle-mounted data acquisition device; a processing unit coupled with the voice recognition module, the event camera and the vehicle-mounted data acquisition device respectively, the processing unit is configured to receive a trigger signal sent by the voice recognition module and / or the event camera, and control the vehicle-mounted data acquisition device to acquire vehicle-mounted data.

2. The vehicle-mounted data acquisition system according to claim 1, wherein the signal triggering device comprises a physical button, the physical button is coupled with the processing unit and arranged on a steering wheel of the vehicle.

3. The vehicle-mounted data acquisition system according to claim 2, wherein the steering wheel comprises an airbag cover, a rim and spokes, the airbag cover is connected with the rim through the spokes; the signal triggering device further comprises a plurality of capacitive sensors, the plurality of capacitive sensors are coupled with the processing unit; wherein the physical button is arranged on the spokes, and the plurality of capacitive sensors are arranged on the rim.

4. The vehicle-mounted data acquisition system according to claim 1, wherein the signal triggering device further comprises at least one millimeter wave sensor, the at least one millimeter wave sensor is coupled with the processing unit and arranged on an instrument panel of the vehicle.

5. The vehicle-mounted data acquisition system according to claim 1, wherein the signal triggering device further comprises at least one ultrasonic sensor array, the at least one ultrasonic sensor array is coupled with the processing unit and arranged on the instrument panel of the vehicle.

6. The vehicle-mounted data acquisition system according to claim 1, wherein the vehicle-mounted data acquisition system further comprises a communication unit, the communication unit is coupled with the processing unit, and the communication unit is configured to send vehicle-mounted data acquired by the vehicle-mounted data acquisition device to a cloud server.

7. The vehicle-mounted data acquisition system according to claim 1, wherein the vehicle-mounted data acquisition system further comprises a prompt light, the prompt light is coupled with the processing unit.

8. The vehicle-mounted data acquisition system according to claim 1, wherein the vehicle-mounted data acquisition system further comprises a loudspeaker, the loudspeaker is coupled with the processing unit.

9. The vehicle-mounted data acquisition system according to claim 1, wherein the vehicle-mounted data acquisition device comprises at least one of a camera, a laser radar, an ultrasonic radar, a millimeter wave radar, a gyroscope and a wheel speed sensor.

10. A vehicle characterized by comprising: The vehicle comprises the vehicle-mounted data acquisition system according to any one of claims 1-9.

Images