WO2022041671A1 - 方向盘脱手检测方法及装置、电子设备和存储介质 - Google Patents

方向盘脱手检测方法及装置、电子设备和存储介质 Download PDF

Info

Publication number
WO2022041671A1
WO2022041671A1 PCT/CN2021/078701 CN2021078701W WO2022041671A1 WO 2022041671 A1 WO2022041671 A1 WO 2022041671A1 CN 2021078701 W CN2021078701 W CN 2021078701W WO 2022041671 A1 WO2022041671 A1 WO 2022041671A1
Authority
WO
WIPO (PCT)
Prior art keywords
steering wheel
driver
hand
detection result
hands
Prior art date
Application number
PCT/CN2021/078701
Other languages
English (en)
French (fr)
Inventor
祁凯悦
伍俊
范亦卿
陶莹
许亮
Original Assignee
上海商汤临港智能科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 上海商汤临港智能科技有限公司 filed Critical 上海商汤临港智能科技有限公司
Publication of WO2022041671A1 publication Critical patent/WO2022041671A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items

Definitions

  • the present disclosure relates to the technical field of computer vision, and in particular, to a method and device for detecting a hands-off of a steering wheel, an electronic device and a storage medium.
  • the present disclosure provides a technical solution for detection of steering wheel hands-off detection.
  • a steering wheel release detection method including:
  • a reminder message is generated.
  • the steering wheel hands-off detection is performed on the driver, and the steering wheel hands-off detection result is obtained, including:
  • the steering wheel disengagement category is determined as the steering wheel disengagement detection result.
  • the steering wheel hands-off detection is performed on the driver, and the steering wheel hands-off detection result is obtained, including:
  • the detection result of the steering wheel release is determined.
  • the steering wheel disengagement category is that the hands are not disengaged from the steering wheel, one hand disengages the steering wheel, or both hands disengage the steering wheel.
  • generating reminder information based on the steering wheel release detection result including:
  • the reminder information is generated.
  • generating reminder information based on the steering wheel release detection result including:
  • the driving state is determined based on the detection result of the steering wheel being released;
  • Alerting information is generated in response to the driving state being a dangerous state.
  • the determining of the driving state based on the steering wheel release detection result includes:
  • the determining of the driving state based on the steering wheel hands-off detection result includes:
  • a driving state is determined based on the steering wheel release detection result and the driver's attention detection result.
  • the determining of the driving state based on the length of time that the driver's hand is off the steering wheel includes:
  • the determination of the driving state based on the detection result of the steering wheel off-hand and the detection result of the driver's attention includes:
  • generating reminder information based on the steering wheel release detection result including:
  • the generating reminder information includes:
  • the reminder information is generated according to at least one of the number of hands off the steering wheel, the duration of the hands off the steering wheel, and the driver's hand action category.
  • generating the reminder information according to at least one of the number of hands that are off the steering wheel, the length of time that the hands are off the steering wheel, and the hand action category of the driver including:
  • the hand motion category of the driver is a preset motion category
  • control information for controlling the display screen to display the reminder animation, and/or generating control information for controlling the speaker to play the voice.
  • the steering wheel disengagement detection result includes a steering wheel disengagement category
  • the generating reminder information based on the steering wheel hands-off detection result includes:
  • Reminder information of a corresponding warning level is generated according to the steering wheel release category, wherein the steering wheel release category includes: the hand is not released from the steering wheel, one hand is released from the steering wheel, or both hands are released from the steering wheel.
  • generating reminder information based on the steering wheel release detection result including:
  • the step based on the video stream of the driving area, performing steering wheel release detection on the driver, and obtaining a steering wheel release detection result comprising: in response to the driving speed of the vehicle belonging to the driving area being greater than a first preset speed threshold, based on the driving The video stream of the area is used to detect the driver's hands-off of the steering wheel, and the detection result of the steering-wheel off-hand is obtained;
  • the generating the reminder information based on the detection result of the steering wheel disengagement includes: in response to the detection result of the steering wheel disengagement being that one hand is disengaged from the steering wheel, the driver's hand movement is a dangerous action, and the driving speed reaches the second speed. Preset speed threshold and generate reminder information;
  • the generating reminder information based on the detection result of the steering wheel disengagement includes: in response to the detection result of the steering wheel disengagement being that both hands are released from the steering wheel, and the driving speed reaches a third preset speed threshold, generating the reminder information, wherein the The third preset speed threshold is not greater than the second preset speed threshold.
  • the method further includes:
  • reminder information is generated.
  • the steering wheel hands-off detection is performed on the driver, and the steering wheel hands-off detection result is obtained, including:
  • At least one frame of image in the video stream of the driving area is input into the neural network, and the driver's steering wheel is detected via the neural network, and the steering wheel release category corresponding to the video stream of the driving area and the driver's hands-off detection are obtained.
  • the hand motion category is determined, and the steering wheel off-hand detection result is determined according to the steering wheel off-hand category and the driver's hand motion category.
  • a steering wheel hands-off detection device including:
  • the acquisition module is used to acquire the video stream of the driving area
  • a first detection module configured to detect the driver's hands-off of the steering wheel based on the video stream of the driving area, and obtain the detection result of the hands-off of the steering wheel;
  • the first generating module is configured to generate reminder information based on the detection result of the steering wheel being released.
  • an electronic device comprising: one or more processors; a memory for storing executable instructions; wherein the one or more processors are configured to invoke the memory storage executable instructions to perform the above method.
  • a computer-readable storage medium having computer program instructions stored thereon, the computer program instructions implementing the above method when executed by a processor.
  • a computer program comprising computer-readable code, which when the computer-readable code is executed in an electronic device, is executed by a processor in the electronic device for implementing the above method.
  • the video stream of the driving area is acquired, and based on the video stream of the driving area, the driver performs the steering wheel release detection to obtain the detection result of the steering wheel release, and based on the detection result of the steering wheel release, the reminder information is generated
  • the solution can help reduce the safety hazards during driving.
  • the computer vision method is used to detect the hands-off of the steering wheel in the video stream of the driving area, and reliable detection results can be obtained without adding additional hardware, which can reduce the cost of the hands-off detection of the steering wheel.
  • FIG. 1 shows a flowchart of a method for detecting hands-off of a steering wheel provided by an embodiment of the present disclosure.
  • FIG. 2 shows a block diagram of a steering wheel release detection device provided by an embodiment of the present disclosure.
  • FIG. 3 shows a block diagram of an electronic device 800 provided by an embodiment of the present disclosure.
  • FIG. 4 shows a block diagram of an electronic device 1900 provided by an embodiment of the present disclosure.
  • the driver by acquiring the video stream of the driving area, and based on the video stream of the driving area, the driver performs the steering wheel release detection to obtain the detection result of the steering wheel release, and based on the detection result of the steering wheel release, the reminder information is generated , thereby helping to improve driving safety.
  • the video stream of the driving area to detect the hands-off of the steering wheel, there is no need to add additional hardware, thereby reducing the cost of the hands-off detection of the steering wheel.
  • FIG. 1 shows a flowchart of a method for detecting hands-off of a steering wheel provided by an embodiment of the present disclosure.
  • the execution subject of the steering wheel release detection method may be a steering wheel release detection device.
  • the method for detecting hands-off of the steering wheel may be executed by a terminal device or a server or other processing device.
  • the terminal device may be a vehicle-mounted device, a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a Personal Digital Assistant (PDA), a handheld device, a computing device, or a wearable devices, etc.
  • UE user equipment
  • PDA Personal Digital Assistant
  • the in-vehicle device may be a vehicle, a domain controller or a processor in the cabin, or may be a DMS (Driver Monitor System, driver monitoring system) or an OMS (Occupant Monitoring System, occupant monitoring system) used to execute images Device host, etc. for data processing operations.
  • the steering wheel release detection method may be implemented by the processor calling computer-readable instructions stored in the memory. As shown in FIG. 1 , the steering wheel release detection method includes steps S11 to S13.
  • step S11 a video stream of the driving area is acquired.
  • the vehicle may be a vehicle, or may be a vehicle for carrying people or goods, such as a ship or an airplane.
  • the vehicle can be a private car or a commercial vehicle.
  • the commercial vehicle can be a shared car, an online car-hailing car, a taxi, a bus, a school bus, a long-distance truck, a short-distance truck, a long-distance bus, a short-distance bus, a train, a subway, a railroad car Tram etc.
  • a video stream of the driving area may be collected by a camera disposed in the cabin of the vehicle.
  • the cameras provided in the cabin may include DMS cameras, OMS cameras, and the like.
  • DMS can also perform other driver detection functions, such as fatigue detection, attention detection, etc.
  • the OMS may also perform other occupant detection functions, such as detection of occupant attributes (eg, at least one of age, gender, emotional state, physical state, etc.), occupant speech motion detection, and the like.
  • the video stream of the driving area may be acquired in real time through a camera disposed in the cabin. That is, the acquired video stream of the driving area may be a real-time video stream of the driving area.
  • the driving area may include the area of the main driver's seat.
  • step S12 based on the video stream of the driving area, a steering wheel release detection is performed on the driver, and a steering wheel release detection result is obtained.
  • the driver may be detected for hands-off of the steering wheel to obtain a detection result of the hands-off of the steering wheel.
  • the disengagement of the steering wheel may refer to the disengagement of the hand from the steering wheel
  • the detection of the disengagement of the steering wheel may include detecting whether the driver's hand is disengaged from the steering wheel.
  • performing a steering wheel release detection on the driver based on the video stream of the driving area, and obtaining a steering wheel release detection result may include: detecting the driver's hands-off detection based on the video stream of the driving area. The position of the hand; according to the position of the steering wheel and the position of the driver's hand, it is determined whether the driver's hand is off the steering wheel.
  • the position information of the steering wheel may be pre-stored, and the pre-stored position information of the steering wheel may be acquired to determine whether the driver's hand is off the steering wheel.
  • the position information of the steering wheel may be detected based on the video stream of the driving area.
  • the position of the steering wheel may include a three-dimensional coordinate range of the steering wheel, or a two-dimensional coordinate range in an image captured by a camera at a fixed position (such as a DMS camera), the driver's hand
  • the position of the driver's hand may include the three-dimensional or two-dimensional coordinate range of the driver's hand; the determining whether the driver's hand is off the steering wheel according to the position of the steering wheel and the position of the driver's hand may be The method includes: determining whether the driver's hand is off the steering wheel according to the coordinate range of the steering wheel and the coordinate range of the driver's hand.
  • the coordinate range of the steering wheel may include an image coordinate range in an image coordinate system corresponding to the image of the steering wheel in the video stream of the driving area
  • the coordinate range of the driver's hand may include The image coordinate range of the driver's hand in the image coordinate system.
  • the coordinate range of the steering wheel may include a spatial coordinate range of the steering wheel in a spatial coordinate system in a cabin of a vehicle to which the driving area belongs, and the coordinate range of the driver's hand may Including the spatial coordinate range of the driver's hand in the spatial coordinate system.
  • the determining whether the driver's hand is off the steering wheel according to the coordinate range of the steering wheel and the coordinate range of the driver's hand may include: according to the coordinate range of the steering wheel, all the The coordinate range of the driver's left hand and the coordinate range of the driver's right hand are used to determine whether the driver's hand is off the steering wheel. For example, it can be determined whether the driver's left hand is off the steering wheel according to the size of the overlapping area between the coordinate range of the steering wheel and the coordinate range of the driver's left hand; it can be determined according to the coordinate range of the steering wheel and the driver's left hand. The size of the overlapping area of the coordinate range of the right hand determines whether the driver's right hand is off the steering wheel.
  • the overlapping area of the coordinate range of the steering wheel and the coordinate range of the driver's left hand reaches a first preset area threshold, it can be determined that the driver's left hand has not left the steering wheel; If the overlapping area of the coordinate range of the driver's left hand and the coordinate range of the driver's left hand does not reach the first preset area threshold, it is determined that the driver's left hand is off the steering wheel.
  • the second preset area threshold may be equal to the first preset area threshold, or may not be equal to the first preset area threshold.
  • the steering wheel off-hand detection result may include one-hand off the steering wheel and/or left hand off the steering wheel;
  • the steering wheel off-hand detection result may include one-hand off the steering wheel and/or the right hand off the steering wheel; when it is detected that the driver's left hand and right hand are both off.
  • the steering wheel disengagement detection result may include that both hands are disengaged from the steering wheel; when it is detected that neither the left hand nor the right hand of the driver is disengaged from the steering wheel, the steering wheel disengagement detection result may include that the hands are not disengaged from the steering wheel.
  • step S13 reminder information is generated based on the detection result of the steering wheel being released.
  • reminder information for reminding the driver to put his hand back on the steering wheel may be generated.
  • the reminder information may be generated according to at least one of the steering wheel release category corresponding to the steering wheel release detection result, the driver's hand action category and the driving state.
  • reminder information may be generated according to the steering wheel release category corresponding to the steering wheel release detection result. For example, if the steering wheel disengagement category corresponding to the steering wheel disengagement detection result is one-hand disengagement from the steering wheel or two-hand disengagement from the steering wheel, the reminder information may include "please put both hands on the steering wheel".
  • reminder information may be generated according to the driver's hand motion category corresponding to the steering wheel release detection result. For example, if the type of the driver's hand action corresponding to the steering wheel release detection result is making a phone call, the reminder information may include "do not make a phone call”. For another example, if the type of the driver's hand action corresponding to the steering wheel release detection result is smoking, the reminder information may include "do not smoke" information.
  • reminder information may be generated according to the driving state of the driver. For example, when the automatic driving function is turned on, if the driving state is a non-dangerous state, the reminder information of "automatic driving" may be displayed through the vehicle machine and/or the center console. For another example, when the automatic driving function is turned on, if the driving state is a dangerous state, the reminder information may include information such as "please pay attention" and "please put your hands on the steering wheel".
  • the driver by acquiring the video stream of the driving area, based on the video stream of the driving area, the driver is detected by using computer vision to release the steering wheel to obtain the detection result of the steering wheel release, and based on the steering wheel release detection result As a result, reminder information is generated, thereby contributing to the improvement of driving safety.
  • the video stream of the driving area to detect the hands-off of the steering wheel, more reliable detection results can be obtained without adding additional hardware, such as steering column torque sensor, steering wheel pressure sensor, steering wheel tactile sensor and other hardware. The cost of steering wheel hands-off detection.
  • performing a steering wheel hands-off detection on the driver based on the video stream of the driving area, and obtaining a steering wheel hands-off detection result includes: detecting the driver based on the video stream of the driving area Whether the hand of the driver is off the steering wheel, obtain the steering wheel off-hand category corresponding to the video stream of the driving area; determine the steering wheel off-hand category as the steering wheel off-hand detection result.
  • the situation of disengagement of the steering wheel may be classified in advance.
  • the category of disengagement of the steering wheel is set to include: the steering wheel is not released, the steering wheel is disengaged with one hand, and the steering wheel is disengaged with both hands; optionally, the category of disengagement with one hand can be further subdivided into : Disengage the left hand from the steering wheel after one hand and disengage the right hand from the steering wheel with one hand.
  • the driver's steering wheel off-hand category is then detected by means of image classification/video classification.
  • the steering wheel off-hand category corresponding to the video stream of the driving area is one-hand off the steering wheel, and It may be determined that the steering wheel disengagement detection result includes one-hand disengagement from the steering wheel.
  • the steering wheel off-hand category corresponding to the video stream of the driving area is one-hand off the steering wheel
  • the steering wheel disengagement detection result includes one-hand disengagement from the steering wheel.
  • the steering wheel disengagement detection result includes the disengagement of both hands from the steering wheel.
  • the steering wheel off-hand category corresponding to the video stream of the driving area is that the hand is not off the steering wheel
  • the steering wheel disengagement detection result includes that the hand is not disengaged from the steering wheel
  • the steering wheel release detection result can be accurately obtained based on the steering wheel release type.
  • the steering wheel release category is that the hands are not released from the steering wheel, one hand is released from the steering wheel, or both hands are released from the steering wheel.
  • the one-hand disengagement may be the left hand disengaging the steering wheel and the right hand not disengaging the steering wheel, or it may be the right hand disengaging the steering wheel and the left hand not disengaging the steering wheel.
  • the categories of the steering wheel off hands are further refined, so that different categories of the steering wheel off hands can be detected, and then the steering wheel can be more accurately performed. Hands-off reminder.
  • the method may further include: detecting the hand motion of the driver based on the video stream of the driving area , to obtain the driver's hand motion category corresponding to the video stream of the driving area.
  • the driver's hands may be further detected based on the video stream of the driving area in response to the steering wheel release category being hands off the steering wheel (eg, one hand off the steering wheel and/or two hands off the steering wheel).
  • the steering wheel hands-off category corresponding to the video stream of the driving area is obtained, the hand motion of the driver may not be detected.
  • performing a steering wheel hands-off detection on the driver based on the video stream of the driving area, and obtaining a steering wheel hands-off detection result includes: detecting the driver based on the video stream of the driving area Whether the hand of the driver is off the steering wheel and/or the driver's hand motion, obtain the steering wheel off-hand category and/or the driver's hand motion category corresponding to the video stream of the driving area; according to the steering wheel off-hand category and/or the hand action category of the driver to determine the detection result of the steering wheel being released.
  • the steering wheel release category is that the hands are not released from the steering wheel, one hand is released from the steering wheel, or both hands are released from the steering wheel.
  • the detection of whether the driver's hand is off the steering wheel and the detection of the driver's hand movement may be performed simultaneously.
  • based on the video stream of the driving area firstly detect whether the driver's hand is off the steering wheel, obtain the steering wheel off-hand category corresponding to the video stream of the driving area, and then based on the In the video stream of the driving area, the hand motion of the driver is detected, and the hand motion category of the driver corresponding to the video stream of the driving area is obtained.
  • the driver based on the video stream of the driving area, it is possible to first detect whether the driver's hand is off the steering wheel to obtain the steering wheel off-hand category corresponding to the video stream of the driving area.
  • the steering wheel release category is that the hand is not released from the steering wheel, the hand movement of the driver can no longer be detected; when the steering wheel release category is that the hand is released from the steering wheel, the driver can be detected.
  • the hand motion category of the driver corresponding to the video stream of the driving area is obtained.
  • the driver's hand motion may be detected first, and the driver's hand motion category corresponding to the video stream of the driving area may be obtained, Then, it is detected whether the driver's hand is off the steering wheel, and the steering wheel off-hand category corresponding to the video stream of the driving area is obtained.
  • the driver's hand motion may be detected first to obtain the driver's hand motion category corresponding to the video stream of the driving area.
  • the steering wheel release detection result may be determined according to the driver's hand motion category; if the driver's hand motion category does not belong to the preset dangerous motion category
  • the set dangerous action category based on the video stream of the driving area, it is possible to detect whether the driver's hand is off the steering wheel, obtain the steering wheel off-hand category corresponding to the video stream of the driving area, and according to the steering wheel
  • the hands-off category determines the detection result of the steering wheel's hands-off.
  • the preset dangerous action categories may include action categories that may cause driver distraction and affect driving safety.
  • the preset dangerous action category may include at least one of making a phone call with one hand, drinking water with one hand, smoking with one hand, operating a mobile phone with both hands, and the like. For example, if the type of the driver's hand movement is making a phone call with one hand, it may be determined that the detection result of the steering wheel being released is "calling with one hand off the steering wheel"; if the type of the driver's hand movement is operating a mobile phone with both hands , then it can be determined that the detection result of the steering wheel disengagement is "operating the mobile phone with both hands away from the steering wheel".
  • the driver's hand motion category does not belong to the preset dangerous motion category, it is possible to detect whether the driver's hand is off the steering wheel based on the video stream of the driving area, and obtain the video stream of the driving area The corresponding steering wheel release category. If the steering wheel disengagement category is that the hand is not disengaged from the steering wheel, the steering wheel disengagement detection result may include that the hand is not disengaged from the steering wheel; if the steering wheel disengagement category is one-hand disengagement from the steering wheel, the steering wheel disengagement detection result may include a single hand. Hands disengaged from the steering wheel; if the steering wheel disengagement category is two hands disengaged from the steering wheel, the steering wheel disengagement detection result may include two hands disengaged from the steering wheel.
  • This implementation can obtain more accurate detection results of hand motion categories, further determine whether the hand motion categories are safe, and can provide more targeted reminders based on the more accurate detection results of hand motion categories, such as for the driver's single
  • the action of holding the steering wheel in one hand and the phone in the other hand generates a reminder message "Please do not call while driving", assisting the driver to drive safely and reducing potential safety hazards while driving.
  • the generating reminder information based on the detection result of the steering wheel disengagement includes: in response to the detection result of the steering wheel disengagement being that the driver's hand is disengaged from the steering wheel, and the driver's Hand movements are dangerous movements and generate reminders.
  • the dangerous action may include at least one of drinking water, making a phone call, operating a cell phone, smoking a cigarette, and the like.
  • the generating reminder information in response to the detection result of the steering wheel being off the steering wheel is that the driver's hand is off the steering wheel, and the driver's hand action is a dangerous action, which may include: responding When the detection result of the steering wheel disengagement is that one hand is disengaged from the steering wheel, and the hand movement of the driver is a dangerous action, a reminder message is generated.
  • the reminder information may be generated in response to the detection result of the steering wheel being released from the steering wheel and the driver's hand action is drinking water, making a phone call, or smoking a cigarette.
  • the generating reminder information in response to the detection result of the steering wheel being off the steering wheel is that the driver's hand is off the steering wheel, and the driver's hand movement is a dangerous action, which may include: In response to the detection result of the steering wheel being released from the steering wheel, the hands are released from the steering wheel, and the driver's hand movement is a dangerous movement, and a reminder message is generated.
  • the reminder information may be generated in response to the detection result of the steering wheel being released from the steering wheel, and the driver's hand movement is that the hands are operating the mobile phone.
  • This implementation can discriminate whether the driver performs a normal manipulation or a dangerous action under the condition of letting go, and reminds the driver not to perform a dangerous action during driving, thereby helping to reduce potential safety hazards during driving.
  • the reminder information may not be generated.
  • the non-hazardous action may be at least one of shifting gears, operating an in-vehicle entertainment system, pulling a handbrake, and the like.
  • the driver takes off the steering wheel with one hand and performs a short-term non-dangerous action, no reminder is performed, so that unnecessary reminders can be reduced.
  • the generating reminder information based on the detection result of the steering wheel disengagement includes: generating the reminder information in response to the detection result of the steering wheel disengagement being that both hands are released from the steering wheel.
  • the generating the reminder information based on the detection result of the steering wheel off-hand includes: in the case that the automatic driving function is enabled, determining the driving state based on the detection result of the steering wheel off-hand; responding to When the driving state is a dangerous state, a reminder message is generated.
  • the automatic driving function may refer to the function of a vehicle (eg, a vehicle) to achieve a safe driving state without driver manipulation.
  • the automatic driving function may also be called the assisted driving function.
  • the autopilot function can be turned on or off based on the driver's actions, or it can be turned on or off automatically.
  • reminder information when the automatic driving function is turned on, if it is determined that the driving state is a dangerous state based on the steering wheel release detection result, reminder information can be generated; when the automatic driving function is turned on Next, if it is determined that the driving state is a non-dangerous state based on the steering wheel release detection result, the reminder information may not be generated.
  • the driving state is a dangerous state in combination with the on state of the automatic driving function, so that when the steering wheel release detection method is applied to a vehicle with the automatic driving function, the automatic driving function can be turned on. Only make necessary reminders to reduce the interference caused by excessive reminders to the driver.
  • the determining the driving state based on the detection result of the steering wheel release includes: determining, based on the detection result of the steering wheel release, determining the length of time that the driver's hand is released from the steering wheel; The length of time that the hands are off the steering wheel to determine the driving state.
  • the length of time the driver's hands are off the steering wheel may be detected based on the video stream of the driving area.
  • the duration of the driver's hand off the steering wheel may be determined based on the time difference between the first frame and the last frame image in which the driver's hand off the steering wheel is detected in the continuous video clips in the video stream where the driver's hand is off the steering wheel.
  • the determining the driving state based on the detection result of the steering wheel release includes: determining the driving state based on the detection result of the steering wheel release and the driver's attention detection result.
  • the attention detection of the driver may be performed based on the video stream of the driving area to obtain the attention detection result of the driver.
  • the attention detection may be used to detect whether the driver's attention is focused on driving, that is, to detect whether the driver is in a distracted state.
  • the driving state is determined based on the length of time that the driver's hand is released from the steering wheel and/or based on the detection result of the driver's steering wheel release and the detection result of the driver's attention, so that the determined driving state can be accurately reflect the current level of danger.
  • the determining the driving state based on the duration of the driver's hand being off the steering wheel includes: determining that the driving state is a dangerous state in response to the duration of the driver's hand being off the steering wheel reaching a first duration threshold .
  • determining the driving state based on the steering wheel release detection result and the driver's attention detection result includes: in response to the steering wheel release detection result that the driver's hand is released from the steering wheel, and the The driver's attention detection result is that the driver is in a distracted state, and the driving state is determined to be a dangerous state.
  • the first duration threshold may be 10 seconds.
  • determining that the driver is in a distracted state is determined in response to a first time duration threshold for which the driver's hand is off the steering wheel and/or the result of the driver's attention detection in the steering wheel off state being that the driver is in a distracted state.
  • the driving state is a dangerous state
  • a reminder information is generated, and the reminder information can be generated in a dangerous scenario where the driver's hand is off the steering wheel for too long or the driver is distracted when the automatic driving function is turned on.
  • the determining the driving state based on the duration of the driver's hand off the steering wheel and/or the driver's attention detection result includes: in response to the driver's hand off the steering wheel The length of time has not reached the first time length threshold, and the driver's attention detection result is concentrated attention, and it is determined that the driving state is a non-dangerous state.
  • the driver can be allowed to disengage his hands from the steering wheel for a short time when the automatic driving function is turned on, but the driver is required to maintain concentration, that is, to maintain observation of the driving environment.
  • the driver's attention detection result is that the driver is focused on driving (ie, the driver is not distracted)
  • the automatic driving function in response to the driving state being a dangerous state, the automatic driving function may be turned off and a reminder message to remind the driver to resume manual driving may be generated.
  • the generating the reminder information based on the detection result of the steering wheel hands-off includes: in the case that the automatic driving function is not enabled, in response to the detection result of the hands-off of the steering wheel, the driver is the driver.
  • the driver's hand is off the steering wheel, and the driver's hand action is a dangerous action, and a reminder message is generated.
  • the safety of the driver's action is determined according to the hand action when the automatic driving function is turned off, thereby further improving the safety of driving.
  • the generating the reminder information includes: generating the reminder information according to at least one of the number of hands off the steering wheel, the length of time the hands are off the steering wheel, and the driver's hand action category .
  • reminder information may be generated according to the number of hands that are off the steering wheel.
  • the voice content in the reminder information corresponding to two hands off the steering wheel may contain more urgent reminder content than the voice content in the reminder information corresponding to one hand off the steering wheel.
  • reminder information may be generated according to the length of time that the hand is off the steering wheel.
  • the warning level of the reminder information may be positively correlated with the length of time the hand is off the steering wheel, and the longer the time when the hand is off the steering wheel, the higher the warning level of the reminder information.
  • reminder information may be generated according to the driver's hand motion category. For example, if the type of the driver's hand action is making a phone call, the reminder information may include the information of "don't make a phone call while driving".
  • generating the reminder information according to at least one of the number of hands that have been disengaged from the steering wheel, the length of time that the hands have been disengaged from the steering wheel, and the hand action category of the driver including: When the hand motion category of the operator is a preset motion category, obtain the reminder animation and/or voice corresponding to the preset motion category; generate control information for controlling the display screen to display the reminder animation, and/or generate a control The speaker plays the reminder information of the voice.
  • the preset action category may include at least one of making a phone call, drinking water, smoking, and the like.
  • a reminder animation corresponding to a phone call may include an animation of making a phone call while driving
  • a reminder animation corresponding to drinking water may include an animation of drinking water while driving
  • a reminder animation corresponding to smoking may include an animation of smoking while driving, etc.
  • the voice corresponding to a phone call may include the voice of "Do not call while driving”
  • the voice corresponding to drinking water may include the voice of "Do not drink water while driving”
  • the voice corresponding to smoking may include the voice of "Driving while driving.” Do not smoke" speech, etc.
  • a reminder animation and/or voice corresponding to the preset motion category is obtained, and a control display screen is generated to display the reminder
  • the control information of the animation, and/or, the control information for controlling the speaker to play the voice is generated, so that a targeted reminder can be visually and/or audibly based on the driver's hand movement, so that the reminder effect can be improved, This improves driving safety.
  • the steering wheel disengagement detection result includes a steering wheel disengagement category; the generating reminder information based on the steering wheel disengagement detection result includes: generating reminder information of a corresponding warning level according to the steering wheel disengagement category,
  • the steering wheel disengagement category includes: the hand is not disengaged from the steering wheel, one hand disengages the steering wheel, or both hands disengage the steering wheel.
  • the warning level of the alert message corresponding to two hands off the steering wheel may be higher than the alert level of the alert message corresponding to one hand off the steering wheel.
  • the frequency of the prompt sound in the reminder information corresponding to two hands off the steering wheel may be higher than the frequency of the prompt sound in the reminder information corresponding to one hand off the steering wheel.
  • the duration of the prompt sound in the reminder information corresponding to two hands off the steering wheel may be longer than the duration of the prompt sound in the reminder information corresponding to one hand off the steering wheel.
  • the number of repetitions of the prompt voice in the reminder information corresponding to two hands off the steering wheel may be greater than the number of repetitions of the prompt voice in the prompt information corresponding to one hand off the steering wheel.
  • the prompt voice in the reminder information corresponding to two hands off the steering wheel can be repeated three times, and the prompt voice in the prompt information corresponding to one hand off the steering wheel can be repeated twice.
  • the flickering frequency of the indicator light in the reminder information corresponding to two hands off the steering wheel may be higher than the flashing frequency of the indicator light in the reminder message corresponding to one hand off the steering wheel.
  • a reminder can be given based on the degree of danger corresponding to the steering wheel disengagement category, so that the reminded person can accurately know the warning level of the steering wheel disengagement category, thereby further improving driving safety.
  • the generating reminder information based on the detection result of the steering wheel being released includes: determining a dangerous state level corresponding to the driving state of the driver according to the detection result of the steering wheel being released; generating the Reminder information corresponding to the dangerous state level.
  • the dangerous state level may include a first dangerous state level and a second dangerous state level, wherein the dangerous degree of the driving state corresponding to the first dangerous state level is higher than the second dangerous state level .
  • the prompt information corresponding to the first dangerous state level may include a first prompt tone
  • the second dangerous state level may include a second prompt tone
  • the frequency of the first prompt tone may be higher than The frequency of the second prompt tone, and/or the duration of the first prompt tone may be greater than the duration of the second prompt tone.
  • the reminder information corresponding to the first dangerous state level may include a first voice
  • the second dangerous state level may include a second voice, wherein the voice content of the first voice may be higher than that of the second voice.
  • the voice content of the voice has a more sense of urgency.
  • the reminder information corresponding to the first dangerous state level may include an instruction to control the indicator light to flash at a first frequency
  • the reminder information corresponding to the second dangerous state level may include controlling the indicator light to flash at a second frequency Flashing instructions, wherein the first frequency may be higher than the second frequency
  • the number of dangerous state levels may be larger, for example, it may include three or four dangerous state levels, etc., which is not limited herein.
  • performing a steering wheel release detection on the driver based on the video stream of the driving area, and obtaining a steering wheel release detection result comprising: in response to the driving speed of the vehicle belonging to the driving area being greater than a first Presetting the speed threshold, based on the video stream of the driving area, performing steering wheel release detection on the driver to obtain a steering wheel release detection result; and/or, generating reminder information based on the steering wheel release detection result, including: responding to The detection result of the steering wheel disengagement is that one hand is disengaged from the steering wheel, the hand movement of the driver is a dangerous action, and the driving speed reaches a second preset speed threshold, and a reminder message is generated; and/or, based on the The steering wheel disengagement detection result, generating reminder information includes: in response to the steering wheel disengagement detection result that both hands are disengaged from the steering wheel, and the driving speed reaches a third preset speed threshold, generating reminder information, wherein the third preset speed The threshold is not greater than the second preset
  • the driver when the driving speed of the vehicle to which the driving area belongs is greater than the first preset speed threshold, based on the video stream of the driving area, the driver can be detected for the driver's hands-off of the steering wheel, and the detection result of the hands-off of the steering wheel can be obtained. , so that the safety of driving can be improved; and when the driving speed of the vehicle to which the driving area belongs is not greater than the first preset speed threshold, the steering wheel hands-off detection can be avoided, thereby reducing unnecessary detection and reminders .
  • the first preset speed threshold may be 0.
  • the first preset speed threshold may also be flexibly set according to actual application scenario requirements, which is not limited herein.
  • the driver in response to the driving speed of the vehicle to which the driving area belongs is greater than 0, based on the video stream of the driving area, the driver can be detected for the driver's hands-off of the steering wheel to obtain the detection result of the steering-wheel off-hand;
  • the steering wheel hands-off detection is not performed, so as to avoid unnecessary detection and occupation of redundant driving energy consumption and processing resources.
  • the reminder message may be generated in response to the detection result of the steering wheel being released from the steering wheel with one hand being released from the steering wheel, the driver's hand movement is a dangerous action, and the driving speed reaches a second preset speed threshold;
  • the second preset speed threshold may be 30 km/h.
  • a reminder message may be generated in response to the detection result of the steering wheel being released from the steering wheel, and the driving speed reaches a third preset speed threshold; and the detection result of the steering wheel being released is that the hands are released from the steering wheel. , and when the traveling speed does not reach the third preset speed threshold, no reminder information is generated.
  • the third preset speed threshold may be 10 km/h.
  • the method further includes: performing fatigue detection on the driver according to the video stream of the driving area to obtain a fatigue detection result; and generating reminder information based on the fatigue detection result.
  • the fatigue detection result may include a fatigue state or a non-fatigue state.
  • reminder information may be generated in response to the fatigue state result being a fatigue state.
  • the steering wheel hands-off detection and Fatigue detection thereby reducing the cost of installing cameras in the cabin of the vehicle.
  • the behavior detection system can realize the functions of driver fatigue detection and steering wheel release detection, and integrate different driver behavior detection functions into the same system to reduce the detection cost.
  • driving safety can be further improved.
  • performing the steering wheel hands-off detection on the driver based on the video stream of the driving area, and obtaining the steering wheel hands-off detection result includes: converting at least one frame of image in the video stream of the driving area Input the neural network, and perform the steering wheel hands-off detection for the driver through the neural network, obtain the steering wheel hands-off category corresponding to the video stream of the driving area, and determine the steering wheel hands-off category as the steering wheel hands-off detection result; At least one frame of image in the video stream of the driving area is input into the neural network, and the driver is detected by the neural network for steering wheel hands-off, and the steering wheel hands-off category corresponding to the video stream of the driving area and the hand action of the driver are obtained.
  • the detection result of the steering wheel disengagement is determined according to the category of the disengagement of the steering wheel and the category of the hand action of the driver.
  • the detection of disengagement of the steering wheel is performed through the neural network, which can improve the accuracy and speed of the detection of the disengagement of the steering wheel.
  • the neural network can be pre-trained and deployed, and can quickly detect images or video streams with a large amount of data, so it can be applied to video stream detection in real-time driving scenarios.
  • the video stream of the driving area can be collected by the DMS camera
  • the processor can obtain the video stream of the driving area from the DMS camera
  • the hand of the driver can be detected Whether to disengage the steering wheel and the driver's hand movement, obtain the steering wheel release category and the driver's hand action category corresponding to the video stream of the driving area, and according to the steering wheel release category and the driver's hand action category
  • the hand action category determines the result of the steering wheel hands-off detection.
  • the steering wheel off-hand detection result is that one hand is off the steering wheel to make a phone call
  • a reminder animation of making a phone call while driving can be displayed on the center console, and a voice of "don't make a phone call while driving" can be played.
  • the present disclosure also provides a steering wheel disengagement detection device, an electronic device, a computer-readable storage medium, and a program, all of which can be used to implement any of the steering wheel disengagement detection methods provided by the present disclosure, and the corresponding technical solutions and technical effects can be found in the method section. The corresponding records will not be repeated.
  • FIG. 2 shows a block diagram of a steering wheel release detection device provided by an embodiment of the present disclosure.
  • the steering wheel release detection device includes: an acquisition module 21 for acquiring a video stream of a driving area; a first detection module 22 for performing a steering wheel release for the driver based on the video stream of the driving area The detection is performed to obtain the detection result of the steering wheel disengagement; the first generating module 23 is configured to generate reminder information based on the detection result of the steering wheel disengagement.
  • the first detection module 22 is configured to: based on the video stream of the driving area, detect whether the driver's hand is off the steering wheel, and obtain the corresponding video stream of the driving area. Steering wheel disengagement category; determine the steering wheel disengagement category as the steering wheel disengagement detection result.
  • the first detection module 22 is configured to: based on the video stream of the driving area, detect whether the driver's hand is off the steering wheel and/or the driver's hand movement , obtain the steering wheel release category and/or the driver's hand motion category corresponding to the video stream of the driving area; according to the steering wheel release category and/or the driver's hand motion category, determine the steering wheel release detection result.
  • the steering wheel disengagement category is that the hands are not disengaged from the steering wheel, one hand disengages the steering wheel, or both hands disengage the steering wheel.
  • the first generation module 23 is configured to: in response to the detection result of the steering wheel disengagement being that the driver's hand has disengaged from the steering wheel, and the driver's hand action is a dangerous action to generate a reminder message.
  • the first generation module 23 is configured to: in the case that the automatic driving function is enabled, determine the driving state based on the detection result of the steering wheel being released; in response to the driving state being Dangerous state, generate a reminder message.
  • the first generation module 23 is configured to: based on the detection result of the steering wheel being released from the steering wheel, determine the duration of the driver's hand being released from the steering wheel; and based on the driver's hand being released from the steering wheel and/or the first generating module is configured to: determine the driving state based on the steering wheel release detection result and the driver's attention detection result.
  • the first generation module 23 is configured to: determine that the driving state is a dangerous state in response to the time when the driver's hand is off the steering wheel reaching a first time duration threshold; and/or in response to The steering wheel disengagement detection result is that the driver's hand is out of the steering wheel, and the driver's attention detection result is that the driver is in a distracted state, and it is determined that the driving state is a dangerous state.
  • the first generation module 23 is configured to: when the automatic driving function is not enabled, in response to the detection result of the steering wheel being released from the steering wheel, the driver's hand is released from the steering wheel, And the hand movement of the driver is a dangerous movement, and the reminder information is generated.
  • the first generating module 23 is configured to: generate a method according to at least one of the number of hands disengaged from the steering wheel, the length of time that the hands have disengaged from the steering wheel, and the hand action categories of the driver. Reminder information.
  • the first generating module 23 is configured to: in the case that the hand motion category of the driver is a preset motion category, obtain the reminder animation and/or the preset motion category or voice; generate control information for controlling the display screen to display the reminder animation, and/or generate control information for controlling the speaker to play the voice.
  • the steering wheel disengagement detection result includes a steering wheel disengagement category; the first generating module 23 is configured to: generate reminder information of a corresponding warning level according to the steering wheel disengagement category, wherein the steering wheel
  • the disengagement categories include: the hand is not off the steering wheel, one hand is off the steering wheel, or both hands are off the steering wheel.
  • the first generating module 23 is configured to: determine a dangerous state level corresponding to the driving state of the driver according to the steering wheel release detection result; generate a reminder corresponding to the dangerous state level information.
  • the first detection module 22 is configured to: in response to the driving speed of the vehicle belonging to the driving area being greater than a first preset speed threshold, based on the video stream of the driving area, detect the driver Performing steering wheel release detection to obtain a steering wheel release detection result; and/or, the first generation module 23 is configured to: in response to the steering wheel release detection result being that one hand is released from the steering wheel, the driver's hand movement is a dangerous action , and the driving speed reaches the second preset speed threshold, and generates reminder information; and/or, the first generating module 23 is configured to: in response to the detection result of the steering wheel being released from the steering wheel, both hands are released from the steering wheel, and the driving speed is Reaching a third preset speed threshold, generating reminder information, wherein the third preset speed threshold is not greater than the second preset speed threshold.
  • the device further includes: a second detection module, configured to perform fatigue detection on the driver according to the video stream of the driving area to obtain a fatigue detection result; a second generation module, for generating reminder information based on the fatigue detection result.
  • the detection module is configured to: input at least one frame of image in the video stream of the driving area into a neural network, and detect the driver's hands-off of the steering wheel via the neural network, and obtain the The steering wheel disengagement category corresponding to the video stream of the driving area, and the steering wheel disengagement category is determined as the detection result of the steering wheel disengagement; Perform steering wheel release detection on the driver, obtain the steering wheel release category and the driver's hand action category corresponding to the video stream of the driving area, and determine according to the steering wheel release category and the driver's hand action category Steering wheel hands-off detection results.
  • the driver by acquiring the video stream of the driving area, and based on the video stream of the driving area, the driver performs the steering wheel release detection to obtain the detection result of the steering wheel release, and based on the detection result of the steering wheel release, the reminder information is generated , thereby helping to improve driving safety.
  • the video stream of the driving area to detect the hands-off of the steering wheel, there is no need to add additional hardware, thereby reducing the cost of the hands-off detection of the steering wheel.
  • the functions or modules included in the apparatus provided in the embodiments of the present disclosure may be used to execute the methods described in the above method embodiments, and the specific implementation and technical effects may refer to the above method embodiments. It is concise and will not be repeated here.
  • Embodiments of the present disclosure further provide a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the foregoing method is implemented.
  • the computer-readable storage medium may be a non-volatile computer-readable storage medium, or may be a volatile computer-readable storage medium.
  • Embodiments of the present disclosure further provide a computer program, including computer-readable codes, when the computer-readable codes are executed in an electronic device, the processor in the electronic device executes the above method.
  • Embodiments of the present disclosure further provide another computer program product for storing computer-readable instructions, which, when executed, cause the computer to perform operations of the steering wheel hands-off detection method provided by any of the foregoing embodiments.
  • Embodiments of the present disclosure further provide an electronic device, including: one or more processors; a memory for storing executable instructions; wherein the one or more processors are configured to invoke executable instructions stored in the memory instruction to execute the above method.
  • the electronic device may be provided as a terminal, server or other form of device.
  • the electronic device may be a vehicle machine, a domain controller, or a processor in the vehicle cabin, and may also be a device host in a DMS or an OMS for performing data processing operations such as images.
  • FIG. 3 shows a block diagram of an electronic device 800 provided by an embodiment of the present disclosure.
  • electronic device 800 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, fitness device, personal digital assistant, etc. terminal.
  • electronic device 800 may include one or more of the following components: processing component 802, memory 804, power supply component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814 , and the communication component 816 .
  • the processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations.
  • the processing component 802 can include one or more processors 820 to execute instructions to perform all or some of the steps of the methods described above.
  • processing component 802 may include one or more modules that facilitate interaction between processing component 802 and other components.
  • processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.
  • Memory 804 is configured to store various types of data to support operation at electronic device 800 . Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, and the like. Memory 804 may be implemented by any type of volatile or nonvolatile storage device or combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic or Optical Disk.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read only memory
  • EPROM erasable Programmable Read Only Memory
  • PROM Programmable Read Only Memory
  • ROM Read Only Memory
  • Magnetic Memory Flash Memory
  • Magnetic or Optical Disk Magnetic Disk
  • Power supply assembly 806 provides power to various components of electronic device 800 .
  • Power supply components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 800 .
  • Multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user.
  • the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user.
  • the touch panel includes one or more touch sensors to sense touch, swipe, and gestures on the touch panel. The touch sensor may not only sense the boundaries of a touch or swipe action, but also detect the duration and pressure associated with the touch or swipe action.
  • the multimedia component 808 includes a front-facing camera and/or a rear-facing camera. When the electronic device 800 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each of the front and rear cameras can be a fixed optical lens system or have focal length and optical zoom capability.
  • Audio component 810 is configured to output and/or input audio signals.
  • audio component 810 includes a microphone (MIC) that is configured to receive external audio signals when electronic device 800 is in operating modes, such as calling mode, recording mode, and voice recognition mode.
  • the received audio signal may be further stored in memory 804 or transmitted via communication component 816 .
  • audio component 810 also includes a speaker for outputting audio signals.
  • the I/O interface 812 provides an interface between the processing component 802 and a peripheral interface module, which may be a keyboard, a click wheel, a button, or the like. These buttons may include, but are not limited to: home button, volume buttons, start button, and lock button.
  • Sensor assembly 814 includes one or more sensors for providing status assessment of various aspects of electronic device 800 .
  • the sensor assembly 814 can detect the on/off state of the electronic device 800, the relative positioning of the components, such as the display and the keypad of the electronic device 800, the sensor assembly 814 can also detect the electronic device 800 or one of the electronic device 800 Changes in the position of components, presence or absence of user contact with the electronic device 800 , orientation or acceleration/deceleration of the electronic device 800 and changes in the temperature of the electronic device 800 .
  • Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact.
  • Sensor assembly 814 may also include a light sensor, such as a complementary metal oxide semiconductor (CMOS) or charge coupled device (CCD) image sensor, for use in imaging applications.
  • CMOS complementary metal oxide semiconductor
  • CCD charge coupled device
  • the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
  • Communication component 816 is configured to facilitate wired or wireless communication between electronic device 800 and other devices.
  • the electronic device 800 can access a wireless network based on communication standards, such as wireless network (Wi-Fi), second generation mobile communication technology (2G), third generation mobile communication technology (3G), fourth generation mobile communication technology (4G) )/Long Term Evolution (LTE) of Universal Mobile Communications Technology, Fifth Generation Mobile Communications Technology (5G), or a combination thereof.
  • the communication component 816 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel.
  • the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication.
  • the NFC module may be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.
  • RFID radio frequency identification
  • IrDA infrared data association
  • UWB ultra-wideband
  • Bluetooth Bluetooth
  • electronic device 800 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable A programmed gate array (FPGA), controller, microcontroller, microprocessor or other electronic component implementation is used to perform the above method.
  • ASICs application specific integrated circuits
  • DSPs digital signal processors
  • DSPDs digital signal processing devices
  • PLDs programmable logic devices
  • FPGA field programmable A programmed gate array
  • controller microcontroller, microprocessor or other electronic component implementation is used to perform the above method.
  • a non-volatile computer-readable storage medium such as a memory 804 comprising computer program instructions executable by the processor 820 of the electronic device 800 to perform the above method is also provided.
  • FIG. 4 shows a block diagram of an electronic device 1900 provided by an embodiment of the present disclosure.
  • the electronic device 1900 may be provided as a server.
  • electronic device 1900 includes processing component 1922, which further includes one or more processors, and a memory resource represented by memory 1932 for storing instructions executable by processing component 1922, such as applications.
  • An application program stored in memory 1932 may include one or more modules, each corresponding to a set of instructions.
  • the processing component 1922 is configured to execute instructions to perform the above-described methods.
  • the electronic device 1900 may also include a power supply assembly 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input output (I/O) interface 1958 .
  • the electronic device 1900 can operate based on an operating system stored in the memory 1932, such as a Microsoft server operating system (Windows Server TM ), a graphical user interface based operating system (Mac OS X TM ) introduced by Apple, a multi-user multi-process computer operating system (Unix TM ), Free and Open Source Unix-like Operating System (Linux TM ), Open Source Unix-like Operating System (FreeBSD TM ) or the like.
  • Microsoft server operating system Windows Server TM
  • Mac OS X TM graphical user interface based operating system
  • Uniix TM multi-user multi-process computer operating system
  • Free and Open Source Unix-like Operating System Linux TM
  • FreeBSD TM Open Source Unix-like Operating System
  • a non-volatile computer-readable storage medium such as memory 1932 comprising computer program instructions executable by processing component 1922 of electronic device 1900 to perform the above-described method.
  • the present disclosure may be a system, method and/or computer program product.
  • the computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of the present disclosure.
  • a computer-readable storage medium may be a tangible device that can hold and store instructions for use by the instruction execution device.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
  • Non-exhaustive list of computer readable storage media include: portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM) or flash memory), static random access memory (SRAM), portable compact disk read only memory (CD-ROM), digital versatile disk (DVD), memory sticks, floppy disks, mechanically coded devices, such as printers with instructions stored thereon Hole cards or raised structures in grooves, and any suitable combination of the above.
  • RAM random access memory
  • ROM read only memory
  • EPROM erasable programmable read only memory
  • flash memory static random access memory
  • SRAM static random access memory
  • CD-ROM compact disk read only memory
  • DVD digital versatile disk
  • memory sticks floppy disks
  • mechanically coded devices such as printers with instructions stored thereon Hole cards or raised structures in grooves, and any suitable combination of the above.
  • Computer-readable storage media are not to be construed as transient signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (eg, light pulses through fiber optic cables), or through electrical wires transmitted electrical signals.
  • the computer readable program instructions described herein may be downloaded to various computing/processing devices from a computer readable storage medium, or to an external computer or external storage device over a network such as the Internet, a local area network, a wide area network, and/or a wireless network.
  • the network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers.
  • a network adapter card or network interface in each computing/processing device receives computer-readable program instructions from a network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing/processing device .
  • Computer program instructions for carrying out operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or instructions in one or more programming languages.
  • Source or object code written in any combination, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as the "C" language or similar programming languages.
  • the computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server implement.
  • the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider through the Internet connect).
  • LAN local area network
  • WAN wide area network
  • custom electronic circuits such as programmable logic circuits, field programmable gate arrays (FPGAs), or programmable logic arrays (PLAs) can be personalized by utilizing state information of computer readable program instructions.
  • Computer readable program instructions are executed to implement various aspects of the present disclosure.
  • These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer or other programmable data processing apparatus to produce a machine that causes the instructions when executed by the processor of the computer or other programmable data processing apparatus , resulting in means for implementing the functions/acts specified in one or more blocks of the flowchart and/or block diagrams.
  • These computer readable program instructions can also be stored in a computer readable storage medium, these instructions cause a computer, programmable data processing apparatus and/or other equipment to operate in a specific manner, so that the computer readable medium on which the instructions are stored includes An article of manufacture comprising instructions for implementing various aspects of the functions/acts specified in one or more blocks of the flowchart and/or block diagrams.
  • Computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other equipment to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other equipment to produce a computer-implemented process , thereby causing instructions executing on a computer, other programmable data processing apparatus, or other device to implement the functions/acts specified in one or more blocks of the flowcharts and/or block diagrams.
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more functions for implementing the specified logical function(s) executable instructions.
  • the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented in dedicated hardware-based systems that perform the specified functions or actions , or can be implemented in a combination of dedicated hardware and computer instructions.
  • the computer program product can be specifically implemented by hardware, software or a combination thereof.
  • the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK), etc. Wait.
  • a software development kit Software Development Kit, SDK

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Multimedia (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种方向盘脱手检测方法及装置、电子设备和存储介质。所述方法包括：获取驾驶区域的视频流（S11）；基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果（S12）；基于所述方向盘脱手检测结果，生成提醒信息（S13）。

Description

方向盘脱手检测方法及装置、电子设备和存储介质
本申请要求在2020年8月31日提交中国专利局、申请号为202010899671.1、申请名称为“方向盘脱手检测方法及装置、电子设备和存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本公开涉及计算机视觉技术领域，尤其涉及一种方向盘脱手检测方法及装置、电子设备和存储介质。
背景技术
在驾驶过程中，手部脱离方向盘是非常危险的驾驶行为，容易引起交通事故。因此，对驾驶员进行方向盘脱手检测，对于安全驾驶具有重要意义。
发明内容
本公开提供了一种方向盘脱手检测技术方案。
根据本公开的一方面，提供了一种方向盘脱手检测方法，包括：
获取驾驶区域的视频流；
基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果；
基于所述方向盘脱手检测结果，生成提醒信息。
在一种可能的实现方式中，所述基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果，包括：
基于所述驾驶区域的视频流，检测所述驾驶员的手部是否脱离方向盘，得到所述驾驶区域的视频流对应的方向盘脱手类别；
将所述方向盘脱手类别，确定为方向盘脱手检测结果。
在一种可能的实现方式中，所述基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果，包括：
基于所述驾驶区域的视频流，检测所述驾驶员的手部是否脱离方向盘和/或所述驾驶员的手部动作，得到所述驾驶区域的视频流对应的方向盘脱手类别和/或所述驾驶员的手部动作类别；
根据所述方向盘脱手类别和/或所述驾驶员的手部动作类别，确定方向盘脱手检测结果。
在一种可能的实现方式中，所述方向盘脱手类别为手部未脱离方向盘、单手脱离方向盘或者双手脱离方向盘。
在一种可能的实现方式中，所述基于所述方向盘脱手检测结果，生成提醒信息，包括：
响应于所述方向盘脱手检测结果为所述驾驶员的手部脱离方向盘，且所述驾驶员的手部动作属于危险动作，生成提醒信息。
在一种可能的实现方式中，所述基于所述方向盘脱手检测结果，生成提醒信息，包括：
在自动驾驶功能为已开启状态的情况下，基于所述方向盘脱手检测结果，确定驾驶状态；
响应于所述驾驶状态为危险状态，生成提醒信息。
在一种可能的实现方式中，所述基于所述方向盘脱手检测结果，确定驾驶状态，包括：
基于所述方向盘脱手检测结果，确定所述驾驶员的手部脱离方向盘的时长；
基于所述驾驶员的手部脱离方向盘的时长，确定驾驶状态；和/或
所述基于所述方向盘脱手检测结果，确定驾驶状态，包括：
基于所述方向盘脱手检测结果和所述驾驶员的注意力检测结果，确定驾驶状态。
在一种可能的实现方式中，所述基于所述驾驶员的手部脱离方向盘的时长，确定驾驶状态，包括：
响应于所述驾驶员的手部脱离方向盘的时长达到第一时长阈值，确定驾驶状态为危险状态；
所述基于所述方向盘脱手检测结果和所述驾驶员的注意力检测结果，确定驾驶状态，包括：
响应于所述方向盘脱手检测结果为所述驾驶员的手部脱离方向盘，且所述驾驶员的注意力检测结果为驾驶员处于分心状态，确定驾驶状态为危险状态。
在一种可能的实现方式中，所述基于所述方向盘脱手检测结果，生成提醒信息，包括：
在自动驾驶功能为未开启状态的情况下，响应于所述方向盘脱手检测结果为所述驾驶员的手部脱离方向盘，且所述驾驶员的手部动作属于危险动作，生成提醒信息。
在一种可能的实现方式中，所述生成提醒信息，包括：
根据脱离方向盘的手的数量、手部脱离方向盘的时长和所述驾驶员的手部动作类别中的至少之一，生成提醒信息。
在一种可能的实现方式中，所述根据脱离方向盘的手的数量、手部脱离方向盘的时长和所述驾驶员的手部动作类别中的至少之一，生成提醒信息，包括：
在所述驾驶员的手部动作类别为预设动作类别的情况下，获取所述预设动作类别对应的提醒动画和/或语音；
生成控制显示屏显示所述提醒动画的控制信息，和/或，生成控制扬声器播放所述语音的控制信息。
在一种可能的实现方式中，所述方向盘脱手检测结果包括方向盘脱手类别；
所述基于所述方向盘脱手检测结果，生成提醒信息包括：
根据所述方向盘脱手类别生成对应的警示级别的提醒信息，其中，所述方向盘脱手类别包括：手部未脱离方向盘、单手脱离方向盘或者双手脱离方向盘。
在一种可能的实现方式中，所述基于所述方向盘脱手检测结果，生成提醒信息，包括：
根据所述方向盘脱手检测结果，确定所述驾驶员的驾驶状态对应的危险状态级别；
生成所述危险状态级别对应的提醒信息。
在一种可能的实现方式中，
所述基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果，包括：响应于所述驾驶区域所属车辆的行驶速度大于第一预设速度阈值，基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果；
和/或，
所述基于所述方向盘脱手检测结果，生成提醒信息，包括：响应于所述方向盘脱手检测结果为单手脱离方向盘，所述驾驶员的手部动作属于危险动作，且所述行驶速度达到第二预设速度阈值，生成 提醒信息；
和/或，
所述基于所述方向盘脱手检测结果，生成提醒信息，包括：响应于所述方向盘脱手检测结果为双手脱离方向盘，且所述行驶速度达到第三预设速度阈值，生成提醒信息，其中，所述第三预设速度阈值不大于所述第二预设速度阈值。
在一种可能的实现方式中，所述方法还包括：
根据所述驾驶区域的视频流，对所述驾驶员进行疲劳检测，得到疲劳检测结果；
基于所述疲劳检测结果，生成提醒信息。
在一种可能的实现方式中，所述基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果，包括：
将所述驾驶区域的视频流中的至少一帧图像输入神经网络，经由所述神经网络对驾驶员进行方向盘脱手检测，得到所述驾驶区域的视频流对应的方向盘脱手类别，并将所述方向盘脱手类别确定为方向盘脱手检测结果；
或者，
将所述驾驶区域的视频流中的至少一帧图像输入神经网络，经由所述神经网络对驾驶员进行方向盘脱手检测，得到所述驾驶区域的视频流对应的方向盘脱手类别和所述驾驶员的手部动作类别，并根据所述方向盘脱手类别和所述驾驶员的手部动作类别确定方向盘脱手检测结果。
根据本公开的一方面，提供了一种方向盘脱手检测装置，包括：
获取模块，用于获取驾驶区域的视频流；
第一检测模块，用于基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果；
第一生成模块，用于基于所述方向盘脱手检测结果，生成提醒信息。
根据本公开的一方面，提供了一种电子设备，包括：一个或多个处理器；用于存储可执行指令的存储器；其中，所述一个或多个处理器被配置为调用所述存储器存储的可执行指令，以执行上述方法。
根据本公开的一方面，提供了一种计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现上述方法。
根据本公开的一方面，提供了一种计算机程序，包括计算机可读代码，当所述计算机可读代码在电子设备中运行时，所述电子设备中的处理器执行用于实现上述方法。
在本公开实施例中，采用获取驾驶区域的视频流，基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果，并基于所述方向盘脱手检测结果，生成提醒信息的方案，有助于减少行驶过程中的安全隐患。另外，利用计算机视觉的方法对驾驶区域的视频流进行方向盘脱手检测，无需增设额外的硬件即可获得可靠的检测结果，能够降低方向盘脱手检测的成本。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，而非限制本公开。
根据下面参考附图对示例性实施例的详细说明，本公开的其它特征及方面将变得清楚。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，这些附图示出了符合本公开的实施例，并 与说明书一起用于说明本公开的技术方案。
图1示出本公开实施例提供的方向盘脱手检测方法的流程图。
图2示出本公开实施例提供的方向盘脱手检测装置的框图。
图3示出本公开实施例提供的一种电子设备800的框图。
图4示出本公开实施例提供的一种电子设备1900的框图。
具体实施方式
以下将参考附图详细说明本公开的各种示例性实施例、特征和方面。附图中相同的附图标记表示功能相同或相似的元件。尽管在附图中示出了实施例的各种方面，但是除非特别指出，不必按比例绘制附图。
在这里专用的词“示例性”意为“用作例子、实施例或说明性”。这里作为“示例性”所说明的任何实施例不必解释为优于或好于其它实施例。
本文中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中术语“至少一种”表示多种中的任意一种或多种中的至少两种的任意组合，例如，包括A、B、C中的至少一种，可以表示包括从A、B和C构成的集合中选择的任意一个或多个元素。
另外，为了更好地说明本公开，在下文的具体实施方式中给出了众多的具体细节。本领域技术人员应当理解，没有某些具体细节，本公开同样可以实施。在一些实例中，对于本领域技术人员熟知的方法、手段、元件和电路未作详细描述，以便于凸显本公开的主旨。
在本公开实施例中，通过获取驾驶区域的视频流，基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果，并基于所述方向盘脱手检测结果，生成提醒信息，由此有助于提高行驶的安全性。另外，通过利用驾驶区域的视频流进行方向盘脱手检测，无需增设额外的硬件，从而能够降低方向盘脱手检测的成本。
图1示出本公开实施例提供的方向盘脱手检测方法的流程图。所述方向盘脱手检测方法的执行主体可以是方向盘脱手检测装置。在一种可能的实现方式中，所述方向盘脱手检测方法可以由终端设备或服务器或其它处理设备执行。其中，终端设备可以是车载设备、用户设备(User Equipment，UE)、移动设备、用户终端、终端、蜂窝电话、无绳电话、个人数字助理(Personal Digital Assistant，PDA)、手持设备、计算设备或者可穿戴设备等。其中，车载设备可以是车舱内的车机、域控制器或者处理器，还可以是DMS(Driver Monitor System，驾驶员监控系统)或者OMS(Occupant Monitoring System，乘员监控系统)中用于执行图像等数据处理操作的设备主机等。在一些可能的实现方式中，所述方向盘脱手检测方法可以通过处理器调用存储器中存储的计算机可读指令的方式来实现。如图1所示，所述方向盘脱手检测方法包括步骤S11至步骤S13。
在步骤S11中，获取驾驶区域的视频流。
本公开实施例提供的方向盘脱手检测方法可以应用于各种类型的交通工具中。例如，所述交通工具可以是车辆，也可以是船舶或者飞机等用于载人或者载货的交通工具。其中，车辆可以是私家车或者营运车辆，例如，营运车辆可以是共享汽车、网约车、出租车、公交车、校车、长途货车、短途货车、长途客车、短途客车、火车、地铁、有轨电车等。
在一种可能的实现方式中，可以通过设置在交通工具的舱内的摄像头，采集所述驾驶区域的视频流。例如，设置在所述舱内的摄像头可以包括DMS摄像头、OMS摄像头等。其中，DMS还可以执行其他的驾驶员检测功能，例如疲劳检测、注意力检测等。OMS还可以执行其他的乘员检测功能，例如乘员属性(如年龄、性别、情绪状态、身体状态等中的至少一项)的检测，乘员的说话动作检测，等等。
在一种可能的实现方式中，可以实时通过设置在所述舱内的摄像头获取所述驾驶区域的视频流。即，所获取的所述驾驶区域的视频流可以是所述驾驶区域的实时视频流。其中，所述驾驶区域可以包括主驾驶座的区域。
在步骤S12中，基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果。
在本公开实施例中，可以基于所述驾驶区域的视频流中的单帧或多帧图像，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果。其中，方向盘脱手可以指手部脱离方向盘，方向盘脱手检测可以包括检测所述驾驶员的手部是否脱离方向盘。
在一种可能的实现方式中，所述基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果，可以包括：基于所述驾驶区域的视频流，检测驾驶员的手部的位置；根据方向盘的位置和所述驾驶员的手部的位置，确定所述驾驶员的手部是否脱离方向盘。
作为该实现方式的一个示例，可以预先存储所述方向盘的位置信息，并获取预先存储的所述方向盘的位置信息，以确定所述驾驶员的手部是否脱离方向盘。作为该实现方式的另一个示例，可以基于所述驾驶区域的视频流，检测所述方向盘的位置信息。
作为该实现方式的一个示例，所述方向盘的位置可以包括所述方向盘的三维坐标范围，或者在固定位置的摄像头(例如DMS摄像头)采集的图像中的二维坐标范围，所述驾驶员的手部的位置可以包括所述驾驶员的手部的三维或二维坐标范围；所述根据方向盘的位置和所述驾驶员的手部的位置，确定所述驾驶员的手部是否脱离方向盘，可以包括：根据所述方向盘的坐标范围和所述驾驶员的手部的坐标范围，确定所述驾驶员的手部是否脱离方向盘。
在一个例子中，所述方向盘的坐标范围可以包括所述方向盘在所述驾驶区域的视频流中的图像对应的图像坐标系中的图像坐标范围，所述驾驶员的手部的坐标范围可以包括所述驾驶员的手部在所述图像坐标系中的图像坐标范围。
在另一个例子中，所述方向盘的坐标范围可以包括所述方向盘在所述驾驶区域所属的交通工具的舱内的空间坐标系中的空间坐标范围，所述驾驶员的手部的坐标范围可以包括所述驾驶员的手部在所述空间坐标系中的空间坐标范围。
在一个例子中，所述根据所述方向盘的坐标范围和所述驾驶员的手部的坐标范围，确定所述驾驶员的手部是否脱离方向盘，可以包括：根据所述方向盘的坐标范围、所述驾驶员的左手的坐标范围和所述驾驶员的右手的坐标范围，确定所述驾驶员的手部是否脱离方向盘。例如，可以根据所述方向盘的坐标范围与所述驾驶员的左手的坐标范围的重合区域的大小，确定所述驾驶员的左手是否脱离方向盘；可以根据所述方向盘的坐标范围与所述驾驶员的右手的坐标范围的重合区域的大小，确定所述驾驶员的右手是否脱离方向盘。例如，可以在所述方向盘的坐标范围与所述驾驶员的左手的坐标范围的重合区域达到第一预设面积阈值的情况下，确定所述驾驶员的左手未脱离方向盘；可以在所述方向盘 的坐标范围与所述驾驶员的左手的坐标范围的重合区域未达到第一预设面积阈值的情况下，确定所述驾驶员的左手脱离方向盘。又如，可以在所述方向盘的坐标范围与所述驾驶员的右手的坐标范围的重合区域达到第二预设面积阈值的情况下，确定所述驾驶员的右手未脱离方向盘；可以在所述方向盘的坐标范围与所述驾驶员的右手的坐标范围的重合区域未达到第二预设面积阈值的情况下，确定所述驾驶员的右手脱离方向盘。其中，所述第二预设面积阈值可以等于所述第一预设面积阈值，也可以不等于所述第一预设面积阈值。又例如，可以根据方向盘位置的中心坐标和手部位置的中心坐标之间的距离，通过判断该距离是否超过预定的距离阈值，相应地确定驾驶员的手部是否脱离方向盘
在一种可能的实现方式中，在检测到所述驾驶员的左手脱离方向盘、右手未脱离方向盘的情况下，所述方向盘脱手检测结果可以包括单手脱离方向盘和/或左手脱离方向盘；在检测到所述驾驶员的右手脱离方向盘、左手未脱离方向盘的情况下，所述方向盘脱手检测结果可以包括单手脱离方向盘和/或右手脱离方向盘；在检测到所述驾驶员的左手和右手均脱离方向盘的情况下，所述方向盘脱手检测结果可以包括双手脱离方向盘；在检测到所述驾驶员的左手和右手均未脱离方向盘的情况下，所述方向盘脱手检测结果可以包括手部未脱离方向盘。
在步骤S13中，基于所述方向盘脱手检测结果，生成提醒信息。
在本公开实施例中，可以响应于所述方向盘脱手检测结果包括所述驾驶员的手部脱离方向盘，生成用于提醒所述驾驶员将手部放回方向盘上的提醒信息。
在一种可能的实现方式中，可以根据所述方向盘脱手检测结果对应的方向盘脱手类别、所述驾驶员的手部动作类别和驾驶状态中的至少之一，生成提醒信息。
作为该实现方式的一个示例，可以根据所述方向盘脱手检测结果对应的方向盘脱手类别，生成提醒信息。例如，若所述方向盘脱手检测结果对应的方向盘脱手类别为单手脱离方向盘或双手脱离方向盘，则所述提醒信息可以包括“请将双手放在方向盘上”的信息。
作为该实现方式的一个示例，可以根据所述方向盘脱手检测结果对应的所述驾驶员的手部动作类别，生成提醒信息。例如，若所述方向盘脱手检测结果对应的所述驾驶员的手部动作类别为打电话，则所述提醒信息可以包括“请勿打电话”的信息。又如，若所述方向盘脱手检测结果对应的所述驾驶员的手部动作类别为抽烟，则所述提醒信息可以包括“请勿抽烟”的信息。
作为该实现方式的一个示例，可以根据所述驾驶员的驾驶状态，生成提醒信息。例如，在自动驾驶功能为已开启状态的情况下，若所述驾驶状态为非危险状态，则可以通过车机和/或中控台等显示“自动驾驶中”的提醒信息。又如，在自动驾驶功能为已开启状态的情况下，若所述驾驶状态为危险状态，则所述提醒信息可以包括“请集中注意力”“请将双手放在方向盘上”等信息。
在本公开实施例中，通过获取驾驶区域的视频流，基于所述驾驶区域的视频流，利用计算机视觉的方式对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果，并基于所述方向盘脱手检测结果，生成提醒信息，由此有助于提高行驶的安全性。另外，通过利用驾驶区域的视频流进行方向盘脱手检测，能够获得较为可靠的检测结果，无需增设额外的硬件，例如，无需增设转向柱扭矩传感器、方向盘压力传感器、方向盘触觉传感器等硬件，从而能够降低方向盘脱手检测的成本。
在一种可能的实现方式中，所述基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果，包括：基于所述驾驶区域的视频流，检测所述驾驶员的手部是否脱离方向盘，得到所述驾驶区域的视频流对应的方向盘脱手类别；将所述方向盘脱手类别，确定为方向盘脱手检测 结果。
具体地，可以预先对方向盘脱手的情况进行分类，例如设定方向盘脱手类别包括：方向盘未脱手、单手脱离方向盘和双手脱离方向盘；可选地，单手脱离方向盘的类别还可以进一步细分为：左手单后脱离方向盘和右手单手脱离方向盘。然后通过图像分类/视频分类的方式检测驾驶员的方向盘脱手类别。例如，若基于所述驾驶区域的视频流，检测到所述驾驶员的左手脱离方向盘、右手未脱离方向盘，则可以得到所述驾驶区域的视频流对应的方向盘脱手类别为单手脱离方向盘，并可以确定所述方向盘脱手检测结果包括单手脱离方向盘。又如，若基于所述驾驶区域的视频流，检测到所述驾驶员的右手脱离方向盘、左手未脱离方向盘，则可以得到所述驾驶区域的视频流对应的方向盘脱手类别为单手脱离方向盘，并可以确定所述方向盘脱手检测结果包括单手脱离方向盘。又如，若基于所述驾驶区域的视频流，检测到所述驾驶员的左手和右手均脱离方向盘，则可以得到所述驾驶区域的视频流对应的方向盘脱手类别为双手脱离方向盘，并可以确定所述方向盘脱手检测结果包括双手脱离方向盘。又如，若基于所述驾驶区域的视频流，检测到所述驾驶员的左手和右手均未脱离方向盘，则可以得到所述驾驶区域的视频流对应的方向盘脱手类别为手部未脱离方向盘，并可以确定所述方向盘脱手检测结果包括手部未脱离方向盘。
在该实现方式中，能够基于方向盘脱手类别准确地得到方向盘脱手检测结果。
作为该实现方式的一个示例，所述方向盘脱手类别为手部未脱离方向盘、单手脱离方向盘或者双手脱离方向盘。在该示例中，单手脱离方向盘可以是左手脱离方向盘、右手未脱离方向盘，或者可以是右手脱离方向盘、左手未脱离方向盘。在该示例中，通过将手部脱离方向盘进一步划分为单手脱离方向盘和双手脱离方向盘，进一步细化了方向盘脱手的类别，由此能够检测出不同的方向盘脱手类别，进而可以更精准地进行方向盘脱手提醒。
作为实现方式的一个示例，在所述得到所述驾驶区域的视频流对应的方向盘脱手类别之后，所述方法还可以包括：基于所述驾驶区域的视频流，检测所述驾驶员的手部动作，得到所述驾驶区域的视频流对应的驾驶员的手部动作类别。在该示例中，可以响应于所述方向盘脱手类别为手部脱离方向盘(例如单手脱离方向盘和/或双手脱离方向盘)，基于所述驾驶区域的视频流，进一步检测所述驾驶员的手部动作，以便在驾驶员单手脱离方向盘或双手脱离方向盘时进一步分析驾驶员手部动作的危险性。当然，在其他示例中，在所述得到所述驾驶区域的视频流对应的方向盘脱手类别之后，也可以不检测所述驾驶员的手部动作。
在一种可能的实现方式中，所述基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果，包括：基于所述驾驶区域的视频流，检测所述驾驶员的手部是否脱离方向盘和/或所述驾驶员的手部动作，得到所述驾驶区域的视频流对应的方向盘脱手类别和/或所述驾驶员的手部动作类别；根据所述方向盘脱手类别和/或所述驾驶员的手部动作类别，确定方向盘脱手检测结果。
作为该实现方式的一个示例，所述方向盘脱手类别为手部未脱离方向盘、单手脱离方向盘或者双手脱离方向盘。
作为该实现方式的一个示例，可以基于所述驾驶区域的视频流，并行检测所述驾驶员的手部是否脱离方向盘以及所述驾驶员的手部动作，得到所述驾驶区域的视频流对应的方向盘脱手类别和所述驾驶员的手部动作类别。即，在该示例，检测所述驾驶员的手部是否脱离方向盘以及检测所述驾驶员的 手部动作可以同时进行。
作为该实现方式的另一个示例，可以基于所述驾驶区域的视频流，先检测所述驾驶员的手部是否脱离方向盘，得到所述驾驶区域的视频流对应的方向盘脱手类别，再基于所述驾驶区域的视频流，检测所述驾驶员的手部动作，得到所述驾驶区域的视频流对应的所述驾驶员的手部动作类别。
作为该实现方式的另一个示例，可以基于所述驾驶区域的视频流，先检测所述驾驶员的手部是否脱离方向盘，得到所述驾驶区域的视频流对应的方向盘脱手类别。在所述方向盘脱手类别为手部未脱离方向盘的情况下，可以不再检测所述驾驶员的手部动作；在所述方向盘脱手类别为手部脱离方向盘的情况下，可以检测所述驾驶员的手部动作，得到所述驾驶区域的视频流对应的所述驾驶员的手部动作类别。
作为该实现方式的另一个示例，可以基于所述驾驶区域的视频流，先检测所述驾驶员的手部动作，得到所述驾驶区域的视频流对应的所述驾驶员的手部动作类别，再检测所述驾驶员的手部是否脱离方向盘，得到所述驾驶区域的视频流对应的方向盘脱手类别。
作为该实现方式的另一个示例，可以基于所述驾驶区域的视频流，先检测所述驾驶员的手部动作，得到所述驾驶区域的视频流对应的所述驾驶员的手部动作类别。在所述驾驶员的手部动作类别属于预设的危险动作类别的情况下，可以根据驾驶员的手部动作类别，确定方向盘脱手检测结果；在所述驾驶员的手部动作类别不属于预设的危险动作类别的情况下，可以基于所述驾驶区域的视频流，检测所述驾驶员的手部是否脱离方向盘，得到所述驾驶区域的视频流对应的方向盘脱手类别，并根据所述方向盘脱手类别，确定方向盘脱手检测结果。
预设的危险动作类别可以包括可能造成驾驶员分心等影响驾驶安全的动作类别。例如，预设的危险动作类别可以包括单手打电话、单手喝水、单手抽烟、双手操作手机等中的至少之一。例如，若所述驾驶员的手部动作类别为单手打电话，则可以确定所述方向盘脱手检测结果为“单手脱离方向盘打电话”；若所述驾驶员的手部动作类别为双手操作手机，则可以确定所述方向盘脱手检测结果为“双手脱离方向盘操作手机”。若所述驾驶员的手部动作类别不属于预设的危险动作类别，则可以基于所述驾驶区域的视频流，检测所述驾驶员的手部是否脱离方向盘，得到所述驾驶区域的视频流对应的方向盘脱手类别。若所述方向盘脱手类别为手部未脱离方向盘，则所述方向盘脱手检测结果可以包括手部未脱离方向盘；若所述方向盘脱手类别为单手脱离方向盘，则所述方向盘脱手检测结果可以包括单手脱离方向盘；若所述方向盘脱手类别为双手脱离方向盘，则所述方向盘脱手检测结果可以包括双手脱离方向盘。
该实现方式能够获得更精确的手部动作类别检测结果，并进一步判断手部动作类别是否安全，以及可以根据更精确的手部动作类别检测结果进行更有针对性的提醒，例如针对驾驶员单手握方向盘、另一手握持电话的动作生成“开车时请不要打电话哦”的提醒信息，协助驾驶员安全驾驶，减少行驶中的安全隐患。
在一种可能的实现方式中，所述基于所述方向盘脱手检测结果，生成提醒信息，包括：响应于所述方向盘脱手检测结果为所述驾驶员的手部脱离方向盘，且所述驾驶员的手部动作属于危险动作，生成提醒信息。
例如，危险动作可以包括喝水、打电话、操作手机、抽烟等中的至少之一。
作为该实现方式的一个示例，所述响应于所述方向盘脱手检测结果为所述驾驶员的手部脱离方向 盘，且所述驾驶员的手部动作属于危险动作，生成提醒信息，可以包括：响应于所述方向盘脱手检测结果为单手脱离方向盘，且所述驾驶员的手部动作属于危险动作，生成提醒信息。例如，可以响应于所述方向盘脱手检测结果为单手脱离方向盘，且所述驾驶员的手部动作为喝水、打电话或抽烟，生成提醒信息。
作为该实现方式的另一个示例，所述响应于所述方向盘脱手检测结果为所述驾驶员的手部脱离方向盘，且所述驾驶员的手部动作属于危险动作，生成提醒信息，可以包括：响应于所述方向盘脱手检测结果为双手脱离方向盘，且所述驾驶员的手部动作属于危险动作，生成提醒信息。例如，可以响应于所述方向盘脱手检测结果为双手脱离方向盘，且所述驾驶员的手部动作为双手操作手机，生成提醒信息。
该实现方式能够判别驾驶员脱手情况下是执行正常的操控还是危险动作，提醒驾驶员在驾车过程中不进行危险动作，从而有助于减少行驶中的安全隐患。
在一种可能的实现方式中，在所述方向盘脱手检测结果为单手脱离方向盘，所述驾驶员的手部动作属于非危险动作，且单手脱离方向盘的时长未达到第二时长阈值的情况下，可以不生成提醒信息。例如，非危险动作可以是换挡、操作车载娱乐系统、拉手刹等中的至少之一。根据该实现方式，可以在驾驶员单手脱离方向盘进行短时间的非危险动作时，不进行提醒，从而可以减少不必要的提醒。
在一种可能的实现方式中，所述基于所述方向盘脱手检测结果，生成提醒信息，包括：响应于所述方向盘脱手检测结果为双手脱离方向盘，生成提醒信息。
在一种可能的实现方式中，所述基于所述方向盘脱手检测结果，生成提醒信息，包括：在自动驾驶功能为已开启状态的情况下，基于所述方向盘脱手检测结果，确定驾驶状态；响应于所述驾驶状态为危险状态，生成提醒信息。
在该实现方式中，自动驾驶功能可以表示交通工具(例如车辆)无需驾驶员操控即可达到安全驾驶状态的功能。在一些车辆产品或应用场景中，自动驾驶功能也可能被称作辅助驾驶功能。自动驾驶功能可以基于驾驶员的操作开启或关闭，也可以自动开启或关闭。
在该实现方式中，在自动驾驶功能为已开启状态的情况下，若基于所述方向盘脱手检测结果，确定驾驶状态为危险状态，则可以生成提醒信息；在自动驾驶功能为已开启状态的情况下，若基于所述方向盘脱手检测结果，确定驾驶状态为非危险状态，则可以不生成提醒信息。
在该实现方式中，能够结合自动驾驶功能的开启状态来判断驾驶状态是否为危险状态，从而使得方向盘脱手检测方法应用于具有自动驾驶功能的车辆中时，能够在自动驾驶功能开启的情况下进行只做必要的提醒，减少过度提醒对驾驶员造成的干扰。
作为该实现方式的一个示例，所述基于所述方向盘脱手检测结果，确定驾驶状态，包括：基于所述方向盘脱手检测结果，确定所述驾驶员的手部脱离方向盘的时长；基于所述驾驶员的手部脱离方向盘的时长，确定驾驶状态。
在该示例中，可以基于驾驶区域的视频流检测驾驶员手部脱离方向盘的时长。其中，驾驶员手部脱离方向盘的时长可以基于视频流中连续的驾驶员手部脱离方向盘状态的视频片段中，检测到驾驶员手部脱离方向盘的首帧和末帧图像之间的时间差来确定。
作为该实现方式的另一个示例，所述基于所述方向盘脱手检测结果，确定驾驶状态，包括：基于所述方向盘脱手检测结果和所述驾驶员的注意力检测结果，确定驾驶状态。
在该示例中，可以基于所述驾驶区域的视频流，对所述驾驶员进行注意力检测，得到所述驾驶员的注意力检测结果。其中，注意力检测可以用于检测所述驾驶员的注意力是否集中于驾驶，即检测驾驶员是否处于分心状态。在该示例中，基于所述驾驶员的手部脱离方向盘的时长和/或基于所述驾驶员方向盘脱手检测结果结合驾驶员的注意力检测结果，确定驾驶状态，由此确定的驾驶状态能够准确地反映当前的危险程度。
在一个例子中，所述基于所述驾驶员的手部脱离方向盘的时长，确定驾驶状态，包括：响应于所述驾驶员的手部脱离方向盘的时长达到第一时长阈值确定驾驶状态为危险状态。以及，所述基于所述方向盘脱手检测结果和所述驾驶员的注意力检测结果，确定驾驶状态，包括：响应于所述方向盘脱手检测结果为所述驾驶员的手部脱离方向盘，且所述驾驶员的注意力检测结果为驾驶员处于分心状态，确定驾驶状态为危险状态。例如，第一时长阈值可以是10秒。在这个例子中，通过响应于所述驾驶员的手部脱离方向盘的时长达到第一时长阈值和/或所述驾驶员在方向盘脱手状态下的注意力检测结果为驾驶员处于分心状态，确定驾驶状态为危险状态，并响应于所述驾驶状态为危险状态，生成提醒信息，能够在自动驾驶功能开启状态下驾驶员手部脱离方向盘时间过长或驾驶员分心的危险场景中生成提醒信息以帮助减少行驶中的安全隐患。
在另一个例子中，所述基于所述驾驶员的手部脱离方向盘的时长和/或所述驾驶员的注意力检测结果，确定驾驶状态，包括：响应于所述驾驶员的手部脱离方向盘的时长未达到第一时长阈值，且所述驾驶员的注意力检测结果为注意力集中，确定驾驶状态为非危险状态。根据这个例子，可以允许驾驶员在自动驾驶功能开启的情况下，手部短时间脱离方向盘，但要求驾驶员保持注意力集中，即，保持对驾驶环境的观察。通过响应于所述驾驶员的手部脱离方向盘的时长未达到第一时长阈值，且所述驾驶员的注意力检测结果为驾驶员专注于驾驶(即驾驶员未分心)，确定驾驶状态为非危险状态，由此能够减少不必要的提醒。
在一个例子中，可以响应于所述驾驶状态为危险状态，关闭所述自动驾驶功能并生成提醒驾驶员恢复手动驾驶的提醒信息。
在一种可能的实现方式中，所述基于所述方向盘脱手检测结果，生成提醒信息，包括：在自动驾驶功能为未开启状态的情况下，响应于所述方向盘脱手检测结果为所述驾驶员的手部脱离方向盘，且所述驾驶员的手部动作属于危险动作，生成提醒信息。在该实现方式中，通过该实现方式，在自动驾驶功能关闭状态下根据手部动作确定驾驶员动作的安全性，进一步提升行驶的安全性。
在一种可能的实现方式中，所述生成提醒信息，包括：根据脱离方向盘的手的数量、手部脱离方向盘的时长和所述驾驶员的手部动作类别中的至少之一，生成提醒信息。
作为该实现方式的一个示例，可以根据脱离方向盘的手的数量，生成提醒信息。例如，双手脱离方向盘对应的提醒信息中的语音内容与单手脱离方向盘对应的提醒信息中的语音内容相比，可以包含更具有紧迫感的提醒内容。
作为该实现方式的一个示例，可以根据手部脱离方向盘的时长，生成提醒信息。例如，提醒信息的警示级别可以与所述手部脱离方向盘的时长正相关，所述手部脱离方向盘的时长越长，则提醒信息的警示级别越高。
作为该实现方式的一个示例，可以根据所述驾驶员的手部动作类别，生成提醒信息。例如，若所述驾驶员的手部动作类别为打电话，则所述提醒信息可以包括“开车过程中请勿打电话”的信息。
在该实现方式中，通过根据脱离方向盘的手的数量、手部脱离方向盘的时长和所述驾驶员的手部动作类别中的至少之一生成提醒信息，能够更具针对性地进行提醒，从而有助于进一步提高行驶的安全性。
作为该实现方式的一个示例，所述根据脱离方向盘的手的数量、手部脱离方向盘的时长和所述驾驶员的手部动作类别中的至少之一，生成提醒信息，包括：在所述驾驶员的手部动作类别为预设动作类别的情况下，获取所述预设动作类别对应的提醒动画和/或语音；生成控制显示屏显示所述提醒动画的控制信息，和/或，生成控制扬声器播放所述语音的提醒信息。
在一个例子中，预设动作类别可以包括打电话、喝水、抽烟等中的至少之一。例如，打电话对应的提醒动画可以包括边开车边打电话的动画，喝水对应的提醒动画可以包括边开车边喝水的动画，抽烟对应的提醒动画可以包括边开车边抽烟的动画，等等。又如，打电话对应的语音可以包括“开车过程中请勿打电话”的语音，喝水对应的语音可以包括“开车过程中请勿喝水”的语音，抽烟对应的语音可以包括“开车过程中请勿抽烟”的语音，等等。
在该示例中，通过在所述驾驶员的手部动作类别为预设动作类别的情况下，获取所述预设动作类别对应的提醒动画和/或语音，并生成控制显示屏显示所述提醒动画的控制信息，和/或，生成控制扬声器播放所述语音的控制信息，由此能够基于驾驶员的手部动作从视觉上和/或听觉上进行针对性的提醒，从而能够提升提醒效果，进而提升行驶的安全性。
在一种可能的实现方式中，所述方向盘脱手检测结果包括方向盘脱手类别；所述基于所述方向盘脱手检测结果，生成提醒信息包括：根据所述方向盘脱手类别生成对应的警示级别的提醒信息，其中，所述方向盘脱手类别包括：手部未脱离方向盘、单手脱离方向盘或者双手脱离方向盘。
由于双手脱离方向盘的危险程度通常高于单手脱离方向盘，因此，双手脱离方向盘对应的提醒信息的警示级别可以高于单手脱离方向盘对应的提醒信息的警示级别。例如，双手脱离方向盘对应的提醒信息中的提示音的频率可以高于单手脱离方向盘对应的提醒信息中的提示音的频率。又如，双手脱离方向盘对应的提醒信息中的提示音的时长可以高于单手脱离方向盘对应的提醒信息中的提示音的时长。又如，双手脱离方向盘对应的提醒信息中的提示语音的重复次数可以多于单手脱离方向盘对应的提醒信息中的提示语音的重复次数。例如，双手脱离方向盘对应的提醒信息中的提示语音可以重复3次，单手脱离方向盘对应的提醒信息中的提示语音可以重复2次。又如，双手脱离方向盘对应的提醒信息中的指示灯的闪烁频率可以高于单手脱离方向盘对应的提醒信息中的指示灯的闪烁频率。
该实现方式中，能够基于所述方向盘脱手类别对应的危险程度进行提醒，从而能够使被提醒的人员准确获知方向盘脱手类别的警示级别，进一步提高行驶的安全性。
在一种可能的实现方式中，所述基于所述方向盘脱手检测结果，生成提醒信息，包括：根据所述方向盘脱手检测结果，确定所述驾驶员的驾驶状态对应的危险状态级别；生成所述危险状态级别对应的提醒信息。
作为该实现方式的一个示例，危险状态级别可以包括第一危险状态级别和第二危险状态级别，其中，所述第一危险状态级别对应的驾驶状态的危险程度高于所述第二危险状态级别。
在一个例子中，所述第一危险状态级别对应的提醒信息可以包括第一提示音，所述第二危险状态级别可以包括第二提示音，其中，所述第一提示音的频率可以高于所述第二提示音的频率，和/或，所述第一提示音的时长可以大于所述第二提示音的时长。
在另一个例子中，所述第一危险状态级别对应的提醒信息可以包括第一语音，所述第二危险状态级别可以包括第二语音，其中，所述第一语音的语音内容可以比第二语音的语音内容更具有紧迫感。
在另一个例子中，所述第一危险状态级别对应的提醒信息可以包括控制指示灯以第一频率闪烁的指令，所述第二危险状态级别对应的提醒信息可以包括控制指示灯以第二频率闪烁的指令，其中，第一频率可以高于所述第二频率。
当然，在其他示例中，危险状态级别的数量可以更多，例如可以包括3个或4个危险状态级别等，在此不作限定。
在该实现方式中，通过根据所述方向盘脱手检测结果，确定所述驾驶员的驾驶状态对应的危险状态级别，并生成所述危险状态级别对应的提醒信息，由此能够基于所述驾驶员的驾驶状态对应的危险程度进行提醒，从而能够进一步提高行驶的安全性。
在一种可能的实现方式中，所述基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果，包括：响应于所述驾驶区域所属车辆的行驶速度大于第一预设速度阈值，基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果；和/或，所述基于所述方向盘脱手检测结果，生成提醒信息，包括：响应于所述方向盘脱手检测结果为单手脱离方向盘，所述驾驶员的手部动作属于危险动作，且所述行驶速度达到第二预设速度阈值，生成提醒信息；和/或，所述基于所述方向盘脱手检测结果，生成提醒信息，包括：响应于所述方向盘脱手检测结果为双手脱离方向盘，且所述行驶速度达到第三预设速度阈值，生成提醒信息，其中，所述第三预设速度阈值不大于所述第二预设速度阈值。
在该实现方式中，可以在所述驾驶区域所属车辆的行驶速度大于第一预设速度阈值的情况下，基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果，由此能够提高行驶的安全性；并可以在所述驾驶区域所属车辆的行驶速度不大于第一预设速度阈值的情况下，不进行方向盘脱手检测，由此能够减少不必要的检测和提醒。作为该实现方式的一个示例，第一预设速度阈值可以是0，当然，也可以根据实际应用场景需求灵活设置第一预设速度阈值，在此不作限定。在该示例中，可以响应于所述驾驶区域所属车辆的行驶速度大于0，基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果；并可以在所述驾驶区域所属车辆的行驶速度为0的情况下，不进行方向盘脱手检测，以免不必要的检测和占用多余的驱动耗能和处理资源。
在该实现方式中，可以响应于所述方向盘脱手检测结果为单手脱离方向盘，所述驾驶员的手部动作属于危险动作，且所述行驶速度达到第二预设速度阈值，生成提醒信息；并可以在所述方向盘脱手检测结果为单手脱离方向盘，所述驾驶员的手部动作属于危险动作，且所述行驶速度未达到第二预设速度阈值的情况下，不生成提醒信息。例如，第二预设速度阈值可以为30km/h。
在该实现方式中，可以响应于所述方向盘脱手检测结果为双手脱离方向盘，且所述行驶速度达到第三预设速度阈值，生成提醒信息；并可以在所述方向盘脱手检测结果为双手脱离方向盘，且所述行驶速度未达到第三预设速度阈值的情况下，不生成提醒信息。例如，第三预设速度阈值可以为10km/h。
根据该实现方式，能够在处于行驶速度较低的低风险状态时减少提醒，以及在单手脱手和双手脱手时基于不同的速度阈值针对性地开启提醒，减少行驶中的安全隐患的同时，减少不必要的检测和/或提醒。
在一种可能的实现方式中，所述方法还包括：根据所述驾驶区域的视频流，对所述驾驶员进行疲 劳检测，得到疲劳检测结果；基于所述疲劳检测结果，生成提醒信息。在该实现方式中，所述疲劳检测结果可以包括疲劳状态或者非疲劳状态。在该实现方式中，可以响应于所述疲劳状态结果为疲劳状态，生成提醒信息。
在该实现方式中，通过根据所述驾驶区域的视频流，对所述驾驶员进行疲劳检测，由此能够基于同一个或同一组摄像头采集的所述驾驶区域的视频流分别进行方向盘脱手检测和疲劳检测，从而能够降低在交通工具的舱内设置摄像头的成本。例如，可以基于在舱内部署的一套驾驶员，行为检测系统实现驾驶员疲劳检测和方向盘脱手检测功能，将不同的驾驶员行为检测功能集成在同一系统中，降低检测成本。另外，通过基于所述疲劳检测结果和方向盘脱手检测结果，生成提醒信息，能够进一步提高行驶的安全性。
在一种可能的实现方式中，所述基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果，包括：将所述驾驶区域的视频流中的至少一帧图像输入神经网络，经由所述神经网络对驾驶员进行方向盘脱手检测，得到所述驾驶区域的视频流对应的方向盘脱手类别，并将所述方向盘脱手类别确定为方向盘脱手检测结果；或者，将所述驾驶区域的视频流中的至少一帧图像输入神经网络，经由所述神经网络对驾驶员进行方向盘脱手检测，得到所述驾驶区域的视频流对应的方向盘脱手类别和所述驾驶员的手部动作类别，并根据所述方向盘脱手类别和所述驾驶员的手部动作类别确定方向盘脱手检测结果。在该实现方式中，通过神经网络进行方向盘脱手检测，能够提高方向盘脱手检测的准确性和速度。且神经网络可以预先训练并部署，可以快速实现较大数据量的图像或视频流的检测，因此可以应用于实时驾驶场景的视频流检测中。
下面对本公开实施例的一个应用场景进行说明。在该应用场景中，可以通过DMS摄像头采集驾驶区域的视频流，处理器可以从所述DMS摄像头获取所述驾驶区域的视频流，并基于驾驶区域的视频流，检测所述驾驶员的手部是否脱离方向盘和所述驾驶员的手部动作，得到所述驾驶区域的视频流对应的方向盘脱手类别和所述驾驶员的手部动作类别，并根据所述方向盘脱手类别和所述驾驶员的手部动作类别，确定方向盘脱手检测结果。若所述方向盘脱手检测结果为单手脱离方向盘打电话，则可以通过中控台显示边开车边打电话的提醒动画，并播放“开车过程中请勿打电话”的语音。
可以理解，本公开提及的上述各个方法实施例，在不违背原理逻辑的情况下，均可以彼此相互结合形成结合后的实施例，限于篇幅，本公开不再赘述。本领域技术人员可以理解，在具体实施方式的上述方法中，各步骤的具体执行顺序应当以其功能和可能的内在逻辑确定。
此外，本公开还提供了方向盘脱手检测装置、电子设备、计算机可读存储介质、程序，上述均可用来实现本公开提供的任一种方向盘脱手检测方法，相应技术方案和技术效果可参见方法部分的相应记载，不再赘述。
图2示出本公开实施例提供的方向盘脱手检测装置的框图。如图2所示，所述方向盘脱手检测装置包括：获取模块21，用于获取驾驶区域的视频流；第一检测模块22，用于基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果；第一生成模块23，用于基于所述方向盘脱手检测结果，生成提醒信息。
在一种可能的实现方式中，所述第一检测模块22用于：基于所述驾驶区域的视频流，检测所述驾驶员的手部是否脱离方向盘，得到所述驾驶区域的视频流对应的方向盘脱手类别；将所述方向盘脱手类别，确定为方向盘脱手检测结果。
在一种可能的实现方式中，所述第一检测模块22用于：基于所述驾驶区域的视频流，检测所述驾驶员的手部是否脱离方向盘和/或所述驾驶员的手部动作，得到所述驾驶区域的视频流对应的方向盘脱手类别和/或所述驾驶员的手部动作类别；根据所述方向盘脱手类别和/或所述驾驶员的手部动作类别，确定方向盘脱手检测结果。
在一种可能的实现方式中，所述方向盘脱手类别为手部未脱离方向盘、单手脱离方向盘或者双手脱离方向盘。
在一种可能的实现方式中，所述第一生成模块23用于：响应于所述方向盘脱手检测结果为所述驾驶员的手部脱离方向盘，且所述驾驶员的手部动作属于危险动作，生成提醒信息。
在一种可能的实现方式中，所述第一生成模块23用于：在自动驾驶功能为已开启状态的情况下，基于所述方向盘脱手检测结果，确定驾驶状态；响应于所述驾驶状态为危险状态，生成提醒信息。
在一种可能的实现方式中，所述第一生成模块23用于：基于所述方向盘脱手检测结果，确定所述驾驶员的手部脱离方向盘的时长；基于所述驾驶员的手部脱离方向盘的时长，确定驾驶状态；和/或所述第一生成模块用于：基于所述方向盘脱手检测结果和所述驾驶员的注意力检测结果，确定驾驶状态。
在一种可能的实现方式中，所述第一生成模块23用于：响应于所述驾驶员的手部脱离方向盘的时长达到第一时长阈值，确定驾驶状态为危险状态；和/或响应于所述方向盘脱手检测结果为所述驾驶员的手部脱离方向盘，且所述驾驶员的注意力检测结果为驾驶员处于分心状态，确定驾驶状态为危险状态。
在一种可能的实现方式中，所述第一生成模块23用于：在自动驾驶功能为未开启状态的情况下，响应于所述方向盘脱手检测结果为所述驾驶员的手部脱离方向盘，且所述驾驶员的手部动作属于危险动作，生成提醒信息。
在一种可能的实现方式中，所述第一生成模块23用于：根据脱离方向盘的手的数量、手部脱离方向盘的时长和所述驾驶员的手部动作类别中的至少之一，生成提醒信息。
在一种可能的实现方式中，所述第一生成模块23用于：在所述驾驶员的手部动作类别为预设动作类别的情况下，获取所述预设动作类别的提醒动画和/或语音；生成控制显示屏显示所述提醒动画的控制信息，和/或，生成控制扬声器播放所述语音的控制信息。
在一种可能的实现方式中，所述方向盘脱手检测结果包括方向盘脱手类别；所述第一生成模块23用于：根据所述方向盘脱手类别生成对应的警示级别的提醒信息，其中，所述方向盘脱手类别包括：手部未脱离方向盘、单手脱离方向盘或者双手脱离方向盘。
在一种可能的实现方式中，所述第一生成模块23用于：根据所述方向盘脱手检测结果，确定所述驾驶员的驾驶状态对应的危险状态级别；生成所述危险状态级别对应的提醒信息。
在一种可能的实现方式中，所述第一检测模块22用于：响应于所述驾驶区域所属车辆的行驶速度大于第一预设速度阈值，基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果；和/或，所述第一生成模块23用于：响应于所述方向盘脱手检测结果为单手脱离方向盘，所述驾驶员的手部动作属于危险动作，且所述行驶速度达到第二预设速度阈值，生成提醒信息；和/或，所述第一生成模块23用于：响应于所述方向盘脱手检测结果为双手脱离方向盘，且所述行驶速度达到第三预设速度阈值，生成提醒信息，其中，所述第三预设速度阈值不大于所述第二预设速度阈值。
在一种可能的实现方式中，所述装置还包括：第二检测模块，用于根据所述驾驶区域的视频流，对所述驾驶员进行疲劳检测，得到疲劳检测结果；第二生成模块，用于基于所述疲劳检测结果，生成提醒信息。
在一种可能的实现方式中，所述检测模块用于：将所述驾驶区域的视频流中的至少一帧图像输入神经网络，经由所述神经网络对驾驶员进行方向盘脱手检测，得到所述驾驶区域的视频流对应的方向盘脱手类别，并将所述方向盘脱手类别确定为方向盘脱手检测结果；或者，将所述驾驶区域的视频流中的至少一帧图像输入神经网络，经由所述神经网络对驾驶员进行方向盘脱手检测，得到所述驾驶区域的视频流对应的方向盘脱手类别和所述驾驶员的手部动作类别，并根据所述方向盘脱手类别和所述驾驶员的手部动作类别确定方向盘脱手检测结果。
在本公开实施例中，通过获取驾驶区域的视频流，基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果，并基于所述方向盘脱手检测结果，生成提醒信息，由此有助于提高行驶的安全性。另外，通过利用驾驶区域的视频流进行方向盘脱手检测，无需增设额外的硬件，从而能够降低方向盘脱手检测的成本。
在一些实施例中，本公开实施例提供的装置具有的功能或包含的模块可以用于执行上文方法实施例描述的方法，其具体实现和技术效果可以参照上文方法实施例的描述，为了简洁，这里不再赘述。
本公开实施例还提供一种计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现上述方法。其中，所述计算机可读存储介质可以是非易失性计算机可读存储介质，或者可以是易失性计算机可读存储介质。
本公开实施例还提出一种计算机程序，包括计算机可读代码，当所述计算机可读代码在电子设备中运行时，所述电子设备中的处理器执行用于实现上述方法。
本公开实施例还提供了另一种计算机程序产品，用于存储计算机可读指令，指令被执行时使得计算机执行上述任一实施例提供的方向盘脱手检测方法的操作。
本公开实施例还提供一种电子设备，包括：一个或多个处理器；用于存储可执行指令的存储器；其中，所述一个或多个处理器被配置为调用所述存储器存储的可执行指令，以执行上述方法。
电子设备可以被提供为终端、服务器或其它形态的设备。所述电子设备可以是车舱内的车机、域控制器或者处理器，还可以是DMS或者OMS中用于执行图像等数据处理操作的设备主机等。
图3示出本公开实施例提供的一种电子设备800的框图。例如，电子设备800可以是移动电话，计算机，数字广播终端，消息收发设备，游戏控制台，平板设备，医疗设备，健身设备，个人数字助理等终端。
参照图3，电子设备800可以包括以下一个或多个组件：处理组件802，存储器804，电源组件806，多媒体组件808，音频组件810，输入/输出(I/O)的接口812，传感器组件814，以及通信组件816。
处理组件802通常控制电子设备800的整体操作，诸如与显示，电话呼叫，数据通信，相机操作和记录操作相关联的操作。处理组件802可以包括一个或多个处理器820来执行指令，以完成上述的方法的全部或部分步骤。此外，处理组件802可以包括一个或多个模块，便于处理组件802和其他组件之间的交互。例如，处理组件802可以包括多媒体模块，以方便多媒体组件808和处理组件802之间的交互。
存储器804被配置为存储各种类型的数据以支持在电子设备800的操作。这些数据的示例包括用于 在电子设备800上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。存储器804可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。
电源组件806为电子设备800的各种组件提供电力。电源组件806可以包括电源管理系统，一个或多个电源，及其他与为电子设备800生成、管理和分配电力相关联的组件。
多媒体组件808包括在所述电子设备800和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件808包括一个前置摄像头和/或后置摄像头。当电子设备800处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件810被配置为输出和/或输入音频信号。例如，音频组件810包括一个麦克风(MIC)，当电子设备800处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器804或经由通信组件816发送。在一些实施例中，音频组件810还包括一个扬声器，用于输出音频信号。
I/O接口812为处理组件802和外围接口模块之间提供接口，上述外围接口模块可以是键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。
传感器组件814包括一个或多个传感器，用于为电子设备800提供各个方面的状态评估。例如，传感器组件814可以检测到电子设备800的打开/关闭状态，组件的相对定位，例如所述组件为电子设备800的显示器和小键盘，传感器组件814还可以检测电子设备800或电子设备800一个组件的位置改变，用户与电子设备800接触的存在或不存在，电子设备800方位或加速/减速和电子设备800的温度变化。传感器组件814可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件814还可以包括光传感器，如互补金属氧化物半导体(CMOS)或电荷耦合装置(CCD)图像传感器，用于在成像应用中使用。在一些实施例中，该传感器组件814还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器或温度传感器。
通信组件816被配置为便于电子设备800和其他设备之间有线或无线方式的通信。电子设备800可以接入基于通信标准的无线网络，如无线网络(Wi-Fi)、第二代移动通信技术(2G)、第三代移动通信技术(3G)、第四代移动通信技术(4G)/通用移动通信技术的长期演进(LTE)、第五代移动通信技术(5G)或它们的组合。在一个示例性实施例中，通信组件816经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信组件816还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
在示例性实施例中，电子设备800可以被一个或多个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控 制器、微控制器、微处理器或其他电子元件实现，用于执行上述方法。
在示例性实施例中，还提供了一种非易失性计算机可读存储介质，例如包括计算机程序指令的存储器804，上述计算机程序指令可由电子设备800的处理器820执行以完成上述方法。
图4示出本公开实施例提供的一种电子设备1900的框图。例如，电子设备1900可以被提供为一服务器。参照图4，电子设备1900包括处理组件1922，其进一步包括一个或多个处理器，以及由存储器1932所代表的存储器资源，用于存储可由处理组件1922的执行的指令，例如应用程序。存储器1932中存储的应用程序可以包括一个或一个以上的每一个对应于一组指令的模块。此外，处理组件1922被配置为执行指令，以执行上述方法。
电子设备1900还可以包括一个电源组件1926被配置为执行电子设备1900的电源管理，一个有线或无线网络接口1950被配置为将电子设备1900连接到网络，和一个输入输出(I/O)接口1958。电子设备1900可以操作基于存储在存储器1932的操作系统，例如微软服务器操作系统(Windows Server TM)，苹果公司推出的基于图形用户界面操作系统(Mac OS X TM)，多用户多进程的计算机操作系统(Unix TM),自由和开放原代码的类Unix操作系统(Linux TM)，开放原代码的类Unix操作系统(FreeBSD TM)或类似。
在示例性实施例中，还提供了一种非易失性计算机可读存储介质，例如包括计算机程序指令的存储器1932，上述计算机程序指令可由电子设备1900的处理组件1922执行以完成上述方法。
本公开可以是系统、方法和/或计算机程序产品。计算机程序产品可以包括计算机可读存储介质，其上载有用于使处理器实现本公开的各个方面的计算机可读程序指令。
计算机可读存储介质可以是可以保持和存储由指令执行设备使用的指令的有形设备。计算机可读存储介质例如可以是――但不限于――电存储设备、磁存储设备、光存储设备、电磁存储设备、半导体存储设备或者上述的任意合适的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、静态随机存取存储器(SRAM)、便携式压缩盘只读存储器(CD-ROM)、数字多功能盘(DVD)、记忆棒、软盘、机械编码设备、例如其上存储有指令的打孔卡或凹槽内凸起结构、以及上述的任意合适的组合。这里所使用的计算机可读存储介质不被解释为瞬时信号本身，诸如无线电波或者其他自由传播的电磁波、通过波导或其他传输媒介传播的电磁波(例如，通过光纤电缆的光脉冲)、或者通过电线传输的电信号。
这里所描述的计算机可读程序指令可以从计算机可读存储介质下载到各个计算/处理设备，或者通过网络、例如因特网、局域网、广域网和/或无线网下载到外部计算机或外部存储设备。网络可以包括铜传输电缆、光纤传输、无线传输、路由器、防火墙、交换机、网关计算机和/或边缘服务器。每个计算/处理设备中的网络适配卡或者网络接口从网络接收计算机可读程序指令，并转发该计算机可读程序指令，以供存储在各个计算/处理设备中的计算机可读存储介质中。
用于执行本公开操作的计算机程序指令可以是汇编指令、指令集架构(ISA)指令、机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码，所述编程语言包括面向对象的编程语言—诸如Smalltalk、C++等，以及常规的过程式编程语言—诸如“C”语言或类似的编程语言。计算机可读程序指令可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上 执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络—包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。在一些实施例中，通过利用计算机可读程序指令的状态信息来个性化定制电子电路，例如可编程逻辑电路、现场可编程门阵列(FPGA)或可编程逻辑阵列(PLA)，该电子电路可以执行计算机可读程序指令，从而实现本公开的各个方面。
这里参照根据本公开实施例的方法、装置(系统)和计算机程序产品的流程图和/或框图描述了本公开的各个方面。应当理解，流程图和/或框图的每个方框以及流程图和/或框图中各方框的组合，都可以由计算机可读程序指令实现。
这些计算机可读程序指令可以提供给通用计算机、专用计算机或其它可编程数据处理装置的处理器，从而生产出一种机器，使得这些指令在通过计算机或其它可编程数据处理装置的处理器执行时，产生了实现流程图和/或框图中的一个或多个方框中规定的功能/动作的装置。也可以把这些计算机可读程序指令存储在计算机可读存储介质中，这些指令使得计算机、可编程数据处理装置和/或其他设备以特定方式工作，从而，存储有指令的计算机可读介质则包括一个制造品，其包括实现流程图和/或框图中的一个或多个方框中规定的功能/动作的各个方面的指令。
也可以把计算机可读程序指令加载到计算机、其它可编程数据处理装置、或其它设备上，使得在计算机、其它可编程数据处理装置或其它设备上执行一系列操作步骤，以产生计算机实现的过程，从而使得在计算机、其它可编程数据处理装置、或其它设备上执行的指令实现流程图和/或框图中的一个或多个方框中规定的功能/动作。
附图中的流程图和框图显示了根据本公开的多个实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或指令的一部分，所述模块、程序段或指令的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
该计算机程序产品可以具体通过硬件、软件或其结合的方式实现。在一个可选实施例中，所述计算机程序产品具体体现为计算机存储介质，在另一个可选实施例中，计算机程序产品具体体现为软件产品，例如软件开发包(Software Development Kit，SDK)等等。
以上已经描述了本公开的各实施例，上述说明是示例性的，并非穷尽性的，并且也不限于所披露的各实施例。在不偏离所说明的各实施例的范围和精神的情况下，对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。本文中所用术语的选择，旨在最好地解释各实施例的原理、实际应用或对市场中的技术的改进，或者使本技术领域的其它普通技术人员能理解本文披露的各实施例。

Claims (20)

  1. 一种方向盘脱手检测方法，其特征在于，包括：
    获取驾驶区域的视频流；
    基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果；
    基于所述方向盘脱手检测结果，生成提醒信息。
  2. 根据权利要求1所述的方法，其特征在于，所述基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果，包括：
    基于所述驾驶区域的视频流，检测所述驾驶员的手部是否脱离方向盘，得到所述驾驶区域的视频流对应的方向盘脱手类别；
    将所述方向盘脱手类别，确定为方向盘脱手检测结果。
  3. 根据权利要求1所述的方法，其特征在于，所述基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果，包括：
    基于所述驾驶区域的视频流，检测所述驾驶员的手部是否脱离方向盘和/或所述驾驶员的手部动作，得到所述驾驶区域的视频流对应的方向盘脱手类别和/或所述驾驶员的手部动作类别；
    根据所述方向盘脱手类别和/或所述驾驶员的手部动作类别，确定方向盘脱手检测结果。
  4. 根据权利要求2或3所述的方法，其特征在于，所述方向盘脱手类别为手部未脱离方向盘、单手脱离方向盘或者双手脱离方向盘。
  5. 根据权利要求1至4中任意一项所述的方法，其特征在于，所述基于所述方向盘脱手检测结果，生成提醒信息，包括：
    响应于所述方向盘脱手检测结果为所述驾驶员的手部脱离方向盘，且所述驾驶员的手部动作属于危险动作，生成提醒信息。
  6. 根据权利要求1至4中任意一项所述的方法，其特征在于，所述基于所述方向盘脱手检测结果，生成提醒信息，包括：
    在自动驾驶功能为已开启状态的情况下，基于所述方向盘脱手检测结果，确定驾驶状态；
    响应于所述驾驶状态为危险状态，生成提醒信息。
  7. 根据权利要求6所述的方法，其特征在于，所述基于所述方向盘脱手检测结果，确定驾驶状态，包括：
    基于所述方向盘脱手检测结果，确定所述驾驶员的手部脱离方向盘的时长；
    基于所述驾驶员的手部脱离方向盘的时长，确定驾驶状态；和/或
    所述基于所述方向盘脱手检测结果，确定驾驶状态，包括：
    基于所述方向盘脱手检测结果和所述驾驶员的注意力检测结果，确定驾驶状态。
  8. 根据权利要求7所述的方法，其特征在于，所述基于所述驾驶员的手部脱离方向盘的时长确定驾驶状态，包括：
    响应于所述驾驶员的手部脱离方向盘的时长达到第一时长阈值，确定驾驶状态为危险状态；
    所述基于所述方向盘脱手检测结果和所述驾驶员的注意力检测结果，确定驾驶状态，包括：
    响应于所述方向盘脱手检测结果为所述驾驶员的手部脱离方向盘，且所述驾驶员的注意力检测结果为驾驶员处于分心状态，确定驾驶状态为危险状态。
  9. 根据权利要求1至8中任意一项所述的方法，其特征在于，所述基于所述方向盘脱手检测结果， 生成提醒信息，包括：
    在自动驾驶功能为未开启状态的情况下，响应于所述方向盘脱手检测结果为所述驾驶员的手部脱离方向盘，且所述驾驶员的手部动作属于危险动作，生成提醒信息。
  10. 根据权利要求1至9中任意一项所述的方法，其特征在于，所述生成提醒信息，包括：
    根据脱离方向盘的手的数量、手部脱离方向盘的时长和所述驾驶员的手部动作类别中的至少之一，生成提醒信息。
  11. 根据权利要求10所述的方法，其特征在于，所述根据脱离方向盘的手的数量、手部脱离方向盘的时长和所述驾驶员的手部动作类别中的至少之一，生成提醒信息，包括：
    在所述驾驶员的手部动作类别为预设动作类别的情况下，获取所述预设动作类别对应的提醒动画和/或语音；
    生成控制显示屏显示所述提醒动画的控制信息，和/或，生成控制扬声器播放所述语音的控制信息。
  12. 根据权利要求1至11中任意一项所述的方法，其特征在于，所述方向盘脱手检测结果包括方向盘脱手类别；
    所述基于所述方向盘脱手检测结果，生成提醒信息包括：
    根据所述方向盘脱手类别生成对应的警示级别的提醒信息，其中，所述方向盘脱手类别包括：手部未脱离方向盘、单手脱离方向盘或者双手脱离方向盘。
  13. 根据权利要求1至12中任意一项所述的方法，其特征在于，所述基于所述方向盘脱手检测结果，生成提醒信息，包括：
    根据所述方向盘脱手检测结果，确定所述驾驶员的驾驶状态对应的危险状态级别；
    生成所述危险状态级别对应的提醒信息。
  14. 根据权利要求1至13中任意一项所述的方法，其特征在于，
    所述基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果，包括：响应于所述驾驶区域所属车辆的行驶速度大于第一预设速度阈值，基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果；
    和/或，
    所述基于所述方向盘脱手检测结果，生成提醒信息，包括：响应于所述方向盘脱手检测结果为单手脱离方向盘，所述驾驶员的手部动作属于危险动作，且所述行驶速度达到第二预设速度阈值，生成提醒信息；
    和/或，
    所述基于所述方向盘脱手检测结果，生成提醒信息，包括：响应于所述方向盘脱手检测结果为双手脱离方向盘，且所述行驶速度达到第三预设速度阈值，生成提醒信息，其中，所述第三预设速度阈值不大于所述第二预设速度阈值。
  15. 根据权利要求1至14中任意一项所述的方法，其特征在于，所述方法还包括：
    根据所述驾驶区域的视频流，对所述驾驶员进行疲劳检测，得到疲劳检测结果；
    基于所述疲劳检测结果，生成提醒信息。
  16. 根据权利要求1至15中任意一项所述的方法，其特征在于，所述基于所述驾驶区域的视频流， 对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果，包括：
    将所述驾驶区域的视频流中的至少一帧图像输入神经网络，经由所述神经网络对驾驶员进行方向盘脱手检测，得到所述驾驶区域的视频流对应的方向盘脱手类别，并将所述方向盘脱手类别确定为方向盘脱手检测结果；
    或者，
    将所述驾驶区域的视频流中的至少一帧图像输入神经网络，经由所述神经网络对驾驶员进行方向盘脱手检测，得到所述驾驶区域的视频流对应的方向盘脱手类别和所述驾驶员的手部动作类别，并根据所述方向盘脱手类别和所述驾驶员的手部动作类别确定方向盘脱手检测结果。
  17. 一种方向盘脱手检测装置，其特征在于，包括：
    获取模块，用于获取驾驶区域的视频流；
    第一检测模块，用于基于所述驾驶区域的视频流，对驾驶员进行方向盘脱手检测，得到方向盘脱手检测结果；
    第一生成模块，用于基于所述方向盘脱手检测结果，生成提醒信息。
  18. 一种电子设备，其特征在于，包括：
    一个或多个处理器；
    用于存储可执行指令的存储器；
    其中，所述一个或多个处理器被配置为调用所述存储器存储的可执行指令，以执行权利要求1至16中任意一项所述的方法。
  19. 一种计算机可读存储介质，其上存储有计算机程序指令，其特征在于，所述计算机程序指令被处理器执行时实现权利要求1至16中任意一项所述的方法。
  20. 一种计算机程序，包括计算机可读代码，其特征在于，当所述计算机可读代码在电子设备中运行时，所述电子设备中的处理器执行用于实现权利要求1至16中的任一权利要求所述的方法。
PCT/CN2021/078701 2020-08-31 2021-03-02 方向盘脱手检测方法及装置、电子设备和存储介质 WO2022041671A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010899671.1A CN112036314A (zh) 2020-08-31 2020-08-31 方向盘脱手检测方法及装置、电子设备和存储介质
CN202010899671.1 2020-08-31

Publications (1)

Publication Number Publication Date
WO2022041671A1 true WO2022041671A1 (zh) 2022-03-03

Family

ID=73586538

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/078701 WO2022041671A1 (zh) 2020-08-31 2021-03-02 方向盘脱手检测方法及装置、电子设备和存储介质

Country Status (2)

Country Link
CN (1) CN112036314A (zh)
WO (1) WO2022041671A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115782911A (zh) * 2023-01-09 2023-03-14 深圳曦华科技有限公司 行车场景中对方向盘脱手事件的数据处理方法及相关装置

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112036314A (zh) * 2020-08-31 2020-12-04 上海商汤临港智能科技有限公司 方向盘脱手检测方法及装置、电子设备和存储介质
CN112528910B (zh) * 2020-12-18 2023-04-07 上海高德威智能交通系统有限公司 手脱离方向盘检测方法、装置、电子设备及存储介质
CN112818839A (zh) * 2021-01-29 2021-05-18 北京市商汤科技开发有限公司 驾驶员违章行为识别方法、装置、设备及介质
CN113343833B (zh) * 2021-06-02 2022-08-30 东风汽车集团股份有限公司 非安全握姿的脱手检测方法、装置、设备及存储介质
CN113200046B (zh) * 2021-06-17 2023-12-05 东风悦享科技有限公司 一种驾驶员脱手方向盘检测方法及系统
CN114495073A (zh) * 2022-01-29 2022-05-13 上海商汤临港智能科技有限公司 方向盘脱手检测方法及装置、电子设备和存储介质
CN115171082B (zh) * 2022-06-29 2024-01-19 北京百度网讯科技有限公司 驾驶行为的检测方法、装置、电子设备及可读存储介质
CN115297231A (zh) * 2022-07-05 2022-11-04 浙江腾视智驾科技有限公司 一种基于手部定位功能的驾驶员行为监控系统
CN118107605A (zh) * 2024-04-30 2024-05-31 润芯微科技(江苏)有限公司 一种基于方向盘手势交互的车辆控制方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6927694B1 (en) * 2001-08-20 2005-08-09 Research Foundation Of The University Of Central Florida Algorithm for monitoring head/eye motion for driver alertness with one camera
CN101930669A (zh) * 2010-06-11 2010-12-29 金龙联合汽车工业（苏州）有限公司 车载驾驶行为实时监控报警装置
CN102263937A (zh) * 2011-07-26 2011-11-30 华南理工大学 基于视频检测的驾驶员驾驶行为监控装置及监控方法
CN110599791A (zh) * 2019-10-29 2019-12-20 北京汽车研究总院有限公司 信息监控方法、装置和设备
CN112036314A (zh) * 2020-08-31 2020-12-04 上海商汤临港智能科技有限公司 方向盘脱手检测方法及装置、电子设备和存储介质

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9501915B1 (en) * 2014-07-07 2016-11-22 Google Inc. Systems and methods for analyzing a video stream
CN107316436B (zh) * 2017-07-31 2021-06-18 努比亚技术有限公司 危险驾驶状态处理方法、电子设备及存储介质
CN110816403A (zh) * 2019-10-17 2020-02-21 中国第一汽车股份有限公司 车辆驾驶的警示方法、装置、车辆和存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6927694B1 (en) * 2001-08-20 2005-08-09 Research Foundation Of The University Of Central Florida Algorithm for monitoring head/eye motion for driver alertness with one camera
CN101930669A (zh) * 2010-06-11 2010-12-29 金龙联合汽车工业（苏州）有限公司 车载驾驶行为实时监控报警装置
CN102263937A (zh) * 2011-07-26 2011-11-30 华南理工大学 基于视频检测的驾驶员驾驶行为监控装置及监控方法
CN110599791A (zh) * 2019-10-29 2019-12-20 北京汽车研究总院有限公司 信息监控方法、装置和设备
CN112036314A (zh) * 2020-08-31 2020-12-04 上海商汤临港智能科技有限公司 方向盘脱手检测方法及装置、电子设备和存储介质

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115782911A (zh) * 2023-01-09 2023-03-14 深圳曦华科技有限公司 行车场景中对方向盘脱手事件的数据处理方法及相关装置
CN115782911B (zh) * 2023-01-09 2023-10-27 深圳曦华科技有限公司 行车场景中对方向盘脱手事件的数据处理方法及相关装置

Also Published As

Publication number Publication date
CN112036314A (zh) 2020-12-04

Similar Documents

Publication Publication Date Title
WO2022041671A1 (zh) 方向盘脱手检测方法及装置、电子设备和存储介质
WO2022062659A1 (zh) 智能驾驶控制方法及装置、车辆、电子设备和存储介质
WO2022048119A1 (zh) 车辆控制方法及装置、电子设备、存储介质和车辆
WO2022041670A1 (zh) 车舱内的乘员检测方法及装置、电子设备和存储介质
JP6491601B2 (ja) 車両内移動デバイス管理
WO2022062658A1 (zh) 基于酒精检测的智能驾驶控制方法及装置
US20150178990A1 (en) System and method for in-vehicle interaction
CN104134371A (zh) 一种车辆碰撞预警的方法和装置
WO2022041669A1 (zh) 遗留物品的提醒方法及装置、电子设备和存储介质
US9266473B1 (en) Remote hands-free backseat driver
CN108615140B (zh) 行程提醒方法、装置和存储介质
WO2023071174A1 (zh) 车内人员检测方法及装置、电子设备和存储介质
WO2023273060A1 (zh) 危险动作的识别方法及装置、电子设备和存储介质
WO2022052451A1 (zh) 一种影像信息的处理方法及装置、电子设备和存储介质
WO2022142331A1 (zh) 车载显示屏的控制方法及装置、电子设备和存储介质
WO2022188362A1 (zh) 分心提醒方法及装置、电子设备和存储介质
JP6295360B1 (ja) メッセージ表示用プログラム、メッセージ表示装置、及びメッセージ表示方法
JP2010205123A (ja) 運転支援方法、運転支援装置及び運転支援用プログラム
WO2022198907A1 (zh) 车辆显示屏的控制方法及装置、设备、介质及车辆
CN114407630A (zh) 车门控制方法及装置、电子设备和存储介质
WO2023071175A1 (zh) 关联车内的人和物的方法及装置、电子设备和存储介质
CN109461461B (zh) 音频播放方法、装置、电子设备及储存介质
JP2010072701A (ja) 車載装置及び情報出力方法
CN114013367A (zh) 一种远光灯使用提醒方法及装置、电子设备和存储介质
US11365975B2 (en) Visual confirmation system for driver assist system

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21859520

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM1205A DATED 11.08.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21859520

Country of ref document: EP

Kind code of ref document: A1