WO2022241598A1 - 一种自动检测驾驶员玩手机的装置及方法 - Google Patents

一种自动检测驾驶员玩手机的装置及方法 Download PDF

Info

Publication number
WO2022241598A1
WO2022241598A1 PCT/CN2021/094013 CN2021094013W WO2022241598A1 WO 2022241598 A1 WO2022241598 A1 WO 2022241598A1 CN 2021094013 W CN2021094013 W CN 2021094013W WO 2022241598 A1 WO2022241598 A1 WO 2022241598A1
Authority
WO
WIPO (PCT)
Prior art keywords
mobile phone
driver
module
alarm
image
Prior art date
Application number
PCT/CN2021/094013
Other languages
English (en)
French (fr)
Inventor
王艺臻
Original Assignee
海南师范大学
海南锔元科技有限公司
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 海南师范大学, 海南锔元科技有限公司 filed Critical 海南师范大学
Priority to PCT/CN2021/094013 priority Critical patent/WO2022241598A1/zh
Publication of WO2022241598A1 publication Critical patent/WO2022241598A1/zh

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
    • B60Q9/00—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
    • B60W40/09—Driving style or behaviour
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/08—Interaction between the driver and the control system
    • B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention

Definitions

  • the present application relates to the technical field of traffic safety, in particular to a device and method for automatically detecting a driver playing with a mobile phone.
  • the method of supervising the driver's mobile phone use is mainly to capture images through the camera and analyze whether the driver uses the mobile phone.
  • the camera needs to be turned on by the driver before driving, and the driver often forgets to start it due to habit, resulting in the monitoring device not working , cannot play a supervisory role.
  • the embodiment of the present application provides a device and method for automatically detecting whether the driver is playing with the mobile phone, which can automatically detect whether the driver is playing with the mobile phone after the vehicle is started and issue an alarm.
  • the application provides a device for automatically detecting drivers playing with mobile phones, including: a speed collection module, an image collection module, a data processing module and an alarm module; the speed collection module is used to collect the real-time driving speed of the vehicle;
  • the image acquisition module is used to collect image data in the car;
  • the alarm module is used to generate an alarm signal;
  • the data processing module includes a first communication unit, a second communication unit, a third communication unit, a processing unit, a first instruction A generation unit and a second instruction generation unit, the first communication unit is used to realize the data interaction between the processing unit and the speed acquisition module, and the second communication unit is used to realize the data interaction between the processing unit and the image acquisition module , the third communication unit is used to realize the data interaction between the processing unit and the alarm module, and the processing unit is used to judge whether to generate a detection instruction through the first instruction generation unit according to the real-time driving speed of the vehicle and pass the second communication
  • the unit sends to the image acquisition module, and detects whether the driver has a mobile
  • the speed acquisition module includes an acceleration detection unit and a calculation unit connected to each other, the acceleration detection unit is used to detect the real-time acceleration of the vehicle, and the calculation unit is used to calculate the real-time driving speed of the vehicle according to the real-time acceleration.
  • the acceleration detection unit adopts an MPU6050 gyroscope sensor.
  • the image acquisition module includes an interconnected camera unit and a first instruction processing unit, the camera unit is used to acquire image data in the vehicle, and the first instruction processing unit is used to identify and process the detected instruction.
  • the alarm module includes an alarm connected to each other and a second instruction processing unit, the alarm is used for issuing an alarm, and the second instruction processing unit is used for identifying and processing the alarm instruction.
  • a networking module is also included, the networking module is connected to the processing unit, and is used for uploading the data of the processing unit to the server.
  • a GPS module is also included, and the GPS module is connected to the processing unit.
  • the present application also provides a method for automatically detecting a driver playing with a mobile phone, including: a speed acquisition module detects the real-time driving speed of the vehicle and sends it to a data processing module, and the data processing module judges whether the real-time driving speed of the vehicle is greater than the first preset open Speed, when the real-time driving speed of the vehicle is greater than the first preset opening speed, the image acquisition module is controlled to start working; the image acquisition module collects the image data in the car and sends it to the data processing module, and the data processing module according to the The above image data detects whether the driver has the behavior of playing with the mobile phone, and when the behavior of playing with the mobile phone is detected, the alarm module is controlled to send an alarm.
  • the detecting the real-time driving speed of the vehicle includes detecting the real-time acceleration inside the vehicle, and calculating the integral of the real-time acceleration with respect to time to obtain the real-time driving speed of the vehicle.
  • the described detection of whether the driver has a mobile phone behavior according to the image data includes: inputting the obtained image data into the trained mobile phone image detection model for detection, obtaining the target detection result, and judging whether there is a mobile phone according to the target detection result Playing mobile phone behavior; wherein, the acquisition method of the trained mobile phone image detection model includes: collecting image data in different car interior environments, and obtaining an expanded image data set by flipping, mirroring, and cutting the image data, Then perform data preprocessing on the image data set, and then input the image data set to the ssd_mobilenet_v1 model for training to obtain a trained mobile phone image detection model.
  • a device for automatically detecting a driver playing with a mobile phone includes a speed acquisition module, an image acquisition module, a data processing module, an alarm module and a power supply module, which can analyze whether the driver is playing with a mobile phone according to the image data in the car and issue an alarm in time to remind driving It helps reduce the phenomenon of drivers playing with mobile phones while driving, thereby reducing traffic accidents, and obtains real-time driving speed through the speed acquisition module, and opens the image acquisition module according to the driving speed, which does not require the driver to manually open and close, avoiding driving If the operator forgets to turn it on, the whole process is automated and easy to use.
  • a method for automatically detecting a driver playing with a mobile phone in the present application has the same effect as the above-mentioned device, and details are not repeated here.
  • Fig. 1 is the functional block diagram of the device that automatically detects that the driver plays a mobile phone in the embodiment of the present application;
  • Fig. 2 is the functional block diagram of data processing module in the embodiment of the present application.
  • Fig. 3 is the functional block diagram of speed acquisition module in the embodiment of the present application.
  • FIG. 4 is a flowchart of a method for automatically detecting a driver playing with a mobile phone in an embodiment of the present application.
  • a kind of device of automatic detection driver's playing mobile phone comprises data processing module 100 and the speed acquisition module 300 that is connected with data processing module 100 respectively, image acquisition module 200, alarm module 400 and power supply module 500, speed acquisition
  • the module 300 is used to collect the real-time driving speed of the vehicle
  • the image collection module 200 is used to collect the image data inside the vehicle
  • the alarm module 400 is used to generate an alarm signal.
  • the data processing module 100 comprises a first communication unit 102, a second communication unit 103, a third communication unit 104, a processing unit 101, a first instruction generation unit 105 and a second instruction generation unit 106, the first communication unit 102 It is used to realize the data interaction between the processing unit 101 and the speed acquisition module 300, the second communication unit 103 is used to realize the data interaction between the processing unit 101 and the image acquisition module 200, and the third communication unit 104 is used to realize the processing unit 101 and the alarm module 400 data interaction, the processing unit 101 is used to judge whether to generate a detection instruction through the first instruction generation unit 105 and send it to the image acquisition module 200 through the second communication unit 103 according to the real-time driving speed of the vehicle, and according to the image data collected by the image acquisition module 200 Detect whether the driver has the behavior of playing with the mobile phone.
  • the second command generation unit 106 When the behavior of playing with the mobile phone is detected, the second command generation unit 106 is controlled to generate an alarm command and send it to the alarm module 400 through the third communication unit 104 .
  • the data processing module 100 is implemented using a Raspberry Pi development board.
  • the power supply module 500 adopts a lithium battery to provide working power for the speed acquisition module 300 , the image acquisition module 200 , the alarm module 400 and the data processing module 100 .
  • a device for automatically detecting a driver playing with a mobile phone in an embodiment of the present application adopts the mode of "one machine, one vehicle", and the device is installed on the driving seat of each motor vehicle.
  • the speed acquisition module 300 collects the real-time driving speed of the vehicle and sends it to the processing unit 101 through the first communication unit 102, and the processing unit 101 analyzes the real-time driving speed of the vehicle.
  • the first instruction generation unit 105 When the speed is greater than the preset opening speed, the first instruction generation unit 105 generates a detection instruction, and sends the detection instruction to the image acquisition module 200 through the second communication unit 103, and the image acquisition module 200 starts to collect image data in the car after receiving the detection instruction And the data is sent to the processing unit 101, and the processing unit 101 detects whether the driver has the behavior of playing with the mobile phone according to the image data.
  • the generation unit 106 generates an alarm command and sends it to the alarm module 400 through the third communication unit 104. After receiving the alarm command, the alarm module 400 sends out an alarm to warn the driver, so as to prevent the driver from being distracted by playing with the mobile phone and causing driving accidents.
  • the embodiment of the present application can analyze whether the driver is playing with the mobile phone according to the image data in the car and send an alarm in time to remind the driver, which helps to reduce the phenomenon of the driver playing with the mobile phone while driving, thereby reducing the occurrence of traffic accidents, and obtains real-time information through the speed acquisition module 300.
  • Driving speed the image acquisition module 200 is turned on according to the driving speed, which does not require the driver to manually turn it on and off, avoiding the situation that the driver forgets to turn it on. The whole process is automated and easy to use.
  • the speed acquisition module 300 includes an acceleration detection unit and a calculation unit connected to each other, the acceleration detection unit is used to detect the real-time acceleration of the vehicle, and the calculation unit is used to calculate the real-time driving speed of the vehicle according to the real-time acceleration.
  • Speed specifically, the acceleration detection unit uses the MPU6050 gyroscope sensor, and the 3-axis accelerometer of the MPU6050 gyroscope sensor is used to measure the moving acceleration of the car, and the calculation unit integrates the acceleration with respect to time to obtain the real-time driving speed of the vehicle.
  • the image acquisition module 200 includes an interconnected camera unit and a first instruction processing unit 101, the first instruction processing unit 101 is used to identify and process detection instructions, and the camera unit is used to acquire images inside the vehicle Data, specifically, the camera unit adopts a camera, and when the first command processing unit 101 receives the detection command, it controls the camera to start shooting to obtain image data inside the vehicle and transmits it to the processing unit 101 .
  • the alarm module 400 includes an interconnected alarm and a second command processing unit 101, the second command processing unit 101 is used to identify and process the alarm command, and the alarm is used to generate an alarm, when the second command After receiving the alarm instruction, the processing unit 101 controls the alarm to generate an alarm to remind the driver not to play with the mobile phone.
  • the alarm module 400 adopts a buzzer, an alarm lamp, a voice prompt device or other alarm devices.
  • a networking module and a GPS module are also included, and the networking module adopts a 4G module, a 3G module or a WIFI module, and the GPS module is used to locate vehicle position information, and the networking module and the GPS module are respectively connected to the processing unit 101,
  • the processing unit 101 detects that the driver is playing with the mobile phone, the current location information, the owner, the vehicle and other information are uploaded to the server through the networking module, and the situation of using the mobile phone is recorded. The driver of the mobile phone is punished and has achieved the purpose of punishment.
  • the embodiment of the present application also provides a method for automatically detecting that the driver is playing with a mobile phone, including the following steps: the speed acquisition module 300 detects the real-time driving speed of the vehicle and sends it to the data processing module 100, and the data processing module 100 judges the real-time driving speed of the vehicle.
  • the control image acquisition module 200 starts to work; the image acquisition module 200 collects the image data in the car and sends it to the data processing module 100 , the data processing module 100 detects whether the driver has the behavior of playing with the mobile phone according to the image data, and when the behavior of playing with the mobile phone is detected, the alarm module 400 is controlled to issue an alarm.
  • the detecting the real-time driving speed of the vehicle includes detecting the real-time acceleration inside the vehicle, and calculating the integral of the real-time acceleration with respect to time to obtain the real-time driving speed of the vehicle.
  • detecting whether the driver has a mobile phone behavior according to the image data includes: inputting the obtained image data into a trained mobile phone image detection model for detection, obtaining the target detection result, and judging whether to There is a behavior of playing with a mobile phone. For example, when the mobile phone target is detected in the image, it is judged that the driver has a mobile phone playing behavior; wherein, the acquisition method of the trained mobile phone image detection model includes: collecting image data in different car interior environments, and Increase the number of images by flipping, mirroring, and cropping the image data to obtain an expanded image dataset, and then perform data preprocessing on the image dataset. Data preprocessing includes Gaussian blurring and edge enhancement on the image.
  • SSD combines the regression idea in YOLO and the Anchor mechanism in Faster-RCNN, and uses the multi-scale regions of each position of the whole image for regression, which not only maintains the fast speed of YOLO, but also ensures that the window prediction is the same as Faster-RCNN of precision.
  • MobileNet_V1 uses depth-separable convolution instead of ordinary convolution, and uses width multipliers to reduce the amount of parameters, making it a convolutional neural network with a smaller volume and less computation, suitable for small vehicles with limited computing power equipment.
  • the recognition algorithm is the ssdlite_mobilenet_v3_small lightweight target detection network based on PaddlePaddle, and the paddle lite lightweight inference engine is deployed on the mobile terminal for function realization.
  • the disclosed system, device and method can be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components can be combined or integrated. to another system, or some features may be ignored, or not implemented.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.
  • a unit described as a separate component may or may not be physically separated, and a component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.
  • the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.
  • the technical solution of the present application is essentially or part of the contribution to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including several instructions for enabling a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (English full name: Read-Only Memory, English abbreviation: ROM), random access memory (English full name: Random Access Memory, English abbreviation: RAM), magnetic Various media that can store program codes such as discs or optical discs.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Mechanical Engineering (AREA)
  • Human Computer Interaction (AREA)
  • Transportation (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Telephone Function (AREA)

Abstract

本申请公开了一种自动检测驾驶员玩手机的装置及方法，自动检测驾驶员玩手机的装置包括速度采集模块、图像采集模块、数据处理模块和报警模块，能根据车内图像数据分析驾驶员是否玩手机并及时发出警报提醒驾驶员，有助于减少驾驶员开车时玩手机现象，从而减少交通事故发生，并且通过速度采集模块获取实时行驶速度，根据行驶速度开启图像采集模块，不需要驾驶员手动开启和关闭，避免了驾驶员忘记开启的情况，全过程自动化，使用方便。

Description

一种自动检测驾驶员玩手机的装置及方法 技术领域
本申请涉及交通安全技术领域，尤其涉及一种自动检测驾驶员玩手机的装置及方法。
 背景技术
近年来，随着交通运输行业的蓬勃发展，机动车的保有量和机动车驾驶员人数迅速增加，交通事故也越来越多。其中交通事故中由于驾驶员本身注意力不集中导致的占大多数。随着信息技术的快速发展，手机的使用越来越普遍，人对于手机的依赖程度越来越严重在实际场景中，由于玩手机造成的事故屡见不鲜。据公安部交管局统计，全国因开车在道路上玩手机引发的道路交通事故数量呈逐年上升。根据道路交通安全法实施条例的相关规定，驾驶机动车不得有拨打接听手持电话、观看电视等妨碍安全驾驶的行为。
 技术问题
目前，监督驾驶员玩手机的方法，主要是通过摄像头抓拍图像并分析驾驶员是否使用手机，其中摄像头需要驾驶员在开车前主动开启，而驾驶员由于习惯往往会忘记启动，导致监控装置无法工作，不能起到监督作用。
 技术解决方案
本申请实施例提供了一种自动检测驾驶员玩手机的装置及方法，能够在车辆启动后自动开启检测驾驶员是否玩手机并发出警报提醒。
有鉴于此，本申请提供了一种自动检测驾驶员玩手机的装置，包括：速度采集模块、图像采集模块、数据处理模块和报警模块；所述速度采集模块用于采集车辆实时行驶速度；所述图像采集模块用于采集车内的图像数据；所述报警模块用于产生报警信号；所述数据处理模块包括第一通信单元、第二通信单元、第三通信单元、处理单元、第一指令生成单元和第二指令生成单元，所述第一通信单元用于实现处理单元和所述速度采集模块的数据交互，所述第二通信单元用于实现处理单元和所述图像采集模块的数据交互，所述第三通信单元用于实现处理单元和所述报警模块的数据交互，所述处理单元用于根据所述车辆实时行驶速度判断是否通过第一指令生成单元生成检测指令并通过第二通信单元发送至所述图像采集模块，以及根据所述图像采集模块采集的图像数据检测驾驶员是否存在玩手机行为，当检测到玩手机行为时，控制所述第二指令生成单元生成报警指令并通过第三通信单元发送至所述报警模块。
可选地，所述速度采集模块包括相互连接的加速度检测单元和计算单元，所述加速度检测单元用于检测车辆的实时加速度，所述计算单元用于根据所述实时加速度计算车辆实时行驶速度。
可选地，所述加速度检测单元采用MPU6050陀螺仪传感器。
可选地，所述图像采集模块包括相互连接的摄像单元和第一指令处理单元，所述摄像单元用于获取车内的图像数据，所述第一指令处理单元用于识别和处理所述检测指令。
可选地，所述报警模块包括相互连接的报警器和第二指令处理单元，所述报警器用于发出警报，所述第二指令处理单元用于识别和处理所述报警指令。
可选地，还包括联网模块，所述联网模块和所述处理单元连接，用于上传所述处理单元的数据至服务器。
可选地，还包括GPS模块，所述GPS模块和所述处理单元连接。
本申请还提供了一种自动检测驾驶员玩手机的方法，包括：速度采集模块检测车辆实时行驶速度并发送至数据处理模块，数据处理模块判断所述车辆实时行驶速度是否大于第一预设开启速度，当所述车辆实时行驶速度大于第一预设开启速度时，控制图像采集模块开始工作；图像采集模块采集车内的图像数据并发送至所述数据处理模块，所述数据处理模块根据所述图像数据检测驾驶员是否存在玩手机行为，当检测到玩手机行为时，控制所述报警模块发出警报。
可选地，所述检测车辆实时行驶速度包括检测车内的实时加速度，计算所述实时加速度对时间的积分，获得车辆实时行驶速度。
可选地，所述根据所述图像数据检测驾驶员是否存在玩手机行为包括: 将获得的图像数据输入到训练好的手机图像检测模型进行检测，获取目标检测结果，根据目标检测结果判断是否存在玩手机行为；其中，所述训练好的手机图像检测模型的获取方法包括：在不同汽车内饰环境下采集图像数据，并通过对图像数据进行翻转、镜像、裁剪得到扩展后的图像数据集，然后对图像数据集进行数据预处理，再将图像数据集输入到ssd_mobilenet_v1模型进行训练获得训练好的手机图像检测模型。
 有益效果
从以上技术方案可以看出，本申请实施例具有以下优点：
本申请的一种自动检测驾驶员玩手机的装置包括速度采集模块、图像采集模块、数据处理模块、报警模块和供电模块，能根据车内图像数据分析驾驶员是否玩手机并及时发出警报提醒驾驶员，有助于减少驾驶员开车时玩手机现象，从而减少交通事故发生，并且通过速度采集模块获取实时行驶速度，根据行驶速度开启图像采集模块，不需要驾驶员手动开启和关闭，避免了驾驶员忘记开启的情况，全过程自动化，使用方便。
本申请的一种自动检测驾驶员玩手机的方法具有和上述装置一样的效果，在此不做赘述。
 附图说明
为了更清楚地表达说明本发明实施例的技术方案，下面将对实施例描述所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本申请实施例中自动检测驾驶员玩手机的装置的原理框图；
图2为本申请实施例中数据处理模块的原理框图；
图3为本申请实施例中速度采集模块的原理框图；
图4为本申请实施例中自动检测驾驶员玩手机的方法的流程图。
 本发明的最佳实施方式
为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
请参照图1，一种自动检测驾驶员玩手机的装置，包括数据处理模块100及分别和数据处理模块100连接的速度采集模块300、图像采集模块200、报警模块400和供电模块500，速度采集模块300用于采集车辆实时行驶速度，图像采集模块200用于采集车内的图像数据，报警模块400用于产生报警信号。参见图2，数据处理模块100包括第一通信单元102、第二通信单元103、第三通信单元104、处理单元101、第一指令生成单元105和第二指令生成单元106，第一通信单元102用于实现处理单元101和速度采集模块300的数据交互，第二通信单元103用于实现处理单元101和图像采集模块200的数据交互，第三通信单元104用于实现处理单元101和报警模块400的数据交互，处理单元101用于根据车辆实时行驶速度判断是否通过第一指令生成单元105生成检测指令并通过第二通信单元103发送至图像采集模块200，以及根据图像采集模块200采集的图像数据检测驾驶员是否存在玩手机行为，当检测到玩手机行为时，控制第二指令生成单元106生成报警指令并通过第三通信单元104发送至报警模块400。在本申请实施例中，数据处理模块100采用树莓派开发板实现。供电模块500采用锂电池，用于为速度采集模块300、图像采集模块200、报警模块400及数据处理模块100提供工作电源。
本申请实施例的一种自动检测驾驶员玩手机的装置采用“一机一车”的模式，在每一辆机动车的驾驶位上安装该装置。当机动车开启时，行驶速度逐渐增加，速度采集模块300采集车辆的实时行驶速度并通过第一通信单元102发送到处理单元101，处理单元101对车辆的实时行驶速度进行分析，当车辆实时行驶速度大于预设的开启速度时，第一指令生成单元105生成检测指令，并通过第二通信单元103将检测指令发送至图像采集模块200，图像采集模块200接收检测指令后开始采集车内图像数据并将数据发送至处理单元101，处理单元101根据图像数据检测驾驶员是否存在玩手机行为，当检测到图像数据中含有手机目标物时，判定为检测到玩手机行为，此时通过第二指令生成单元106生成报警指令并通过第三通信单元104发送至报警模块400，报警模块400接收报警指令后发出警报警示驾驶员，避免驾驶员玩手机分心从而导致驾驶事故。本申请实施例能根据车内图像数据分析驾驶员是否玩手机并及时发出警报提醒驾驶员，有助于减少驾驶员开车时玩手机现象，从而减少交通事故发生，并且通过速度采集模块300获取实时行驶速度，根据行驶速度开启图像采集模块200，不需要驾驶员手动开启和关闭，避免了驾驶员忘记开启的情况，全过程自动化，使用方便。
参见图3，在本申请的进一步实施例中，速度采集模块300包括相互连接的加速度检测单元和计算单元，加速度检测单元用于检测车辆的实时加速度，计算单元用于根据实时加速度计算车辆实时行驶速度，具体的，加速度检测单元采用MPU6050陀螺仪传感器，利用MPU6050陀螺仪传感器的3轴加速器测得汽车移动加速度，计算单元将加速度对时间的积分获得车辆实时行驶速度。
在本申请的进一步实施例中，图像采集模块200包括相互连接的摄像单元和第一指令处理单元101，第一指令处理单元101用于识别和处理检测指令，摄像单元用于获取车内的图像数据，具体的，摄像单元采用摄像机，当第一指令处理单元101接收到检测指令后控制摄像机开启拍摄获得车内图像数据并传输至处理单元101。
在本申请的进一步实施例中，报警模块400包括相互连接的报警器和第二指令处理单元101，第二指令处理单元101用于识别和处理报警指令，报警器用于产生警报，当第二指令处理单元101接收到报警指令后控制报警器产生警报提醒驾驶员别玩手机。具体的，报警模块400采用蜂鸣器、报警灯、语音提示装置或其他警示装置。
在本申请的进一步实施例中，还包括联网模块和GPS模块，联网模块采用4G模块、3G模块或者WIFI模块，GPS模块用于定位车辆位置信息，联网模块和GPS模块分别和处理单元101连接，当处理单元101检测到驾驶员玩手机时，通过联网模块把当前位置信息及车主、车辆等信息上传至服务器，记录玩手机情况，服务器链接交警系统，交通执法人员可通过服务器记录的信息对玩手机的驾驶员进行处罚已达到惩治的目的。
参见图4，本申请实施例还提供了一种自动检测驾驶员玩手机的方法， 包括以下步骤：速度采集模块300检测车辆实时行驶速度并发送至数据处理模块100，数据处理模块100判断车辆实时行驶速度是否大于第一预设开启速度，当车辆实时行驶速度大于第一预设开启速度时，控制图像采集模块200开始工作；图像采集模块200采集车内的图像数据并发送至数据处理模块100，数据处理模块100根据图像数据检测驾驶员是否存在玩手机行为，当检测到玩手机行为时，控制报警模块400发出警报。
在本申请的进一步实施例中，所述检测车辆实时行驶速度包括检测车内的实时加速度，计算所述实时加速度对时间的积分，获得车辆实时行驶速度。
在本申请的进一步实施例中，根据图像数据检测驾驶员是否存在玩手机行为包括: 将获得的图像数据输入到训练好的手机图像检测模型进行检测，获取目标检测结果，根据目标检测结果判断是否存在玩手机行为，如当检测到图像中含有手机目标物则判断驾驶员存在玩手机行为；其中，训练好的手机图像检测模型的获取方法包括：在不同汽车内饰环境下采集图像数据，并通过对图像数据进行翻转、镜像、裁剪增加图像数量，得到扩展后的图像数据集，然后对图像数据集进行数据预处理，数据预处理包括对图像进行高斯模糊、边缘增强等处理，由于车辆在行驶过程中会有车身颠簸、光线不足等情况，我们的拍摄出来的图像也可能存在着抖动、模糊等问题，极易使图像模糊不清，缺少相应目标的特征，降低了图像数据的质量，因此我们在训练前，对图像数据的预处理主要是高斯模糊、边缘增强等，使其在训练过程中能够学习到更复杂场景下的手机的特征，再将图像数据集输入到ssd_mobilenet_v1模型进行训练获得手机检测模型。SSD结合了YOLO中的回归思想和Faster-RCNN中的Anchor机制，使用全图的各个位置的多尺度区域进行回归，既保持了YOLO速度快的特性，也保证了窗口预测的跟Faster-RCNN一样的精准。MobileNet_V1使用深度可分离卷积代替普通的卷积，并使用宽度乘数减少参数量，使其成为一种体积较小、计算量较少的卷积神经网络，适用于算力有限的车载小型移动设备。具体的，识别算法为基于PaddlePaddle实现的ssdlite_mobilenet_v3_small轻量级目标检测网络，并使用paddle lite轻量化推理引擎部署在移动端进行功能实现。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
本申请的说明书及上述附图中的术语“第一”、“第二”、“第三”、“第四”等（如果存在）是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本申请的实施例例如能够以除了在这里图示或描述的那些以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备（可以是个人计算机，服务器，或者网络设备等）执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器（英文全称：Read-Only Memory，英文缩写：ROM）、随机存取存储器（英文全称：Random Access Memory，英文缩写：RAM）、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。

Claims (10)

  1. 一种自动检测驾驶员玩手机的装置，其特征在于，包括：
    速度采集模块、图像采集模块、数据处理模块和报警模块；
    所述速度采集模块用于采集车辆实时行驶速度；
    所述图像采集模块用于采集车内的图像数据；
    所述报警模块用于产生报警信号；
    所述数据处理模块包括第一通信单元、第二通信单元、第三通信单元、处理单元、第一指令生成单元和第二指令生成单元，所述第一通信单元用于实现处理单元和所述速度采集模块的数据交互，所述第二通信单元用于实现处理单元和所述图像采集模块的数据交互，所述第三通信单元用于实现处理单元和所述报警模块的数据交互，所述处理单元用于根据所述车辆实时行驶速度判断是否通过第一指令生成单元生成检测指令并通过第二通信单元发送至所述图像采集模块，以及根据所述图像采集模块采集的图像数据检测驾驶员是否存在玩手机行为，当检测到玩手机行为时，控制所述第二指令生成单元生成报警指令并通过第三通信单元发送至所述报警模块。
  2. 根据权利要求1所述的一种自动检测驾驶员玩手机的装置，其特征在于，所述速度采集模块包括相互连接的加速度检测单元和计算单元，所述加速度检测单元用于检测车辆的实时加速度，所述计算单元用于根据所述实时加速度计算车辆实时行驶速度。
  3. 根据权利要求2所述的一种自动检测驾驶员玩手机的装置，其特征在于，所述加速度检测单元采用MPU6050陀螺仪传感器。
  4. 根据权利要求1所述的一种自动检测驾驶员玩手机的装置，其特征在于，所述图像采集模块包括相互连接的摄像单元和第一指令处理单元，所述摄像单元用于获取车内的图像数据，所述第一指令处理单元用于识别和处理所述检测指令。
  5. 根据权利要求1所述的一种自动检测驾驶员玩手机的装置，其特征在于，所述报警模块包括相互连接的报警器和第二指令处理单元，所述报警器用于发出警报，所述第二指令处理单元用于识别和处理所述报警指令。
  6. 根据权利要求1所述的一种自动检测驾驶员玩手机的装置，其特征在于，还包括联网模块，所述联网模块和所述处理单元连接，用于上传所述处理单元的数据至服务器。
  7. 根据权利要求1所述的一种自动检测驾驶员玩手机的装置，其特征在于，还包括GPS模块，所述GPS模块和所述处理单元连接。
  8. 一种自动检测驾驶员玩手机的方法，其特征在于，包括：
    速度采集模块检测车辆实时行驶速度并发送至数据处理模块，数据处理模块判断所述车辆实时行驶速度是否大于第一预设开启速度，当所述车辆实时行驶速度大于第一预设开启速度时，控制图像采集模块开始工作；图像采集模块采集车内的图像数据并发送至所述数据处理模块，所述数据处理模块根据所述图像数据检测驾驶员是否存在玩手机行为，当检测到玩手机行为时，控制所述报警模块发出警报。
  9. 根据权利要求8所述的一种自动检测驾驶员玩手机的方法，其特征在于，所述检测车辆实时行驶速度包括检测车内的实时加速度，计算所述实时加速度对时间的积分，获得车辆实时行驶速度。
  10. 根据权利要求8所述的一种自动检测驾驶员玩手机的方法，其特征在于，所述根据所述图像数据检测驾驶员是否存在玩手机行为包括:
    将获得的图像数据输入到训练好的手机图像检测模型进行检测，获取目标检测结果，根据目标检测结果判断是否存在玩手机行为；其中，所述训练好的手机图像检测模型的获取方法包括：在不同汽车内饰环境下采集图像数据，并通过对图像数据进行翻转、镜像、裁剪得到扩展后的图像数据集，然后对图像数据集进行数据预处理，再将图像数据集输入到ssd_mobilenet_v1模型进行训练获得训练好的手机图像检测模型。
PCT/CN2021/094013 2021-05-17 2021-05-17 一种自动检测驾驶员玩手机的装置及方法 WO2022241598A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/094013 WO2022241598A1 (zh) 2021-05-17 2021-05-17 一种自动检测驾驶员玩手机的装置及方法

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/094013 WO2022241598A1 (zh) 2021-05-17 2021-05-17 一种自动检测驾驶员玩手机的装置及方法

Publications (1)

Publication Number Publication Date
WO2022241598A1 true WO2022241598A1 (zh) 2022-11-24

Family

ID=84140973

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/094013 WO2022241598A1 (zh) 2021-05-17 2021-05-17 一种自动检测驾驶员玩手机的装置及方法

Country Status (1)

Country Link
WO (1) WO2022241598A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160046298A1 (en) * 2014-08-18 2016-02-18 Trimble Navigation Limited Detection of driver behaviors using in-vehicle systems and methods
CN106651910A (zh) * 2016-11-17 2017-05-10 北京蓝天多维科技有限公司 驾驶员异常行为状态的智能图像分析方法和告警系统
EP3324378A1 (en) * 2016-11-16 2018-05-23 Ambrosetti, Sergio Aido Electronic safety system and method for detecting a vehicle driver's attention
CN110059541A (zh) * 2019-02-28 2019-07-26 长江大学 一种驾驶中的手机使用行为检测方法及装置
CN111860254A (zh) * 2020-07-10 2020-10-30 东莞正扬电子机械有限公司 一种驾驶员异常行为检测方法、装置、存储介质及设备
CN112141119A (zh) * 2020-09-23 2020-12-29 上海商汤临港智能科技有限公司 智能驾驶控制方法及装置、车辆、电子设备和存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160046298A1 (en) * 2014-08-18 2016-02-18 Trimble Navigation Limited Detection of driver behaviors using in-vehicle systems and methods
EP3324378A1 (en) * 2016-11-16 2018-05-23 Ambrosetti, Sergio Aido Electronic safety system and method for detecting a vehicle driver's attention
CN106651910A (zh) * 2016-11-17 2017-05-10 北京蓝天多维科技有限公司 驾驶员异常行为状态的智能图像分析方法和告警系统
CN110059541A (zh) * 2019-02-28 2019-07-26 长江大学 一种驾驶中的手机使用行为检测方法及装置
CN111860254A (zh) * 2020-07-10 2020-10-30 东莞正扬电子机械有限公司 一种驾驶员异常行为检测方法、装置、存储介质及设备
CN112141119A (zh) * 2020-09-23 2020-12-29 上海商汤临港智能科技有限公司 智能驾驶控制方法及装置、车辆、电子设备和存储介质

Similar Documents

Publication Publication Date Title
WO2021104476A1 (zh) 一种自动泊车控制方法及装置
CN107608388B (zh) 自主警车
CN110866427A (zh) 一种车辆行为检测方法及装置
WO2018046015A1 (zh) 车辆报警方法、装置及终端
CN103366506A (zh) 一种驾驶员行车途中接打手机行为的自动监控装置及方法
CN110765807A (zh) 驾驶行为分析、处理方法、装置、设备和存储介质
CN105243701A (zh) 一种行车信息上报方法及行车记录终端
KR102051136B1 (ko) 클라우드서버를 기반을 하는 인공지능 대쉬보드로봇을 이용한 사용자 상태인식시스템
CN112818839A (zh) 驾驶员违章行为识别方法、装置、设备及介质
CN114170585B (zh) 危险驾驶行为的识别方法、装置、电子设备及存储介质
CN109435844A (zh) 一种驾驶辅助及司机行为检测方法
CN111860210A (zh) 双手脱离方向盘检测方法、装置、电子设备和存储介质
CN109801475A (zh) 疲劳驾驶检测方法、装置及计算机可读存储介质
CN113486812A (zh) 一种骑行安全控制系统及控制方法
CN112966543B (zh) 一种车辆刮蹭记录方法及装置
CN113312958B (zh) 一种基于司机状态的派单优先度调整方法及装置
WO2022241598A1 (zh) 一种自动检测驾驶员玩手机的装置及方法
CN112330844A (zh) 一种增强型行车记录的方法及其系统
JP2004302902A (ja) 運転支援システム
CN117334047A (zh) 一种危险驾驶行为检测方法及装置
CN111862529A (zh) 报警方法及设备
KR20220014943A (ko) 주행 환경 연동 운전자 감정 판단 방법 및 시스템
CN113506436A (zh) 一种用于监管的检测车内驾驶员玩手机的系统及方法
CN114360267B (zh) 基于云端检测系统的车况检测方法、装置及云端检测系统
CN114241781B (zh) 一种基于车祸识别自动报警功能系统

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: 21940057

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21940057

Country of ref document: EP

Kind code of ref document: A1