WO2022078353A1 - 车辆行使状态判断方法、装置、计算机设备及存储介质 - Google Patents
车辆行使状态判断方法、装置、计算机设备及存储介质 Download PDFInfo
- Publication number
- WO2022078353A1 WO2022078353A1 PCT/CN2021/123413 CN2021123413W WO2022078353A1 WO 2022078353 A1 WO2022078353 A1 WO 2022078353A1 CN 2021123413 W CN2021123413 W CN 2021123413W WO 2022078353 A1 WO2022078353 A1 WO 2022078353A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- vehicle
- acceleration
- key frames
- key frame
- key
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 72
- 230000001133 acceleration Effects 0.000 claims abstract description 241
- 230000002159 abnormal effect Effects 0.000 claims abstract description 74
- 238000004458 analytical method Methods 0.000 claims abstract description 35
- 238000000605 extraction Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 9
- 238000006073 displacement reaction Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000013473 artificial intelligence Methods 0.000 abstract description 5
- 238000001514 detection method Methods 0.000 abstract description 4
- 206010039203 Road traffic accident Diseases 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 9
- 238000012545 processing Methods 0.000 description 5
- 230000005856 abnormality Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000010921 in-depth analysis Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- 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
-
- 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
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/63—Scene text, e.g. street names
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Definitions
- the present application relates to the technical field of image detection of artificial intelligence, and in particular, to a method, device, computer equipment and storage medium for judging the driving state of a vehicle, which use the computer vision technology of artificial intelligence.
- the timeliness is poor. For example, the time from the occurrence of a car accident to the successful report is precious rescue time and processing time; 2.
- the information is inaccurate, For example, a telephone report requires the police and the reporting party to repeatedly confirm the time and location information, and the case information provided by the reporting party is often inaccurate; 3. There are cases of false reports.
- the purpose of this application is to provide a method, device, computer equipment and storage medium for judging the driving state of a vehicle, which are used to solve the problems of poor timeliness, inaccurate information and false reporting of car accident reports in the prior art; this application can be applied to In smart traffic scenarios, to promote the construction of smart cities.
- the present application provides a method for judging the driving state of a vehicle, including:
- acceleration line is a discrete data fitting line formulated according to the acceleration of each key frame
- the present application also provides a vehicle driving state judging device, comprising:
- the speed calculation module is used to obtain the vehicle driving video and extract the consecutive key frames, calculate the driving speed of the vehicle according to the adjacent two key frames, and mark the vehicle information and driving speed of the vehicle in the two key frames. on the next keyframe of ;
- an acceleration calculation module configured to calculate the acceleration of the vehicle according to the vehicle speed of two adjacent key frames, and mark the acceleration on the next key frame of the two key frames;
- a line formulating module configured to perform discrete data fitting analysis on the acceleration of each key frame to obtain an acceleration line, where the acceleration line is a discrete data fitting line formulated according to the acceleration of each key frame;
- the state judgment state is used to judge whether the slope of the acceleration line is lower than the preset abnormal threshold; if it is lower than the abnormal threshold, it is determined that the driving state of the vehicle is abnormal; if it is not lower than the abnormal threshold, Then it is determined that the running state of the vehicle is normal.
- the present application also provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, which is implemented when the processor of the computer device executes the computer program.
- the above-mentioned method for judging the driving state of a vehicle includes:
- acceleration line is a discrete data fitting line formulated according to the acceleration of each key frame
- the present application also provides a computer storage medium, where a computer program is stored on the storage medium, and when the computer program stored in the storage medium is executed by a processor, the above-mentioned vehicle driving state judgment method is realized, and the The method of judging the driving state of the vehicle, including:
- acceleration line is a discrete data fitting line formulated according to the acceleration of each key frame
- the method, device, computer equipment and storage medium for judging the driving state of the vehicle provided by the present application, by calculating the driving speed of the vehicle, and obtaining the acceleration of the vehicle according to the vehicle speed of two adjacent key frames, and then for each key frame.
- the acceleration of the frame is subjected to discrete data fitting analysis to obtain the acceleration line, which realizes the control of the acceleration change generated by the vehicle information with the passage of the key frame, and realizes by judging whether the slope of the acceleration line is lower than the preset abnormal threshold.
- the determination of the driving state of the vehicle realizes the intelligent identification of the abnormal driving state of the vehicle, and solves the problems of poor timeliness, inaccurate information and false reporting of a car accident in the prior art.
- FIG. 1 is a flow chart of Embodiment 1 of the method for judging the driving state of a vehicle according to the application;
- FIG. 2 is a schematic diagram of the environmental application of the method for judging the driving state of a vehicle in Embodiment 2 of the method for judging the driving state of the vehicle;
- FIG. 3 is a specific method flow chart of the vehicle driving state judgment method in Embodiment 2 of the vehicle driving state judgment method of the present application;
- Embodiment 4 is a flowchart of a specific method for calculating the driving speed of a vehicle according to two adjacent key frames in Embodiment 2 of the method for judging the driving state of a vehicle of the present application, and marking the vehicle information and driving speed of the vehicle on the key frames;
- FIG. 5 is a flowchart of a specific method for calculating the acceleration of a vehicle according to the vehicle speed of two adjacent key frames in Embodiment 2 of the method for judging the driving state of a vehicle of the present application, and marking the acceleration on the key frames;
- FIG. 6 is a flowchart of a specific method for obtaining acceleration lines by performing discrete data fitting analysis on the acceleration of each key frame in Embodiment 2 of the vehicle driving state judgment method of the present application;
- FIG. 7 is a schematic diagram of a program module of Embodiment 3 of the apparatus for judging the driving state of a vehicle according to the application;
- FIG. 8 is a schematic diagram of a hardware structure of a computer device in Embodiment 4 of the computer device of the present application.
- the vehicle driving state judgment method, device, computer equipment and storage medium provided by this application are suitable for the field of artificial intelligence image detection technology, and provide a vehicle based on a speed calculation module, an acceleration calculation module, a line drawing module and a state judgment state. Use the state judgment method.
- the vehicle driving video is acquired and the consecutive key frames are extracted, the driving speed of the vehicle is calculated according to the adjacent two key frames, and the vehicle information and driving speed of the vehicle are marked in the latter one of the two key frames.
- the acceleration line is a discrete data fitting line formulated according to the acceleration of each key frame; judging whether the slope of the acceleration line is lower than a preset abnormal threshold; if it is lower than the abnormal threshold , then it is determined that the running state of the vehicle is abnormal; if it is not lower than the abnormal threshold, it is determined that the running state of the vehicle is normal.
- a method for judging the driving state of a vehicle in this embodiment includes:
- S102 Acquire the video of the vehicle driving and extract the consecutive key frames therein, calculate the driving speed of the vehicle according to the adjacent two key frames, and mark the vehicle information and driving speed of the vehicle on the next key frame of the two key frames on the frame.
- S103 Calculate the acceleration of the vehicle according to the vehicle speeds of the two adjacent key frames, and mark the acceleration on the next key frame of the two key frames.
- S104 Perform discrete data fitting analysis on the acceleration of each key frame to obtain an acceleration line, where the acceleration line is a discrete data fitting line formulated according to the acceleration of each key frame.
- S105 Determine whether the slope of the acceleration line is lower than a preset abnormal threshold; if it is lower than the abnormal threshold, determine that the driving state of the vehicle is abnormal; if it is not lower than the abnormal threshold, determine the The driving state of the vehicle is normal.
- the driving speed of the vehicle is calculated by extracting consecutive key frames in the vehicle driving video, and according to the relative displacement of the vehicle in two adjacent key frames, and the vehicle information of the vehicle and the vehicle information are calculated.
- the driving speed is marked on the next key frame of the two key frames, so as to obtain the speed of the running vehicle, so as to accurately obtain the effect of the acceleration of the vehicle;
- the acceleration of the vehicle is obtained by calculating the vehicle speed of the vehicle in two adjacent key frames, and the acceleration is marked on the next key frame of the two key frames, so as to obtain the acceleration of the running vehicle,
- normal such as: normal driving
- abnormal such as: rear-end collision, collision, etc.
- Acceleration lines are obtained by discrete data fitting analysis of the acceleration of each key frame, which can control the acceleration change of vehicle information with the passage of key frames, and then help to judge whether the driving state of the vehicle is normal or not. Effect;
- the determination of the driving state of the vehicle is realized, the driving state of the vehicle is determined according to the acceleration line, and the technical effect of intelligently identifying the driving state of the vehicle is realized; for example: a normal vehicle
- the maximum acceleration of the vehicle is 0.6g
- the maximum acceleration of the vehicle's sudden braking is -1g
- the acceleration line obtained by the least squares method will cause the slope of the acceleration line to decrease abruptly due to the sharply reduced acceleration.
- the technical effect of intelligently identifying vehicle anomalies is realized.
- the present application solves the problems of poor timeliness, inaccurate information, and false reports existing in the prior art by realizing intelligent identification of abnormal vehicle driving states.
- the present application can be applied in smart traffic scenarios, thereby promoting the construction of smart cities.
- Embodiment 2 is a diagrammatic representation of Embodiment 1:
- This embodiment is a specific application scenario of the above-mentioned Embodiment 1. Through this embodiment, the method provided in this application can be described more clearly and specifically.
- the acceleration of the vehicle is calculated for the vehicle speed of two adjacent key frames, and the acceleration line of each key frame is obtained by discrete data fitting analysis.
- the method provided by this embodiment is described in detail by taking the slope of the acceleration line as an example to determine the driving state of the vehicle. It should be noted that this embodiment is only exemplary, and does not limit the protection scope of the embodiment of this application.
- FIG. 2 schematically shows a schematic diagram of an environmental application of the method for judging the driving state of a vehicle according to the second embodiment of the present application.
- the authentication server 2 where the vehicle running state determination method is located is connected to the photographing device 4 through a network 3, the server 2 may provide services through one or more networks 3, and the network 3 may include various network devices, For example routers, switches, multiplexers, hubs, modems, bridges, repeaters, firewalls, proxy devices and/or the like.
- the network 3 may include physical links such as coaxial cable links, twisted pair cable links, fiber optic links, combinations thereof, and/or the like.
- the network 3 may include wireless links, such as cellular links, satellite links, Wi-Fi links and/or the like; the shooting device 4 is a video shooting system, such as a sky-eye system, CCTV and other computer equipment.
- FIG. 3 is a flowchart of a specific method of a method for judging a driving state of a vehicle provided by an embodiment of the present application, and the method specifically includes steps S201 to S205.
- S201 Establish a communication connection with a preset photographing device to acquire in real time the driving video of the vehicle photographed by the photographing device.
- the Sky Eye system can be used as the shooting device.
- the Sky Eye system is a kind of network video system, which usually refers to the IP surveillance system used for specific applications in the field of security monitoring and remote monitoring.
- IP network LAN/WAN/Internet
- the sky-eye system is used to shoot a driving video of a moving vehicle.
- S202 Acquire a video of the vehicle driving and extract consecutive key frames therein, calculate the driving speed of the vehicle according to two adjacent key frames, and mark the vehicle information and driving speed of the vehicle on the next key frame of the two key frames on the frame.
- the continuous key frames in the vehicle driving video are extracted, and the relative displacement of the vehicle in two adjacent key frames is calculated.
- the driving speed of the vehicle, and the vehicle information and driving speed of the vehicle are marked on the next key frame of the two key frames.
- this step passes The key frames are continuously extracted from the vehicle driving video according to the preset extraction interval and extraction quantity.
- the extraction interval and extraction quantity can be set as required. For example, if the extraction interval is 40ms and the extraction quantity is 1000, then 1000 key frames are extracted from the vehicle driving video at an interval of 40ms.
- the driving speed of the vehicle is calculated according to two adjacent key frames, and the vehicle information and driving speed of the vehicle are marked in the next key frame of the two key frames. steps above, including:
- S21 Identify vehicles appearing in each key frame, and mark the vehicle information of the vehicle on the key frame.
- the license plate of the vehicle that appears in each key is identified by the vehicle license plate recognition technology, so as to realize the purpose of identifying the vehicle that appears; The purpose of marking the vehicle.
- image vehicle recognition can be converted into image license plate recognition, and the acceleration of the vehicle motion trajectory is obtained through the acceleration of the license plate.
- vehicle license plate recognition There are many algorithms for vehicle license plate recognition, such as OCR technology. In this solution, the algorithm is only applied without in-depth analysis.
- S22 Calculate the traveling speed of each vehicle according to the relative displacement of the vehicle in two adjacent key frames.
- the relative displacement is obtained by measuring the position of the vehicle in the two key frames by a distance metric method, which is a mathematical law used to measure the distance along the curve and
- the angle between the curves includes the information of the curvature of the space where the curves are located; since the technical problem to be solved in this step is how to obtain the acceleration of the vehicle according to the speed of the vehicle, which is helpful to judge the driving state of the vehicle; therefore, the distance measurement The specific technical principle is not repeated here.
- S23 Mark the traveling speed in the next key frame of the two adjacent key frames, and associate the traveling speed with the vehicle information of the vehicle.
- S203 Calculate the acceleration of the vehicle according to the vehicle speeds of the two adjacent key frames, and mark the acceleration on the next key frame of the two key frames.
- the vehicle speed of the two key frames is used to obtain the acceleration of the vehicle, and the acceleration is marked on the next key frame of the two key frames.
- the acceleration of the vehicle is calculated according to the vehicle speed of two adjacent key frames, and the acceleration is marked on the next key frame of the two key frames, include:
- S32 Mark the acceleration in the next key frame of the two adjacent key frames, and associate the acceleration with the vehicle information.
- two adjacent key frames include key frame B and key frame C, wherein key frame C is located after key frame B; key frame B is marked with vehicle information: "Shanghai A* ****” , travel speed: 25m/s; key frame C is marked with vehicle information: "Shanghai A*****", travel speed: 24.9m/s; and the extraction interval is 40m/s, then the obtained acceleration is -2.5m /s2.
- S204 Perform discrete data fitting analysis on the acceleration of each key frame to obtain an acceleration line, where the acceleration line is a discrete data fitting line formulated according to the acceleration of each key frame.
- this step is performed by discrete data fitting of the acceleration of each key frame.
- the acceleration line is obtained by analysis; wherein, the discrete data fitting analysis is a representation method in which existing data is substituted into a mathematical formula through a mathematical method.
- the discrete data fitting analysis is a representation method in which existing data is substituted into a mathematical formula through a mathematical method.
- several discrete data can be obtained through methods such as sampling and experiments. According to these data, we often hope to obtain a continuous function (that is, a curve) or a denser discrete equation that is consistent with the known data. This process It's called fitting.
- the least squares method is used to linearly fit the acceleration of each key frame as discrete data, so as to perform discrete data fitting analysis on the acceleration of each key frame and obtain the acceleration line.
- the least squares method is a mathematical optimization technique that finds the best functional match for the data by minimizing the sum of squared errors.
- the unknown data can be easily obtained by the least squares method, and the sum of squares of the errors between the obtained data and the actual data can be minimized.
- the Matlab module implements the least squares method to perform discrete data fitting analysis on the acceleration of each key frame.
- the steps of performing discrete data fitting analysis on the acceleration of each key frame to obtain an acceleration line include:
- S42 Formulate discrete points of the vehicle information on the key frame according to the order of the key frame in the sequence and the acceleration of the key frame.
- any key frame in the continuous key frames is used as the target frame, the order of the target frame in the continuous key frames is used as the abscissa, and the acceleration of the target frame is used as the ordinate , to obtain discrete points of the vehicle information on the target frame.
- the obtained consecutive key frames include: key frame 1, key frame 2, key frame 3, key frame 4, and key frame 5;
- the method further includes:
- the corresponding summary information is obtained based on the acceleration lines.
- the summary information is obtained by hashing the acceleration lines, for example, by using the sha256s algorithm.
- Uploading summary information to the blockchain ensures its security and fairness and transparency to users.
- the user equipment can download the summary information from the blockchain to verify whether the acceleration line has been tampered with.
- the blockchain referred to in this example is a new application mode of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm.
- Blockchain essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information to verify its Validity of information (anti-counterfeiting) and generation of the next block.
- the blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.
- S205 Determine whether the slope of the acceleration line is lower than a preset abnormal threshold; if it is lower than the abnormal threshold, determine that the driving state of the vehicle is abnormal; if it is not lower than the abnormal threshold, determine the The driving state of the vehicle is normal.
- this step realizes the judgment of the driving state of the vehicle by judging whether the slope of the acceleration line is lower than the preset abnormal threshold; usually
- the maximum acceleration of the vehicle is 0.6g
- the maximum acceleration of the vehicle sudden braking is -1g
- the acceleration line obtained by the least squares method will cause the slope of the acceleration line to decrease abruptly due to the sharply reduced acceleration. Therefore, by comparing the slope with the preset abnormal threshold, it can be determined that Whether the vehicle has an abnormal situation such as collision or rear-end collision, it realizes the technical effect of intelligently identifying vehicle anomalies (collision, rear-end collision, etc.).
- a vehicle driving state judging device 1 of the present embodiment includes:
- the speed calculation module 12 is used for acquiring the vehicle driving video and extracting consecutive key frames therein, calculating the driving speed of the vehicle according to the adjacent two key frames, and marking the vehicle information and driving speed of the vehicle in the two key frames. on the next keyframe of the frame;
- the acceleration calculation module 13 is used to calculate the acceleration of the vehicle according to the vehicle speed of the two adjacent key frames, and mark the acceleration on the next key frame of the two key frames;
- the line formulating module 14 is used to perform discrete data fitting analysis on the acceleration of each key frame to obtain an acceleration line, and the acceleration line is a discrete data fitting line formulated according to the acceleration of each key frame;
- the state judgment state 15 is used to judge whether the slope of the acceleration line is lower than a preset abnormal threshold; if it is lower than the abnormal threshold, it is determined that the driving state of the vehicle is abnormal; if it is not lower than the abnormal threshold , then it is determined that the running state of the vehicle is normal.
- the vehicle driving state judging device 1 further includes:
- the communication connection module 11 is configured to establish a communication connection with a preset photographing device, so as to obtain the driving video of the vehicle photographed by the photographing device in real time.
- the technical solution relates to the technical field of artificial intelligence image detection.
- the distance measurement method in the image matching technology is used to obtain the vehicle driving video and extract the continuous key frames.
- the driving speed of the vehicle is calculated according to the adjacent two key frames.
- Calculate the acceleration of the vehicle from the vehicle speed of the two keyframes Discrete data fitting analysis is performed on the acceleration of each key frame to obtain an acceleration line, and it is determined whether the slope of the acceleration line is lower than a preset abnormal threshold; if it is lower than the abnormal threshold, it is determined that the driving state of the vehicle is abnormal.
- Embodiment 4 is a diagrammatic representation of Embodiment 4:
- the present application also provides a computer device 5.
- the components of the vehicle driving state judging device 1 of the third embodiment can be dispersed in different computer devices, and the computer device 5 can be a smart phone or a tablet computer that executes programs. , notebook computers, desktop computers, rack servers, blade servers, tower servers or rack servers (including independent servers, or server clusters composed of multiple application servers), etc.
- the computer device in this embodiment at least includes, but is not limited to, a memory 51 and a processor 52 that can be communicatively connected to each other through a system bus, as shown in FIG. 8 . It should be pointed out that FIG. 8 only shows a computer device having a component -, but it should be understood that it is not required to implement all the shown components, and more or less components may be implemented instead.
- the memory 51 (ie, the storage medium) includes flash memory, hard disk, multimedia card, card-type memory (eg, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Programmable Read-Only Memory (PROM), Magnetic Memory, Magnetic Disk, Optical Disc, etc.
- the memory 51 may be an internal storage unit of a computer device, such as a hard disk or a memory of the computer device.
- the memory 51 may also be an external storage device of a computer device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), Secure Digital (SD) card, Flash Card (Flash Card), etc.
- the memory 51 may also include both the internal storage unit of the computer device and its external storage device.
- the memory 51 is generally used to store the operating system and various application software installed on the computer equipment, such as the program code of the vehicle driving state judging device of the third embodiment.
- the memory 51 can also be used to temporarily store various types of data that have been output or will be output.
- the processor 52 may be a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments.
- the processor 52 is typically used to control the overall operation of the computer device.
- the processor 52 is used for running the program code or processing data stored in the memory 51 , for example, running the vehicle running state judging device, so as to realize the vehicle running state judging methods of the first and second embodiments.
- Embodiment 5 is a diagrammatic representation of Embodiment 5:
- the present application also provides a computer storage medium
- the computer-readable storage medium may be non-volatile or volatile, such as flash memory, hard disk, multimedia card, card-type storage (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), Magnetic storage, magnetic disk, optical disk, server, App application mall, etc., on which computer programs are stored, and when the programs are executed by the processor 52, corresponding functions are realized.
- the computer storage medium of this embodiment is used to store the vehicle running state judging device, and when executed by the processor 52, implements the vehicle running state judging methods of the first and second embodiments.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
一种车辆行使状态判断方法、装置、计算机设备及存储介质，涉及人工智能的图像检测技术领域。方法包括：获取车辆行驶视频并提取其中连续的关键帧，根据相邻的两个关键帧计算车辆的行驶速度（S102）；根据相邻的两个关键帧的车辆速度计算车辆的加速度（S103）；对各关键帧的加速度进行离散数据拟合分析得到加速度线条（S104）；判断加速度线条的斜率是否低于预设的异常阈值（S51）；若低于异常阈值，则判定车辆的行使状态为异常（S52）。还涉及区块链技术，信息可存储于区块链节点中。实现了智能识别车辆异常的行驶状态，解决了现有技术中存在的车祸报案时效性差、信息不准确以及虚假报案情况的发生。
Description
本申请要求于2020年10月14日递交的申请号为CN202011096024.3、名称为“车辆行使状态判断方法、装置、计算机设备及存储介质”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。
本申请涉及人工智能的图像检测技术领域，尤其涉及一种车辆行使状态判断方法、装置、计算机设备及存储介质，其使用到人工智能的计算机视觉技术。
目前国内重点道路、区域均已覆盖天眼***监控，拍摄记录了车流数据。但是此监控拍摄视频数据并没有用于自动判断是否有车祸发生，而是通过车祸当事方或者路人主动上报车祸警情。
然而，发明人意识到，通过当事方主动上报，会有多个方面的不足：1、时效性差，如车祸发生到成功报案的时间是宝贵的救援时间和处理时间；2、信息不准确，如电话报案需要警员和报案方反复确认时间、地点信息，报案方提供的案件信息往往不够精确；3、存在虚假报案的情况。
发明内容
本申请的目的是提供一种车辆行使状态判断方法、装置、计算机设备及存储介质，用于解决现有技术存在的车祸报案时效性差、信息不准确以及虚假报案情况的问题；本申请可应用于智慧交通场景中，从而推动智慧城市的建设。
为实现上述目的，本申请提供一种车辆行使状态判断方法，包括：
获取车辆行驶视频并提取其中连续的关键帧，根据相邻的两个关键帧计算车辆的行驶速度，将所述车辆的车辆信息和行驶速度标注在所述两个关键帧的后一关键帧上；
根据相邻的两个关键帧的车辆速度计算车辆的加速度，将所述加速度标注在所述两个关键帧的后一关键帧上；
对各关键帧的加速度进行离散数据拟合分析得到加速度线条，所述加速线条是根据所述各关键帧的加速度所制定的离散数据拟合线条；
判断所述加速度线条的斜率是否低于预设的异常阈值；若低于所述异常阈值，则判定所述车辆的行使状态为异常；若不低于所述异常阈值，则判定所述车辆的行驶状态为正常。
为实现上述目的，本申请还提供一种车辆行使状态判断装置，包括：
速度计算模块，用于获取车辆行驶视频并提取其中连续的关键帧，根据相邻的两个关键帧计算车辆的行驶速度，将所述车辆的车辆信息和行驶速度标注在所述两个关键帧的后一关键帧上；
加速度计算模块，用于根据相邻的两个关键帧的车辆速度计算车辆的加速度，将所述加速度标注在所述两个关键帧的后一关键帧上；
线条制定模块，用于对各关键帧的加速度进行离散数据拟合分析得到加速度线条，所述加速线条是根据所述各关键帧的加速度所制定的离散数据拟合线条；
状态判断状态，用于判断所述加速度线条的斜率是否低于预设的异常阈值；若低于所述异常阈值，则判定所述车辆的行使状态为异常；若不低于所述异常阈值，则判定所述车辆的行驶状态为正常。
为实现上述目的，本申请还提供一种计算机设备，其包括存储器、处理器以及存储在存储器上并可在处理器上运行的计算机程序，所述计算机设备的处理器执行所述计算机程序时实现上述车辆行使状态判断方法，所述车辆行使状态判断方法，包括：
获取车辆行驶视频并提取其中连续的关键帧，根据相邻的两个关键帧计算车辆的行驶速度，将所述车辆的车辆信息和行驶速度标注在所述两个关键帧的后一关键帧上；
根据相邻的两个关键帧的车辆速度计算车辆的加速度，将所述加速度标注在所述两个关键帧的后一关键帧上；
对各关键帧的加速度进行离散数据拟合分析得到加速度线条，所述加速线条是根据所述各关键帧的加速度所制定的离散数据拟合线条；
判断所述加速度线条的斜率是否低于预设的异常阈值；若低于所述异常阈值，则判定所述车辆的行使状态为异常；若不低于所述异常阈值，则判定所述车辆的行驶状态为正常。
为实现上述目的，本申请还提供一种计算机存储介质，所述存储介质上存储有计算机程序，所述存储介质存储的所述计算机程序被处理器执行时实现上述车辆行使状态判断方法，所述车辆行使状态判断方法，包括：
获取车辆行驶视频并提取其中连续的关键帧，根据相邻的两个关键帧计算车辆的行驶速度，将所述车辆的车辆信息和行驶速度标注在所述两个关键帧的后一关键帧上；
根据相邻的两个关键帧的车辆速度计算车辆的加速度，将所述加速度标注在所述两个关键帧的后一关键帧上；
对各关键帧的加速度进行离散数据拟合分析得到加速度线条，所述加速线条是根据所述各关键帧的加速度所制定的离散数据拟合线条；
判断所述加速度线条的斜率是否低于预设的异常阈值；若低于所述异常阈值，则判定所述车辆的行使状态为异常；若不低于所述异常阈值，则判定所述车辆的行驶状态为正常。
本申请提供的车辆行使状态判断方法、装置、计算机设备及存储介质，通过计算所述车辆的行驶速度，并根据相邻的两个关键帧的车辆速度得到所述车辆的加速度，再对各关键帧的加速度进行离散数据拟合分析得到加速度线条，实现对车辆信息随着关键帧的推移而产生的加速度变化进行把控，通过判断所述加速度线条的斜率是否低于预设的异常阈值来实现对车辆行驶状态的判定，实现智能识别车辆异常的行驶状态，解决了现有技术中存在的车祸报案时效性差、信息不准确以及虚假报案情况的发生。
图1为本申请车辆行使状态判断方法实施例一的流程图；
图2为本申请车辆行使状态判断方法实施例二中车辆行使状态判断方法的环境应用示意图；
图3是本申请车辆行使状态判断方法实施例二中车辆行使状态判断方法的具体方法流程图；
图4是本申请车辆行使状态判断方法实施例二中根据相邻的两个关键帧计算车辆的行驶速度，将所述车辆的车辆信息和行驶速度标注在关键帧上的具体方法流程图；
图5是本申请车辆行使状态判断方法实施例二中根据相邻的两个关键帧的车辆速度计算车辆的加速度，将所述加速度标注在关键帧上具体方法流程图；
图6是本申请车辆行使状态判断方法实施例二中对各关键帧的加速度进行离散数据拟合分析得到加速度线条具体方法流程图；
图7为本申请车辆行使状态判断装置实施例三的程序模块示意图；
图8为本申请计算机设备实施例四中计算机设备的硬件结构示意图。
具体实施方式
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本申请，并不用于限定本申请。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。
本申请提供的车辆行使状态判断方法、装置、计算机设备及存储介质，适用于人工智能的图像检测技术领域，为提供一种基于速度计算模块、加速度计算模块、线条制定模块和状态判断状态的车辆行使状态判断方法。本申请通过获取车辆行驶视频并提取其中连续的关键帧，根据相邻的两个关键帧计算车辆的行驶速度，将所述车辆的车辆信息和行驶速度标注在所述两个关键帧的后一关键帧上；根据相邻的两个关键帧的车辆速度计算车辆的加速度，将所述加速度标注在所述两个关键帧的后一关键帧上；对各关键帧的加速度进行离散数据拟合分析得到加速度线条，所述加速线条是根据所述各关键帧的加速度所制定的离散数据拟合线条；判断所述加速度线条的斜率是否低于预设的异常阈值；若低于所述异常阈值，则判定所述车辆的行使状态为异常；若不低于所述异常阈值，则判定所述车辆的行驶状态为正常。
实施例一：
请参阅图1，本实施例的一种车辆行使状态判断方法，包括：
S102：获取车辆行驶视频并提取其中连续的关键帧，根据相邻的两个关键帧计算车辆的行驶速度，将所述车辆的车辆信息和行驶速度标注在所述两个关键帧的后一关键帧上。
S103：根据相邻的两个关键帧的车辆速度计算车辆的加速度，将所述加速度标注在所述两个关键帧的后一关键帧上。
S104：对各关键帧的加速度进行离散数据拟合分析得到加速度线条，所述加速线条是根据所述各关键帧的加速度所制定的离散数据拟合线条。
S105：判断所述加速度线条的斜率是否低于预设的异常阈值；若低于所述异常阈值，则判定所述车辆的行使状态为异常；若不低于所述异常阈值，则判定所述车辆的行驶状态为正常。
在示例性的实施例中，通过提取车辆行驶视频中连续的关键帧，并根据车辆在相邻两个关键帧中的相对位移，计算所述车辆的行驶速度，并将该车辆的车辆信息和行驶速度标注在两个关键帧的后一关键帧上，以实现得到行驶中车辆的速度，以便于准确的获得所述车辆的加速度的效果；
通过计算车辆在相邻的两个关键帧的车辆速度得到所述车辆的加速度，并将所述加速度标注在所述两个关键帧的后一关键帧上，以实现得到行驶中车辆的加速度，以便于准确的把握所述车辆的行驶状态，即：正常（如：正常行驶）或异常（如：追尾、对撞等）的效果；
通过对各关键帧的加速度进行离散数据拟合分析得到加速度线条，实现对车辆信息随着关键帧的推移而产生的加速度变化进行把控，进而有助于判断该车辆的行驶状态是否正常的技术效果；
通过判断所述加速度线条的斜率是否低于预设的异常阈值来实现对车辆行驶状态的判定，实现根据加速度线条判定车辆的行驶状态，进而实现智能识别车辆行驶状态的技术效果；例如：通常车辆的最大加速度为0.6g，车辆急刹车的最大加速度为-1g，而车辆在发生对撞或追尾时，其加速度在20ms之内即可达到-30g，甚至-50g以下，因此，一旦出现对撞或追尾的情况时，采用最小二乘法得到的加速度线条将因出现的急剧降低的加速度，导致加速度线条的斜率陡然降低，因此，通过将所述斜率与预设的异常阈值，即可判断出车辆是否出现对撞或追尾等异常情况，实现了智能识别车辆异常（对撞、追尾等）的技术效果。
因此，本申请通过实现智能识别车辆异常的行驶状态，解决了现有技术中存在的车祸报案时效性差、信息不准确以及虚假报案情况的发生。
本申请可应用于智慧交通场景中，从而推动智慧城市的建设。
其中，所述S105图1中，以以下标注形式展现：
S51：判断所述加速度线条的斜率是否低于预设的异常阈值；
S52：若低于所述异常阈值，则判定所述车辆的行使状态为异常；
S53：若不低于所述异常阈值，则判定所述车辆的行驶状态为正常。
实施例二：
本实施例为上述实施例一的一种具体应用场景，通过本实施例，能够更加清楚、具体地阐述本申请所提供的方法。
下面，以在运行有车辆行使状态判断方法的服务器中，对相邻的两个关键帧的车辆速度计算车辆的加速度，并对各关键帧的加速度进行离散数据拟合分析得到加速度线条，通过所述加速度线条的斜率判断车辆的行使状态为例，来对本实施例提供的方法进行具体说明。需要说明的是，本实施例只是示例性的，并不限制本申请实施例所保护的范围。
图2示意性示出了根据本申请实施例二的车辆行使状态判断方法的环境应用示意图。
在示例性的实施例中，车辆行使状态判断方法所在的认证服务器2通过网络3连接拍摄设备4，所述服务器2可以通过一个或多个网络3提供服务，网络3可以包括各种网络设备，例如路由器，交换机，多路复用器，集线器，调制解调器，网桥，中继器，防火墙，代理设备和/或等等。网络3可以包括物理链路，例如同轴电缆链路，双绞线电缆链路，光纤链路，它们的组合和/或类似物。网络3可以包括无线链路，例如蜂窝链路，卫星链路，Wi-Fi链路和/或类似物；所述拍摄设备4为视频拍摄***，如天眼***、闭路电视等计算机设备。
图3是本申请一个实施例提供的一种车辆行使状态判断方法的具体方法流程图，该方法具体包括步骤S201至S205。
S201：与预设的拍摄设备建立通信连接，以实时获取拍摄设备拍摄所述车辆的行驶视频。
本步骤中，可使用天眼***作为拍摄设备，所述天眼***是一种网络视频***，其通常指的是安全监视和远程监控领域内用于特定应用的IP监视***，该***使用户能够通过IP网络（LAN/WAN/Internet）实现视频监控及视频图像的录像、以及相关的报警管理。于本实施例中，采用所述天眼***是对行驶的车辆拍摄行驶视频。
S202：获取车辆行驶视频并提取其中连续的关键帧，根据相邻的两个关键帧计算车辆的行驶速度，将所述车辆的车辆信息和行驶速度标注在所述两个关键帧的后一关键帧上。
为得到行驶中车辆的速度，以便于准确的获得所述车辆的加速度，本步骤通过提取车辆行驶视频中连续的关键帧，并根据车辆在相邻两个关键帧中的相对位移，计算所述车辆的行驶速度，并将该车辆的车辆信息和行驶速度标注在两个关键帧的后一关键帧上。
优选的，为保证服务器准确获得车辆在实际行驶中每一阶段的加速度，以便于准确把握车辆的行驶状态，同时避免因过于频繁的获得并计算关键帧导致服务器的运算负担过大，本步骤通过按照预设的提取间隔和提取数量从车辆行驶视频中连续的提取关键帧。
于本实施例中，所述提取间隔和提取数量可根据需要设置，例如，提取间隔为40ms，提取数量为1000，那么就按照40ms为间隔，从车辆行驶视频中提取1000个关键帧。
在一个优选的实施例中，请参阅图4，根据相邻的两个关键帧计算车辆的行驶速度，将所述车辆的车辆信息和行驶速度标注在所述两个关键帧的后一关键帧上的步骤，包括：
S21：识别各关键帧中出现的车辆，并将所述车辆的车辆信息标注在所述关键帧上。
本步骤中，通过车辆牌照识别技术识别各关键中出现车辆的车牌，以实现识别出现的车辆的目的；将所述车牌作为所述车辆信息标注在所述关键帧上，以实现在关键帧中标注车辆的目的。
需要说明的是，图像车辆识别可以转化为图像的车牌识别，通过车牌的加速度来得到车辆运动轨迹的加速度。车辆牌照识别的算法有多种，例如OCR技术，此方案中该算法只是应用，不做深入解析。
S22：根据车辆在相邻的两个关键帧中的相对位移计算各车辆的行驶速度。
本步骤中，根据所述车牌在相邻的两个关键帧中的相对位移及所述提取间隔，计算所述车牌在所述相邻的两个关键帧之间的行驶速度，并将其设为所述车辆的行驶速度。
示例性地，若车牌“沪A*****”在两个关键帧的相对位移为1m提取间隔为40ms,那么得到的行驶速度为1m/40ms=25m/s=90km/h。
需要说明的是，所述相对位移是通过距离度量方法测量两个关键帧中的车辆的位置所获得的，所述距离度量是数学中的法则，用在某些空间中测量沿曲线的距离和曲线间的角度，包含曲线所在空间的曲率的信息；由于本步骤所要解决的技术问题是，如何根据车辆的速度得到车辆的加速度，进而有助于判断车辆的行驶状态；因此，关于距离度量的具体技术原理在此不做赘述。
S23：将所述行驶速度标注在所述相邻的两个关键帧的后一关键帧中，将所述行驶速度及其车辆的车辆信息关联。
示例性地，基于上述举例，假设相邻的两个关键帧包括关键帧A，关键帧B，其中，关键帧B位于所述关键帧A之后，那么，将车辆信息：“沪A*****” ，行驶速度：25m/s、90km/h标注在关键帧B上。
S203：根据相邻的两个关键帧的车辆速度计算车辆的加速度，将所述加速度标注在所述两个关键帧的后一关键帧上。
为得到行驶中车辆的加速度，以便于准确的把握所述车辆的行驶状态，即：正常（如：正常行驶）或异常（如：追尾、对撞等），本步骤通过计算车辆在相邻的两个关键帧的车辆速度得到所述车辆的加速度，并将所述加速度标注在所述两个关键帧的后一关键帧上。
在一个优选的实施例中，请参阅图5，根据相邻的两个关键帧的车辆速度计算车辆的加速度，将所述加速度标注在所述两个关键帧的后一关键帧上的步骤，包括：
S31：提取相邻两个关键帧中同一车辆信息的行驶速度，计算所述两个关键帧的行驶速度得到加速度。
S32：将所述加速度标注在所述相邻的两个关键帧的后一关键帧中，并将所述加速度与所述车辆信息关联。
示例性地，基于上述举例，假设相邻的两个关键帧包括关键帧B和关键帧C，其中，关键帧C位于所述关键帧B之后；关键帧B标注有车辆信息：“沪A*****”
，行驶速度：25m/s；关键帧C标注有车辆信息：“沪A*****” ，行驶速度：24.9m/s；而提取间隔为40m/s，那么得到的加速度为-2.5m/s2。
S204：对各关键帧的加速度进行离散数据拟合分析得到加速度线条，所述加速线条是根据所述各关键帧的加速度所制定的离散数据拟合线条。
为实现对车辆信息随着关键帧的推移而产生的加速度变化进行把控，进而有助于判断该车辆的行驶状态是否正常的技术效果，本步骤通过对各关键帧的加速度进行离散数据拟合分析得到加速度线条；其中，所述离散数据拟合分析是一种把现有数据透过数学方法来代入一条数式的表示方式。科学和工程问题可以通过诸如采样、实验等方法获得若干离散的数据，根据这些数据，我们往往希望得到一个连续的函数（也就是曲线）或者更加密集的离散方程与已知数据相吻合，这过程就叫做拟合(fitting)。
于本实施例中，采用最小二乘法对作为离散数据的各关键帧的加速度进行线性拟合，以实现对各所述关键帧的加速度进行离散数据拟合分析并获得所述加速度线条。
需要说明的是，最小二乘法是一种数学优化技术，它通过最小化误差的平方和寻找数据的最佳函数匹配。利用最小二乘法可以简便地求得未知的数据，并使得这些求得的数据与实际数据之间误差的平方和为最小。于本实施例中，Matlab模块实现采用最小二乘法对各关键帧的加速度进行离散数据拟合分析。
在一个优选的实施例中，请参阅图6，对各关键帧的加速度进行离散数据拟合分析得到加速度线条的步骤，包括：
S41：按照所述连续的关键帧的顺序，依次提取各所述关键帧中同一车辆信息的加速度。
S42：根据关键帧在所述顺序中的位次及所述关键帧的加速度，制定所述车辆信息在所述关键帧上的离散点。
本步骤中，将所述连续的关键帧中任一关键帧作为目标帧，以所述目标帧在所述连续的关键帧中的位次作为横坐标，以所述目标帧的加速度作为纵坐标，得到所述车辆信息在所述目标帧上的离散点。
S43：采用最小二乘法计算所述车辆信息的在各关键帧上的离散点得到加速度线条，所述加速度线条拟合了车辆信息随着关键帧的推移而产生的加速度变化。
示例性地，假设获得到的连续的关键帧包括：关键帧1、关键帧2、关键帧3、关键帧4、关键帧5；
提取各关键帧中同一车辆信息，如：沪A*****，的加速度分别为：关键帧1，加速度：-2.5m/s2；关键帧2，加速度：-2.1m/s2；关键帧3，加速度：-1.4m/s2；关键帧4，加速度：-1m/s2；关键帧5，加速度：-0.6m/s2；那么根据最小二乘法，将得到y=0.5x-3的加速度线条。
优选的，对各关键帧的加速度进行离散数据拟合分析得到加速度线条之后，还包括：
将所述加速度线条上传至区块链中。
需要说明的是，基于加速度线条得到对应的摘要信息，具体来说，摘要信息由加速度线条进行散列处理得到，比如利用sha256s算法处理得到。将摘要信息上传至区块链可保证其安全性和对用户的公正透明性。用户设备可以从区块链中下载得该摘要信息，以便查证加速度线条是否被篡改。本示例所指区块链是分布式数据存储、点对点传输、共识机制、加密算法等计算机技术的新型应用模式。区块链(Blockchain)，本质上是一个去中心化的数据库，是一串使用密码学方法相关联产生的数据块，每一个数据块中包含了一批次网络交易的信息，用于验证其信息的有效性(防伪)和生成下一个区块。区块链可以包括区块链底层平台、平台产品服务层以及应用服务层等。
S205：判断所述加速度线条的斜率是否低于预设的异常阈值；若低于所述异常阈值，则判定所述车辆的行使状态为异常；若不低于所述异常阈值，则判定所述车辆的行驶状态为正常。
为实现根据加速度线条判定车辆的行驶状态，进而实现智能识别车辆行驶状态的技术效果，本步骤通过判断所述加速度线条的斜率是否低于预设的异常阈值来实现对车辆行驶状态的判定；通常车辆的最大加速度为0.6g，车辆急刹车的最大加速度为-1g，而车辆在发生对撞或追尾时，其加速度在20ms之内即可达到-30g，甚至-50g以下，因此，一旦出现对撞或追尾的情况时，采用最小二乘法得到的加速度线条将因出现的急剧降低的加速度，导致加速度线条的斜率陡然降低，因此，通过将所述斜率与预设的异常阈值，即可判断出车辆是否出现对撞或追尾等异常情况，实现了智能识别车辆异常（对撞、追尾等）的技术效果。
其中，所述S205图3中，以以下标注形式展现：
S51：判断所述加速度线条的斜率是否低于预设的异常阈值；
S52：若低于所述异常阈值，则判定所述车辆的行使状态为异常；
S53：若不低于所述异常阈值，则判定所述车辆的行驶状态为正常。
示例性地，基于上述举例，得到的将得到y=0.5x-3的加速度线条，其斜率为0.5；若所述异常阈值为-5，则判定该加速度线条的斜率不低于异常阈值，进而判定所述车辆的行驶状态为正常；如果得到的加速度线条为y=-10x-6（一旦发生追尾或对碰时，因加速度的陡然下降，会导致加速度线条的斜率骤然降低），若所述异常阈值仍为-5，则判定该加速线条的斜率低于异常阈值，进而判定所述车辆的行驶状态为异常。
实施例三：
请参阅图7，本实施例的一种车辆行使状态判断装置1，包括：
速度计算模块12，用于获取车辆行驶视频并提取其中连续的关键帧，根据相邻的两个关键帧计算车辆的行驶速度，将所述车辆的车辆信息和行驶速度标注在所述两个关键帧的后一关键帧上；
加速度计算模块13，用于根据相邻的两个关键帧的车辆速度计算车辆的加速度，将所述加速度标注在所述两个关键帧的后一关键帧上；
线条制定模块14，用于对各关键帧的加速度进行离散数据拟合分析得到加速度线条，所述加速线条是根据所述各关键帧的加速度所制定的离散数据拟合线条；
状态判断状态15，用于判断所述加速度线条的斜率是否低于预设的异常阈值；若低于所述异常阈值，则判定所述车辆的行使状态为异常；若不低于所述异常阈值，则判定所述车辆的行驶状态为正常。
可选的，所述车辆行使状态判断装置1还包括：
通信连接模块11，用于与预设的拍摄设备建立通信连接，以实时获取拍摄设备拍摄所述车辆的行驶视频。
本技术方案涉及人工智能的图像检测技术领域，通过图像匹配技术中的距离度量方法获取车辆行驶视频并提取其中连续的关键帧，根据相邻的两个关键帧计算车辆的行驶速度，根据相邻的两个关键帧的车辆速度计算车辆的加速度，
对各关键帧的加速度进行离散数据拟合分析得到加速度线条， 判断加速度线条的斜率是否低于预设的异常阈值；若低于异常阈值，则判定车辆的行使状态为异常。
实施例四：
为实现上述目的，本申请还提供一种计算机设备5，实施例三的车辆行使状态判断装置1的组成部分可分散于不同的计算机设备中，计算机设备5可以是执行程序的智能手机、平板电脑、笔记本电脑、台式计算机、机架式服务器、刀片式服务器、塔式服务器或机柜式服务器（包括独立的服务器，或者多个应用服务器所组成的服务器集群）等。本实施例的计算机设备至少包括但不限于：可通过***总线相互通信连接的存储器51、处理器52，如图8所示。需要指出的是，图8仅示出了具有组件-的计算机设备，但是应理解的是，并不要求实施所有示出的组件，可以替代的实施更多或者更少的组件。
本实施例中，存储器51（即存储介质）包括闪存、硬盘、多媒体卡、卡型存储器（例如，SD或DX存储器等）、随机访问存储器（RAM）、静态随机访问存储器（SRAM）、只读存储器（ROM）、电可擦除可编程只读存储器（EEPROM）、可编程只读存储器（PROM）、磁性存储器、磁盘、光盘等。在一些实施例中，存储器51可以是计算机设备的内部存储单元，例如该计算机设备的硬盘或内存。在另一些实施例中，存储器51也可以是计算机设备的外部存储设备，例如该计算机设备上配备的插接式硬盘，智能存储卡（Smart
Media Card, SMC），安全数字（Secure Digital, SD）卡，闪存卡（Flash Card）等。当然，存储器51还可以既包括计算机设备的内部存储单元也包括其外部存储设备。本实施例中，存储器51通常用于存储安装于计算机设备的操作***和各类应用软件，例如实施例三的车辆行使状态判断装置的程序代码等。此外，存储器51还可以用于暂时地存储已经输出或者将要输出的各类数据。
处理器52在一些实施例中可以是中央处理器（Central Processing Unit，CPU）、控制器、微控制器、微处理器、或其他数据处理芯片。该处理器52通常用于控制计算机设备的总体操作。本实施例中，处理器52用于运行存储器51中存储的程序代码或者处理数据，例如运行车辆行使状态判断装置，以实现实施例一和实施例二的车辆行使状态判断方法。
实施例五：
为实现上述目的，本申请还提供一种计算机存储介质，所述计算机可读存储介质可以是非易失性，也可以是易失性，如闪存、硬盘、多媒体卡、卡型存储器（例如，SD或DX存储器等）、随机访问存储器（RAM）、静态随机访问存储器（SRAM）、只读存储器（ROM）、电可擦除可编程只读存储器（EEPROM）、可编程只读存储器（PROM）、磁性存储器、磁盘、光盘、服务器、App应用商城等等，其上存储有计算机程序，程序被处理器52执行时实现相应功能。本实施例的计算机存储介质用于存储车辆行使状态判断装置，被处理器52执行时实现实施例一和实施例二的车辆行使状态判断方法。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。
以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。
Claims (20)
- 一种车辆行使状态判断方法，其中，包括：获取车辆行驶视频并提取其中连续的关键帧，根据相邻的两个关键帧计算车辆的行驶速度，将所述车辆的车辆信息和行驶速度标注在所述两个关键帧的后一关键帧上；根据相邻的两个关键帧的车辆速度计算车辆的加速度，将所述加速度标注在所述两个关键帧的后一关键帧上；对各关键帧的加速度进行离散数据拟合分析得到加速度线条，所述加速线条是根据所述各关键帧的加速度所制定的离散数据拟合线条；判断所述加速度线条的斜率是否低于预设的异常阈值；若低于所述异常阈值，则判定所述车辆的行使状态为异常；若不低于所述异常阈值，则判定所述车辆的行驶状态为正常。
- 根据权利要求1所述的车辆行使状态判断方法，其中，获取车辆行驶视频之前包括：与预设的拍摄设备建立通信连接，以实时获取拍摄设备拍摄所述车辆的行驶视频。
- 根据权利要求1所述的车辆行使状态判断方法，其中，获取车辆行驶视频并提取其中连续的关键帧包括：按照预设的提取间隔和提取数量从车辆行驶视频中连续的提取关键帧。
- 根据权利要求1所述的车辆行使状态判断方法，其中，根据相邻的两个关键帧计算车辆的行驶速度，将所述车辆的车辆信息和行驶速度标注在所述两个关键帧的后一关键帧上的步骤，包括：识别各关键帧中出现的车辆，并将所述车辆的车辆信息标注在所述关键帧上；根据车辆在相邻的两个关键帧中的相对位移计算各车辆的行驶速度；将所述行驶速度标注在所述相邻的两个关键帧的后一关键帧中，将所述行驶速度及其车辆的车辆信息关联。
- 根据权利要求1所述的车辆行使状态判断方法，其中，根据相邻的两个关键帧的车辆速度计算车辆的加速度，将所述加速度标注在所述两个关键帧的后一关键帧上的步骤，包括：提取相邻两个关键帧中同一车辆信息的行驶速度，计算所述两个关键帧的行驶速度得到加速度；将所述加速度标注在所述相邻的两个关键帧的后一关键帧中，并将所述加速度与所述车辆信息关联。
- 根据权利要求1所述的车辆行使状态判断方法，其中，对各关键帧的加速度进行离散数据拟合分析得到加速度线条包括：采用最小二乘法对作为离散数据的各关键帧的加速度进行线性拟合，以实现对各所述关键帧的加速度进行离散数据拟合分析并获得所述加速度线条。
- 根据权利要求1所述的车辆行使状态判断方法，其中，对各关键帧的加速度进行离散数据拟合分析得到加速度线条的步骤，包括：按照所述连续的关键帧的顺序，依次提取各所述关键帧中同一车辆信息的加速度；根据关键帧在所述顺序中的位次及所述关键帧的加速度，制定所述车辆信息在所述关键帧上的离散点；采用最小二乘法计算所述车辆信息的在各关键帧上的离散点得到加速度线条，所述加速度线条拟合了车辆信息随着关键帧的推移而产生的加速度变化；对各关键帧的加速度进行离散数据拟合分析得到加速度线条之后，还包括：将所述加速度线条上传至区块链中。
- 一种车辆行使状态判断装置，其中，包括：速度计算模块，用于获取车辆行驶视频并提取其中连续的关键帧，根据相邻的两个关键帧计算车辆的行驶速度，将所述车辆的车辆信息和行驶速度标注在所述两个关键帧的后一关键帧上；加速度计算模块，用于根据相邻的两个关键帧的车辆速度计算车辆的加速度，将所述加速度标注在所述两个关键帧的后一关键帧上；线条制定模块，用于对各关键帧的加速度进行离散数据拟合分析得到加速度线条，所述加速线条是根据所述各关键帧的加速度所制定的离散数据拟合线条；状态判断状态，用于判断所述加速度线条的斜率是否低于预设的异常阈值；若低于所述异常阈值，则判定所述车辆的行使状态为异常；若不低于所述异常阈值，则判定所述车辆的行驶状态为正常。
- 一种计算机设备，其包括存储器、处理器以及存储在存储器上并可在处理器上运行的计算机程序，其中，所述计算机设备的处理器执行所述计算机程序时实现所述车辆行使状态判断方法，所述车辆行使状态判断方法的步骤，包括：获取车辆行驶视频并提取其中连续的关键帧，根据相邻的两个关键帧计算车辆的行驶速度，将所述车辆的车辆信息和行驶速度标注在所述两个关键帧的后一关键帧上；根据相邻的两个关键帧的车辆速度计算车辆的加速度，将所述加速度标注在所述两个关键帧的后一关键帧上；对各关键帧的加速度进行离散数据拟合分析得到加速度线条，所述加速线条是根据所述各关键帧的加速度所制定的离散数据拟合线条；判断所述加速度线条的斜率是否低于预设的异常阈值；若低于所述异常阈值，则判定所述车辆的行使状态为异常；若不低于所述异常阈值，则判定所述车辆的行驶状态为正常。
- 根据权利要求9所述的计算机设备，其中，获取车辆行驶视频之前包括：与预设的拍摄设备建立通信连接，以实时获取拍摄设备拍摄所述车辆的行驶视频；获取车辆行驶视频并提取其中连续的关键帧包括：按照预设的提取间隔和提取数量从车辆行驶视频中连续的提取关键帧。
- 根据权利要求9所述的计算机设备，其中，根据相邻的两个关键帧计算车辆的行驶速度，将所述车辆的车辆信息和行驶速度标注在所述两个关键帧的后一关键帧上的步骤，包括：识别各关键帧中出现的车辆，并将所述车辆的车辆信息标注在所述关键帧上；根据车辆在相邻的两个关键帧中的相对位移计算各车辆的行驶速度；将所述行驶速度标注在所述相邻的两个关键帧的后一关键帧中，将所述行驶速度及其车辆的车辆信息关联。
- 根据权利要求9所述的计算机设备，其中，根据相邻的两个关键帧的车辆速度计算车辆的加速度，将所述加速度标注在所述两个关键帧的后一关键帧上的步骤，包括：提取相邻两个关键帧中同一车辆信息的行驶速度，计算所述两个关键帧的行驶速度得到加速度；将所述加速度标注在所述相邻的两个关键帧的后一关键帧中，并将所述加速度与所述车辆信息关联。
- 根据权利要求9所述的计算机设备，其中，对各关键帧的加速度进行离散数据拟合分析得到加速度线条包括：采用最小二乘法对作为离散数据的各关键帧的加速度进行线性拟合，以实现对各所述关键帧的加速度进行离散数据拟合分析并获得所述加速度线条。
- 根据权利要求9所述的计算机设备，其中，对各关键帧的加速度进行离散数据拟合分析得到加速度线条的步骤，包括：按照所述连续的关键帧的顺序，依次提取各所述关键帧中同一车辆信息的加速度；根据关键帧在所述顺序中的位次及所述关键帧的加速度，制定所述车辆信息在所述关键帧上的离散点；采用最小二乘法计算所述车辆信息的在各关键帧上的离散点得到加速度线条，所述加速度线条拟合了车辆信息随着关键帧的推移而产生的加速度变化；对各关键帧的加速度进行离散数据拟合分析得到加速度线条之后，还包括：将所述加速度线条上传至区块链中。
- 一种计算机存储介质，所述存储介质上存储有计算机程序，其中，所述存储介质存储的所述计算机程序被处理器执行时实现所述车辆行使状态判断方法，所述车辆行使状态判断方法的步骤，包括：获取车辆行驶视频并提取其中连续的关键帧，根据相邻的两个关键帧计算车辆的行驶速度，将所述车辆的车辆信息和行驶速度标注在所述两个关键帧的后一关键帧上；根据相邻的两个关键帧的车辆速度计算车辆的加速度，将所述加速度标注在所述两个关键帧的后一关键帧上；对各关键帧的加速度进行离散数据拟合分析得到加速度线条，所述加速线条是根据所述各关键帧的加速度所制定的离散数据拟合线条；判断所述加速度线条的斜率是否低于预设的异常阈值；若低于所述异常阈值，则判定所述车辆的行使状态为异常；若不低于所述异常阈值，则判定所述车辆的行驶状态为正常。
- 根据权利要求15所述的计算机存储介质，其中，获取车辆行驶视频之前包括：与预设的拍摄设备建立通信连接，以实时获取拍摄设备拍摄所述车辆的行驶视频；获取车辆行驶视频并提取其中连续的关键帧包括：按照预设的提取间隔和提取数量从车辆行驶视频中连续的提取关键帧。
- 根据权利要求15所述的计算机存储介质，其中，根据相邻的两个关键帧计算车辆的行驶速度，将所述车辆的车辆信息和行驶速度标注在所述两个关键帧的后一关键帧上的步骤，包括：识别各关键帧中出现的车辆，并将所述车辆的车辆信息标注在所述关键帧上；根据车辆在相邻的两个关键帧中的相对位移计算各车辆的行驶速度；将所述行驶速度标注在所述相邻的两个关键帧的后一关键帧中，将所述行驶速度及其车辆的车辆信息关联。
- 根据权利要求15所述的计算机存储介质，其中，根据相邻的两个关键帧的车辆速度计算车辆的加速度，将所述加速度标注在所述两个关键帧的后一关键帧上的步骤，包括：提取相邻两个关键帧中同一车辆信息的行驶速度，计算所述两个关键帧的行驶速度得到加速度；将所述加速度标注在所述相邻的两个关键帧的后一关键帧中，并将所述加速度与所述车辆信息关联。
- 根据权利要求15所述的计算机存储介质，其中，对各关键帧的加速度进行离散数据拟合分析得到加速度线条包括：采用最小二乘法对作为离散数据的各关键帧的加速度进行线性拟合，以实现对各所述关键帧的加速度进行离散数据拟合分析并获得所述加速度线条。
- 根据权利要求15所述的计算机存储介质，其中，对各关键帧的加速度进行离散数据拟合分析得到加速度线条的步骤，包括：按照所述连续的关键帧的顺序，依次提取各所述关键帧中同一车辆信息的加速度；根据关键帧在所述顺序中的位次及所述关键帧的加速度，制定所述车辆信息在所述关键帧上的离散点；采用最小二乘法计算所述车辆信息的在各关键帧上的离散点得到加速度线条，所述加速度线条拟合了车辆信息随着关键帧的推移而产生的加速度变化；对各关键帧的加速度进行离散数据拟合分析得到加速度线条之后，还包括：将所述加速度线条上传至区块链中。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011096024.3 | 2020-10-14 | ||
| CN202011096024.3A CN112185131A (zh) | 2020-10-14 | 2020-10-14 | 车辆行使状态判断方法、装置、计算机设备及存储介质 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2022078353A1 true WO2022078353A1 (zh) | 2022-04-21 |
Family
ID=73950141
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2021/123413 WO2022078353A1 (zh) | 2020-10-14 | 2021-10-13 | 车辆行使状态判断方法、装置、计算机设备及存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112185131A (zh) |
| WO (1) | WO2022078353A1 (zh) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115935000A (zh) * | 2023-02-24 | 2023-04-07 | 广东瑞恩科技有限公司 | 一种物联网数据智能存储方法及*** |
| CN116691626A (zh) * | 2023-08-08 | 2023-09-05 | 徐州奥特润智能科技有限公司 | 基于人工智能的车辆制动***及方法 |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112185131A (zh) * | 2020-10-14 | 2021-01-05 | 深圳壹账通智能科技有限公司 | 车辆行使状态判断方法、装置、计算机设备及存储介质 |
| CN112829703B (zh) * | 2021-01-18 | 2022-06-21 | 深圳市几米物联有限公司 | 一种基于三轴加速度传感器的汽车碰撞检测方法与*** |
| CN114220191B (zh) * | 2021-12-13 | 2023-11-21 | 平安国际融资租赁有限公司 | 行车状态识别方法、装置、计算机设备及可读存储介质 |
| CN116740660B (zh) * | 2023-08-11 | 2023-11-21 | 深圳市明世弘生电子科技有限公司 | 一种基于ai技术的车辆数据处理方法和*** |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007026301A (ja) * | 2005-07-20 | 2007-02-01 | Matsushita Electric Ind Co Ltd | 停止低速車両検出装置及び停止低速車両検出方法 |
| CN108256380A (zh) * | 2016-12-28 | 2018-07-06 | 南宁市浩发科技有限公司 | 道路交通异常自动检测方法 |
| CN108470453A (zh) * | 2018-03-16 | 2018-08-31 | 长安大学 | 一种车辆直行的车速计算方法 |
| CN109686088A (zh) * | 2018-12-29 | 2019-04-26 | 重庆同济同枥信息技术有限公司 | 一种交通视频告警方法、设备及*** |
| CN110239559A (zh) * | 2019-07-02 | 2019-09-17 | 绍兴数鸿科技有限公司 | 基于新能源车数据的危险驾驶车辆检测方法及装置 |
| CN112185131A (zh) * | 2020-10-14 | 2021-01-05 | 深圳壹账通智能科技有限公司 | 车辆行使状态判断方法、装置、计算机设备及存储介质 |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106494407B (zh) * | 2016-11-16 | 2019-01-29 | 山东天地通数码科技有限公司 | 判断汽车行驶状态的分析方法及装置 |
| CN109726645A (zh) * | 2018-12-14 | 2019-05-07 | 深圳壹账通智能科技有限公司 | 一种碰撞事件的检测方法及*** |
| CN109830116A (zh) * | 2018-12-15 | 2019-05-31 | 深圳壹账通智能科技有限公司 | 基于图像识别的信息提示方法、装置及相关设备 |
| CN110533912B (zh) * | 2019-09-16 | 2022-05-20 | 腾讯科技（深圳）有限公司 | 基于区块链的驾驶行为检测方法及装置 |
| CN111767851A (zh) * | 2020-06-29 | 2020-10-13 | 北京百度网讯科技有限公司 | 突发事件的监控方法、装置、电子设备和介质 |
-
2020
- 2020-10-14 CN CN202011096024.3A patent/CN112185131A/zh active Pending
-
2021
- 2021-10-13 WO PCT/CN2021/123413 patent/WO2022078353A1/zh active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007026301A (ja) * | 2005-07-20 | 2007-02-01 | Matsushita Electric Ind Co Ltd | 停止低速車両検出装置及び停止低速車両検出方法 |
| CN108256380A (zh) * | 2016-12-28 | 2018-07-06 | 南宁市浩发科技有限公司 | 道路交通异常自动检测方法 |
| CN108470453A (zh) * | 2018-03-16 | 2018-08-31 | 长安大学 | 一种车辆直行的车速计算方法 |
| CN109686088A (zh) * | 2018-12-29 | 2019-04-26 | 重庆同济同枥信息技术有限公司 | 一种交通视频告警方法、设备及*** |
| CN110239559A (zh) * | 2019-07-02 | 2019-09-17 | 绍兴数鸿科技有限公司 | 基于新能源车数据的危险驾驶车辆检测方法及装置 |
| CN112185131A (zh) * | 2020-10-14 | 2021-01-05 | 深圳壹账通智能科技有限公司 | 车辆行使状态判断方法、装置、计算机设备及存储介质 |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115935000A (zh) * | 2023-02-24 | 2023-04-07 | 广东瑞恩科技有限公司 | 一种物联网数据智能存储方法及*** |
| CN116691626A (zh) * | 2023-08-08 | 2023-09-05 | 徐州奥特润智能科技有限公司 | 基于人工智能的车辆制动***及方法 |
| CN116691626B (zh) * | 2023-08-08 | 2023-10-31 | 徐州奥特润智能科技有限公司 | 基于人工智能的车辆制动***及方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112185131A (zh) | 2021-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022078353A1 (zh) | 车辆行使状态判断方法、装置、计算机设备及存储介质 | |
| CN112085952B (zh) | 监控车辆数据方法、装置、计算机设备及存储介质 | |
| CN112738039B (zh) | 一种基于流量行为的恶意加密流量检测方法、***及设备 | |
| EP2887333B1 (en) | Privacy-preserving evidence in ALPR applications | |
| CN109741482B (zh) | 一种信息共享方法及装置 | |
| CN113918526B (zh) | 日志处理方法、装置、计算机设备和存储介质 | |
| CN110855648A (zh) | 一种网络攻击的预警控制方法及装置 | |
| CN114637884B (zh) | 一种电像计算时空轨迹与道路网的匹配方法、装置及设备 | |
| CN110533906B (zh) | 一种路况信息的获取方法及相关装置 | |
| CN113037750B (zh) | 一种车辆检测数据增强训练方法、***、车辆及存储介质 | |
| CN114550052A (zh) | 一种车辆事故处理方法、装置、计算机设备及存储介质 | |
| CN112733170B (zh) | 一种基于证据序列提取的主动信任评估方法 | |
| CN113886817A (zh) | 主机入侵检测方法及装置、电子设备、存储介质 | |
| CN110555449B (zh) | 用于输出信息的方法和装置 | |
| CN110851414B (zh) | 一种以聚类法进行边界数据分析的方法及其*** | |
| CN113688385B (zh) | 轻量级分布式入侵检测方法 | |
| CN112182302B (zh) | 基于换乘管理的地铁乘车路线溯源方法及装置 | |
| CN113128294B (zh) | 一种道路事件取证方法、装置、电子设备及存储介质 | |
| CN113099264A (zh) | 基于全局特征的区块链监控视频防篡改方法及*** | |
| CN113822292A (zh) | 车辆特征信息存储方法、装置、计算机设备及存储介质 | |
| CN111753829A (zh) | 一种基于可信计算的车辆综合信息采集装置 | |
| Anuvab et al. | PlateSegFL: A Privacy-Preserving License Plate Detection Using Federated Segmentation Learning | |
| CN117811841B (zh) | 一种针对内部网络的威胁监测防御***、方法及设备 | |
| CN112101279B (zh) | 目标物异常检测方法、装置、电子设备及存储介质 | |
| CN115472014B (zh) | 一种交通追溯方法、***、服务器及计算机存储介质 |
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: 21879396 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 FORM 1205A DATED 18/07/2023) |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 21879396 Country of ref document: EP Kind code of ref document: A1 |