WO2023283997A1 - 基于视频图像的高速公路夜间团雾监测方法及系统 - Google Patents

基于视频图像的高速公路夜间团雾监测方法及系统 Download PDF

Info

Publication number
WO2023283997A1
WO2023283997A1 PCT/CN2021/108214 CN2021108214W WO2023283997A1 WO 2023283997 A1 WO2023283997 A1 WO 2023283997A1 CN 2021108214 W CN2021108214 W CN 2021108214W WO 2023283997 A1 WO2023283997 A1 WO 2023283997A1
Authority
WO
WIPO (PCT)
Prior art keywords
meters
visibility
camera
solar
fog
Prior art date
Application number
PCT/CN2021/108214
Other languages
English (en)
French (fr)
Inventor
冯海霞
Original Assignee
山东交通学院
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 山东交通学院 filed Critical 山东交通学院
Publication of WO2023283997A1 publication Critical patent/WO2023283997A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10Complex mathematical operations
    • G06F17/18Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10Services
    • G06Q50/26Government or public services
    • G06Q50/265Personal security, identity or safety
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02ATECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Definitions

  • the invention relates to the technical field of traffic safety, in particular to a night fog monitoring method and system for highways based on video images.
  • Fog is easy to cause major traffic accidents, known as "high-speed killer". Due to the rapid development of cameras, the monitoring method of visibility and fog based on video images has become a new research trend. There is almost a big problem at night, that is, the overall gray value of the image at night is too low because the light is too dark, and it is almost impossible to effectively obtain image features that can represent visibility, fog, etc., so it is difficult to obtain effective images based on video images at night Visibility and fog data (see Figure 1 and Figure 2, where Figure 1 is the video image at night, and Figure 2 is the video image during the day).
  • Fog generally occurs at night when there is a large temperature difference between day and night, no wind or light wind, or from 4:00 to 8:00 in the morning. Therefore, solving the problem of fog monitoring based on video images at night is the key to solving the problem of fog monitoring based on video images.
  • the suddenness of cloudy fog is strong, and the concentration is large, the range is small, and the visibility will suddenly decrease. Generally, it is only tens of meters to hundreds of meters. In the worst case, it is only a few meters, and it is difficult to predict.
  • Monitoring and early warning are the key to reducing traffic accidents. Therefore, in addition to the visibility recognition of nighttime images, it is also necessary to consider the characteristics of the fog itself, such as sudden appearance, small range, high concentration, and easy occurrence in mountainous areas. Timely interpretation is the key to fog early warning and the key to reducing traffic accidents.
  • the present invention provides a method and system for monitoring fog at night on a highway based on video images; it solves the problem of monitoring fog at night based on video images, and ensures traffic safety and the safety of people's lives and property.
  • the present invention provides a video image-based highway night fog monitoring method
  • a video image-based night fog monitoring method for highways including:
  • the nighttime images are obtained by shooting a number of solar lights installed near each camera for each camera installed on the roadside of the expressway at a set time interval of;
  • the distance between the farthest solar light that can be identified and the current camera is used as the visibility value, and an early warning signal is given according to the visibility value;
  • the present invention provides a night fog monitoring system for highways based on video images
  • Night fog monitoring system for expressways based on video images including:
  • the acquisition module is configured to: acquire the nighttime image of the roadside solar lights of the expressway; the nighttime image is provided by each camera installed on the roadside of the expressway, and a number of solar lights installed near each camera are specified, It is obtained by shooting once at a set time interval;
  • the matching module is configured to: match the position of the solar lights with the electronic highway map and the nighttime image; display the actual installation position of each solar light on the nighttime image;
  • An image processing module which is configured to: obtain the mean value and variance of the gray value of the nighttime image, and obtain the summation result of the mean value and the variance; obtain the gray value of the pixel of the nighttime image corresponding to the actual installation position of each solar lamp; according to the Gray value and described summation result, draw the identification result of solar lamp;
  • the visibility early warning module is configured to: use the distance between the farthest solar light that can be identified and the current camera as the visibility value, and give an early warning signal according to the visibility value;
  • the group fog early warning module is configured to: identify the flow direction and flow velocity of the group fog, and give early warning to the group fog.
  • the present invention also provides an electronic device, comprising:
  • the present invention also provides a storage medium that non-transitorily stores computer-readable instructions, wherein, when the non-transitory computer-readable instructions are executed by a computer, the instructions for executing the method described in the first aspect .
  • the invention provides a method and system for monitoring fog at night on a highway based on a video image; according to the comparison of the mean value, the variance summation result and the gray value, the solar lamp farthest from the camera is identified, and the farthest solar lamp is combined with the visibility optimization
  • the final classification results are used to identify the monitoring results of the current cloud fog at night on the expressway, and at the same time, the flow velocity and flow direction of the cloud fog are interpreted to solve the problem of cloud fog monitoring based on video images at night, and to ensure traffic safety and the safety of people's lives and property.
  • Fig. 1 is night video image
  • Figure 2 is a daytime video image
  • Fig. 3 is the installation schematic diagram of video camera and solar lamp of the first embodiment
  • Fig. 4 is the parking line of sight diagram of the first embodiment.
  • the acquisition of all data in this embodiment is based on compliance with laws and regulations and user consent, and the legal application of data.
  • the present embodiment provides the monitoring method of cloudy fog at night on the expressway based on the video image
  • a video image-based night fog monitoring method for highways including:
  • S101 Obtain nighttime images of solar lights on the roadside of the expressway; the nighttime images are taken by each camera installed on the roadside of the expressway, and a number of solar lights installed near each camera are taken at intervals of a set time obtained once;
  • S102 matching the position of the solar lights on the highway electronic map and the night image; displaying the actual installation position of each solar light on the night image;
  • S103 Obtain the mean value and variance of the gray value of the nighttime image, and obtain the summation result of the mean value and the variance; obtain the gray value of the nighttime image pixel corresponding to the actual installation position of each solar lamp; according to the gray value and the calculated And the result, the recognition result of the solar lamp is obtained;
  • S104 Taking the distance between the farthest solar light that can be identified and the current camera as the visibility value, and giving an early warning signal according to the visibility value;
  • S105 Identify the flow direction and flow velocity of the group fog, and give an early warning of the group fog.
  • steps S101-S105 can be completed by the central server or the cloud server.
  • S101 Acquire the nighttime image of the roadside solar lights on the highway; before the step, it also includes:
  • S100 call the electronic map of the expressway; match the actual installation position of the camera with the actual installation position of several solar lights designated near each camera on the electronic map, and according to the distance between the solar light and the camera, in order from near to The solar lights on the electronic map are numbered in sequence in order of distance.
  • sequence numbers of the nine solar lights closest to the current camera are 1, 2, 3, 4, 5, 6, 7, 8, and 9.
  • the set road section of the fog-prone road section of the expressway is manually designated according to the historical fog-prone section data.
  • solar lights are installed at several set positions next to each camera, including:
  • solar lights are installed at several set positions next to each camera, wherein the positions where the solar lights are installed (5, 10, 15, 25, 35, 50, 80, 120, 200 meters)
  • the setting process is:
  • the road slope is 1%, and the visibility classification results are as follows:
  • the visibility reference value corresponding to visibility level 1 is 200 meters, and the installation position of the ninth solar light is 200 meters away from the camera;
  • the reference value of visibility corresponding to level 2 visibility is 121 meters; artificially correcting 121 meters, the reference value of visibility corresponding to level 2 visibility is 120 meters, and the installation position of the eighth solar light is 120 meters away from the camera;
  • the visibility reference value corresponding to level 3 visibility is 81 meters; 121 meters is artificially corrected, and the reference value of visibility corresponding to level 3 visibility is 80 meters, and the installation position of the seventh solar light is 80 meters away from the camera;
  • the visibility reference value corresponding to visibility level 4 is 54 meters; 54 meters is artificially corrected, and the visibility reference value corresponding to visibility level 4 is 50 meters, and the installation position of the sixth solar light is 50 meters away from the camera;
  • the reference value of visibility corresponding to level 5 visibility is 37 meters; artificial correction is performed on 37 meters, and the reference value of visibility corresponding to level 5 visibility is 35 meters, and the installation position of the fifth solar light is 35 meters away from the camera;
  • the visibility reference value corresponding to visibility level 6 is 26 meters; artificially correcting 26 meters, the visibility reference value corresponding to visibility level 6 is 25 meters, and the installation position of the fourth solar light is 25 meters away from the camera;
  • Visibility level 7 corresponds to visibility less than 25 meters; the installation position of the third solar light is 15 meters away from the camera, the installation position of the second solar light is 10 meters away from the camera, and the installation of the first solar light The location is 5 meters away from the camera.
  • a highway visibility grading formula based on traffic safety is constructed, and solar lights are installed based on the new visibility grading standard and grade warnings.
  • the specific visibility classification formula is derived as follows:
  • A. Call the electronic map of the expressway to determine the speed limit V 1 of the road;
  • V 2 V 1 *(1- ⁇ v)*(1- ⁇ ) (1)
  • V i V i-1 *(1- ⁇ v)*(1- ⁇ ) (2)
  • L1 is the braking reaction distance of the vehicle behind the current vehicle
  • L2 is the braking distance of the vehicle behind the current vehicle
  • L is the safety distance between the current vehicle and the vehicle in front of the current vehicle after they stop completely
  • L 3 is the distance traveled by the vehicle in front during the reaction time and braking time
  • S is the visibility (maximum visual distance) of the road section.
  • NASHRP National Cooperative Highway Research Program
  • V is the driving speed of the vehicle
  • a is the braking deceleration of the vehicle
  • L is the static safety distance
  • i is the longitudinal slope of the road surface
  • S is the visibility of the road section (the maximum safe viewing distance).
  • the model can be expressed as:
  • visibility classification visibility value Visibility reference value calculated according to the formula Level 1 >200 200 level 2 200-120 121 Level 3 120-80 81 level 4 80-50 54 Level 5 50-35 37 Level 6 35-25 26 Level 7 ⁇ 25 19
  • said S103 Obtain the recognition result of the solar lamp according to the gray value and the summation result; specifically include:
  • the distance between the farthest solar light that can be identified and the current camera is used as the visibility value, and before the step of giving an early warning signal according to the visibility value, it also includes:
  • the number of the solar light at the recognition point is interrupted, verify it with the processing of the subsequent three frames of images. If the verification result of the three frames of images is that only one frame of the image is the serial number recognition interruption, it will be interpreted as a misjudgment and the misjudgment result will be deleted. ;
  • the verification result of the three frames of images is that the numbers of each frame of images are discontinuous. If the verification result of the three frames of images is that the numbers of each frame of images are discontinuous, then interpret the number sequence of the solar lights at the interrupted position (usually this situation occurs in places with large road curvature, such as mountainous areas) , the interrupted position is judged as the position where the fog appears, and the sum of the distances between the solar lights in the middle is judged as the range when the fog appears.
  • said S104 taking the distance between the farthest solar light that can be identified and the current camera as the visibility value, and giving an early warning signal according to the visibility value; specifically including:
  • no early warning signal When the visibility value is greater than 200 meters, no early warning signal will be issued; when the visibility value is greater than 120 meters and less than or equal to 200 meters, no early warning signal will be issued; when the visibility value is greater than 80 meters and less than or equal to 120 meters, an early warning signal will be issued for cloud fog; When the visibility value is greater than 50 meters and less than or equal to 80 meters, a yellow warning signal is issued; when the visibility value is greater than 35 meters and less than or equal to 50 meters, a red warning signal is issued; when the visibility value is less than 35 meters, an emergency warning signal is issued.
  • said S105 identifying the flow direction and flow velocity of the group fog, and giving an early warning to the group fog; specifically including:
  • the range of fog is between 200 ⁇ n and 200 ⁇ (n-1);
  • the second camera whose visibility is lower than 120 meters is the direction of the fog flow at the position of the first camera
  • This system is installed on the existing fog-prone sections of an expressway, which can form a fog night monitoring system for the entire expressway, and then can form a regional or even a national fog night monitoring system.
  • the present embodiment provides the night group fog monitoring system of the expressway based on the video image
  • Night fog monitoring system for expressways based on video images including:
  • the acquisition module is configured to: acquire the nighttime image of the roadside solar lights of the expressway; the nighttime image is provided by each camera installed on the roadside of the expressway, and a number of solar lights installed near each camera are specified, It is obtained by shooting once at a set time interval;
  • the matching module is configured to: match the position of the solar lights with the electronic highway map and the nighttime image; display the actual installation position of each solar light on the nighttime image;
  • An image processing module which is configured to: obtain the mean value and variance of the gray value of the nighttime image, and obtain the summation result of the mean value and the variance; obtain the gray value of the pixel of the nighttime image corresponding to the actual installation position of each solar lamp; according to the Gray value and described summation result, draw the identification result of solar lamp;
  • the visibility early warning module is configured to: use the distance between the farthest solar light that can be identified and the current camera as the visibility value, and give an early warning signal according to the visibility value;
  • the group fog early warning module is configured to: identify the flow direction and flow velocity of the group fog, and give early warning to the group fog.
  • the above acquisition module, matching module, image processing module, visibility early warning module and group fog early warning module correspond to steps S101 to S105 in Embodiment 1, the examples and applications realized by the above modules and corresponding steps The scenarios are the same, but are not limited to the content disclosed in Embodiment 1 above. It should be noted that, as a part of the system, the above-mentioned modules can be executed in a computer system such as a set of computer-executable instructions.
  • the proposed system can be implemented in other ways.
  • the above-described system embodiments are only illustrative.
  • the division of the above modules is only a logical function division.
  • there may be other division methods for example, multiple modules can be combined or integrated into another A system, or some feature, can be ignored, or not implemented.
  • This embodiment also provides an electronic device, including: one or more processors, one or more memories, and one or more computer programs; wherein, the processor is connected to the memory, and the one or more computer programs are programmed Stored in the memory, when the electronic device is running, the processor executes one or more computer programs stored in the memory, so that the electronic device executes the method described in Embodiment 1 above.
  • the processor can be a central processing unit CPU, and the processor can also be other general-purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate array FPGA or other programmable logic devices , discrete gate or transistor logic devices, discrete hardware components, etc.
  • a general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.
  • the memory may include read-only memory and random access memory, and provide instructions and data to the processor, and a part of the memory may also include non-volatile random access memory.
  • the memory may also store device type information.
  • each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software.
  • Embodiment 1 can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor.
  • the software module may be located in a mature storage medium in the field such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register.
  • the storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps of the above method in combination with its hardware. To avoid repetition, no detailed description is given here.
  • This embodiment also provides a computer-readable storage medium for storing computer instructions, and when the computer instructions are executed by a processor, the method described in the first embodiment is completed.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Operations Research (AREA)
  • Probability & Statistics with Applications (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Algebra (AREA)
  • Evolutionary Biology (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Traffic Control Systems (AREA)

Abstract

基于视频图像的高速公路夜间团雾监测方法及系统,获取高速公路路边太阳能灯的夜间图像;将高速公路电子地图与夜间图像进行太阳能灯位置匹配;将每个太阳能灯的实际安装位置显示在夜间图像上;获取夜间图像灰度值的均值和方差,得到二者的求和结果;获取每个太阳能灯实际安装位置对应的夜间图像像素的灰度值;根据灰度值和求和结果,得出太阳能灯的识别结果;将识别出来的最远处太阳能灯距离当前摄像机的距离作为能见度值,根据能见度值给出预警信号;识别团雾的流向和流速,对团雾进行提前预警。解决夜间团雾监测问题,保障交通安全和人们生命财产安全。

Description

基于视频图像的高速公路夜间团雾监测方法及系统 技术领域
本发明涉及交通安全技术领域,特别是涉及基于视频图像的高速公路夜间团雾监测方法及系统。
背景技术
本部分的陈述仅仅是提到了与本发明相关的背景技术,并不必然构成现有技术。
团雾易造成重大交通事故,号称“高速杀手”。因摄像机的飞速发展,基于视频图像的能见度、团雾的监测方法成为研究的新趋势,虽然基于视频的能见度、团雾监测已发展了较多的方法,但目前基于视频图像的团雾监测方法在夜间几乎都存在较大的问题,即夜间图像因光线太暗,图像的整体灰度值太低,几乎无法有效获取能表征能见度、雾等的图像特征,因此夜间基于视频图像很难获取有效的能见度、团雾数据(见图1和图2,其中图1为夜间的视频图像,图2为白天的视频图像)。团雾一般出现在昼夜温差较大、无风或微风的夜间,或者是早晨4时至8时,因此解决夜间基于视频图像的团雾监测问题是解决基于视频图像的团雾监测问题的关键。
团雾突发性强,且浓度大,范围小,能见度会突然降低,一般只有数十米到上百米,最严重的时候只有几米,且预测比较困难,因此当团雾发生时,及时的监测和预警才是降低交通事故的关键,因此在夜间图像的能见度识别问题外,还需要考虑团雾自身出现突然,范围小,浓度大、在山区易发等特点,团雾的 流速和流向的及时判读是团雾预警的关键,也是减少交通事故的关键。
发明内容
为了解决现有技术的不足,本发明提供了基于视频图像的高速公路夜间团雾监测方法及系统;解决夜间的基于视频图像的团雾监测问题,保障交通安全和人们生命财产安全。
第一方面,本发明提供了基于视频图像的高速公路夜间团雾监测方法;
基于视频图像的高速公路夜间团雾监测方法,包括:
获取高速公路路边太阳能灯的夜间图像;所述夜间图像是由安装在高速公路路边的每台摄像机,对安装在每台摄像机附近指定的若干个太阳能灯,每间隔设定时间拍摄一次得到的;
将高速公路电子地图与夜间图像进行太阳能灯位置匹配;将每个太阳能灯的实际安装位置显示在夜间图像上;
获取夜间图像灰度值的均值和方差,得到均值与方差的求和结果;获取每个太阳能灯实际安装位置对应的夜间图像像素的灰度值;根据所述灰度值和所述求和结果,得出太阳能灯的识别结果;
将能被识别出来的最远处太阳能灯距离当前摄像机的距离作为能见度值,根据能见度值给出预警信号;
识别团雾的流向和流速,对团雾进行提前预警。
第二方面,本发明提供了基于视频图像的高速公路夜间团雾监测系统;
基于视频图像的高速公路夜间团雾监测系统,包括:
获取模块,其被配置为:获取高速公路路边太阳能灯的夜间图像;所述夜间图像是由安装在高速公路路边的每台摄像机,对安装在每台摄像机附近指定 的若干个太阳能灯,每间隔设定时间拍摄一次得到的;
匹配模块,其被配置为:将高速公路电子地图与夜间图像进行太阳能灯位置匹配;将每个太阳能灯的实际安装位置显示在夜间图像上;
图像处理模块,其被配置为:获取夜间图像灰度值的均值和方差,得到均值与方差的求和结果;获取每个太阳能灯实际安装位置对应的夜间图像像素的灰度值;根据所述灰度值和所述求和结果,得出太阳能灯的识别结果;
能见度预警模块,其被配置为:将能被识别出来的最远处太阳能灯距离当前摄像机的距离作为能见度值,根据能见度值给出预警信号;
团雾预警模块,其被配置为:识别团雾的流向和流速,对团雾进行提前预警。
第三方面,本发明还提供了一种电子设备,包括:
存储器,用于非暂时性存储计算机可读指令;以及
处理器,用于运行所述计算机可读指令,
其中,所述计算机可读指令被所述处理器运行时,执行上述第一方面所述的方法。
第四方面,本发明还提供了一种存储介质,非暂时性地存储计算机可读指令,其中,当所述非暂时性计算机可读指令由计算机执行时,执行第一方面所述方法的指令。
与现有技术相比,本发明的有益效果是:
本发明提供了基于视频图像的高速公路夜间团雾监测方法及系统;根据均值、方差求和结果与灰度值的比较,来识别距离摄像机最远太阳能灯,并根据最远太阳能灯结合能见度优化后的分级结果,来识别当前高速公路夜间团雾的 监测结果,同时对团雾的流速、流向进行判读,解决夜间的基于视频图像的团雾监测问题,保障交通安全和人们生命财产安全。
本发明附加方面的优点将在下面的描述中部分给出,或通过本发明的实践了解到。
附图说明
构成本发明的一部分的说明书附图用来提供对本发明的进一步理解,本发明的示意性实施例及其说明用于解释本发明,并不构成对本发明的不当限定。
图1为夜间视频图像;
图2为白天视频图像;
图3为第一个实施例的摄像机和太阳能灯安装示意图;
图4为第一个实施例的停车视距图。
具体实施方式
应该指出,以下详细说明都是示例性的,旨在对本发明提供进一步的说明。除非另有指明,本文使用的所有技术和科学术语具有与本发明所属技术领域的普通技术人员通常理解的相同含义。
需要注意的是,这里所使用的术语仅是为了描述具体实施方式,而非意图限制根据本发明的示例性实施方式。如在这里所使用的,除非上下文另外明确指出,否则单数形式也意图包括复数形式,此外,还应当理解的是,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。
在不冲突的情况下,本发明中的实施例及实施例中的特征可以相互组合。
本实施例所有数据的获取都在符合法律法规和用户同意的基础上,对数据的合法应用。
实施例一
本实施例提供了基于视频图像的高速公路夜间团雾监测方法;
基于视频图像的高速公路夜间团雾监测方法,包括:
S101:获取高速公路路边太阳能灯的夜间图像;所述夜间图像是由安装在高速公路路边的每台摄像机,对安装在每台摄像机附近指定的若干个太阳能灯,每间隔设定时间拍摄一次得到的;
S102:将高速公路电子地图与夜间图像进行太阳能灯位置匹配;将每个太阳能灯的实际安装位置显示在夜间图像上;
S103:获取夜间图像灰度值的均值和方差,得到均值与方差的求和结果;获取每个太阳能灯实际安装位置对应的夜间图像像素的灰度值;根据所述灰度值和所述求和结果,得出太阳能灯的识别结果;
S104:将能被识别出来的最远处太阳能灯距离当前摄像机的距离作为能见度值,根据能见度值给出预警信号;
S105:识别团雾的流向和流速,对团雾进行提前预警。
示例性的,上述步骤S101-S105,可以由中心服务器来完成、云服务器完成。
进一步地,所述S101:获取高速公路路边太阳能灯的夜间图像;步骤之前还包括:
S100:调用高速公路电子地图;将摄像机的实际安装位置与在每台摄像机附近指定的若干个太阳能灯的实际安装位置均匹配到电子地图上,并根据太阳 能灯距离摄像机的远近,按照由近到远的顺序对电子地图上的太阳能灯依次进行编号。
例如,由近到远,距离当前摄像机最近的9个太阳能灯的依次编号为1、2、3、4、5、6、7、8、9。
进一步地,如图3所示,在高速公路的设定路段的路边安装若干台摄像机,相邻摄像机之间间隔200米,每台摄像机距离地面设定距离;在高速公路路边的地面上,每个摄像机旁边的若干个设定位置处安装太阳能灯;其中,摄像机的实际安装位置与太阳能灯的实际安装位置均为已知量。
示例性的,所述高速公路团雾多发路段的设定路段,是根据历史团雾多发地段数据,由人为指定的。
进一步地,在高速公路路边,每个摄像机旁边的若干个设定位置处安装太阳能灯,具体包括:
在距离摄像机5米的位置安装第一个太阳能灯;在距离摄像机10米的位置安装第二个太阳能灯;在距离摄像机15米的位置安装第三个太阳能灯;在距离摄像机25米的位置安装第四个太阳能灯;在距离摄像机35米的位置安装第五个太阳能灯;在距离摄像机50米的位置安装第六个太阳能灯;在距离摄像机80米的位置安装第七个太阳能灯;在距离摄像机120米的位置安装第八个太阳能灯;在距离摄像机200米的位置安装第九个太阳能灯。
进一步地,在高速公路路边,每个摄像机旁边的若干个设定位置处安装太阳能灯,其中,安装太阳能灯的位置(距离摄像机5、10、15、25、35、50、80、120、200米)设定的过程为:
Figure PCTCN2021108214-appb-000001
高速路段夜间限速取值为100,即v1=100,平均速度下降的梯度Δv为15%,速度的离散度取σ为±10%,车辆制动减速度a,取值为3.4m/s 2,路面坡度为1%,得能见度分级结果:
能见度1级对应的能见度参考值为200米,第9个太阳能灯的安装位置为距离摄像头200米的位置处;
能见度2级对应的能见度参考值为121米;对121米进行人为修正,得到能见度2级对应的能见度参考值为120米,第8个太阳能灯的安装位置为距离摄像头120米的位置处;
能见度3级对应的能见度参考值为81米;对121米进行人为修正,得到能见度3级对应的能见度参考值为80米,第7个太阳能灯的安装位置为距离摄像头80米的位置处;
能见度4级对应的能见度参考值为54米;对54米进行人为修正,得到能见度4级对应的能见度参考值为50米,第6个太阳能灯的安装位置为距离摄像头50米的位置处;
能见度5级对应的能见度参考值为37米;对37米进行人为修正,得到能见度5级对应的能见度参考值为35米,第5个太阳能灯的安装位置为距离摄像头35米的位置处;
能见度6级对应的能见度参考值为26米;对26米进行人为修正,得到能见度6级对应的能见度参考值为25米,第4个太阳能灯的安装位置为距离摄像头25米的位置处;
能见度7级对应能见度小于25米;第3个太阳能灯的安装位置为距离摄像头15米的位置处,第2个太阳能灯的安装位置为距离摄像头10米的位置处, 第1个太阳能灯的安装位置为距离摄像头5米的位置处。
示例性的,针对团雾突发性强,浓度大,范围小、能见度极低的特点,构建基于交通安全的高速公路的能见度分级公式,以新的能见度分级标准为依据,进行太阳能灯的安装和分级预警。具体的能见度分级公式推导如下:
①能见度>200米(研究证实当能见度大于200时,对车辆、车速影响很小),能见度归为一级;
②能见度小于200米时,建立新的能见度分级标准:
A.调用高速公路的电子地图,确定道路的限速V 1
B.随能见度车辆平均速度下降的梯度Δv,速度的离散度取σ,则这个梯度中,速度的下限为:
V 2=V 1*(1-Δv)*(1-σ)         (1)
类推可得,第i个梯度的下限速度为:
V i=V i-1*(1-Δv)*(1-σ)          (2)
其中,i≥2;当Vi<20时,停止运算;
C.停车视距的限速模型,详见示意图4,可得:
L 1+L 2+L<L 3+S                (3)
其中,L 1为当前车辆的后方车辆的制动反应距离;L 2为当前车辆的后方车辆制动距离;L为当前车辆与当前车辆的前方车辆两车完全停止后所保持的安全距离,L 3为前方车辆在反应时间与制动时间内行驶的距离,S为路段的能见度(最大可视距离)。
以美国公路合作研究组织(National Cooperative Highway Research Program,NCHRP)停车视距模型为基础,考虑车辆故障、轮胎损坏、抛锚、货物洒落及事 故等原因,前方车辆必须进行紧急制动,或者前方车辆可以看出前方静止的障碍物位置,L 3为0,模型的表达式如下:
Figure PCTCN2021108214-appb-000002
V为车辆行驶速度,a为车辆制动减速度,L为静止安全距离,i为路面纵坡,S为路段的能见度(最大安全可视距离)。
D.构建基于速度和停车视距的能见度分级模型(标准):
L为静止安全距离,所以L≥0,取L=0,能见度模型可表述为,
Figure PCTCN2021108214-appb-000003
根据第i个梯度下限速度的计算公式,模型可表述为:
Figure PCTCN2021108214-appb-000004
E.高速路段夜间限速取值为100,即v1=100,平均速度下降的梯度Δv为15%,速度的离散度取σ为±10%,车辆制动减速度a,取值为3.4m/s 2,路面坡度为1%,则可得如下的能见度分级表:
表1能见度分级
能见度分级 能见度值 根据公式计算的能见度参考值
1级 >200 200
2级 200-120 121
3级 120-80 81
4级 80-50 54
5级 50-35 37
6级 35-25 26
7级 <25 19
③依据能见度的分级设置确定太阳能灯的安装距离(针对团雾特点,补充 能见度25米以下15、10、5米处太阳灯的安装),故分别在距离摄像机5、10、15、25、35、50、80、120、200米处安装太阳能灯。
进一步地,所述S103:根据所述灰度值和所述求和结果,得出太阳能灯的识别结果;具体包括:
判断每个太阳能灯实际安装位置对应的夜间图像像素的灰度值是否大于求和结果,如果大于,则认为已经识别出当前太阳能灯;否则,则认为未能识别出当前太阳能灯;则对下一个太阳能灯进行识别,直至所有太阳能灯被识别完毕。
进一步地,所述直至所有太阳能灯被识别完毕步骤之后,所述将能被识别出来的最远处太阳能灯距离当前摄像机的距离作为能见度值,根据能见度值给出预警信号步骤之前,还包括:
如果出现识别处的太阳能灯编号中断的情况,则以后续三帧图像的处理进行验证,如果三帧图像的验证结果为只有一帧图像为序号识别中断,判读为存在误判,删除误判结果;
如果三帧图像的验证结果为每一帧图像的编号均存在不连续的情况,则对中断位置的太阳能灯编号顺序进行判读(通常这种情况出现在道路弯曲度较大的地方,比如山区),中断的位置判断为团雾出现的位置,中间的太阳能灯的距离之和判断为团雾的出现时的范围。
应理解的,当太阳能灯编号全部出现时,则表示能见度高,无需预警;当太阳能灯部分出现,但是,太阳能灯的编号是连续时,则根据识别的最远太阳能灯来判定当前能见度;当太阳能灯部分识别出来,但是识别出来的太阳能编号并不连续时,则需要进行误判的识别,以避免误判影响结果的准确性。
进一步地,所述S104:将能被识别出来的最远处太阳能灯距离当前摄像机的距离作为能见度值,根据能见度值给出预警信号;具体包括:
当能见度值大于200米时,不发出预警信号;当能见度值大于120米且小于等于200米时,不发出预警信号;当能见度值大于80米且小于等于120米时,发出团雾预警信号;当能见度值大于50米且小于等于80米时,发出黄色预警信号;当能见度值大于35米且小于等于50米时,发出红色预警信号;当能见度值小于35米时,发出紧急预警信号。
进一步地,所述S105:识别团雾的流向和流速,对团雾进行提前预警;具体包括:
当一个摄像头的能见度出现小于120m时,启动相邻摄像机的判读,以对团雾范围、流速、流向进行判读;
如果n个摄像头的能见度都出现小于120米的情况,则团雾的范围为200×n到200×(n-1)之间;
n个摄像头中第2个出现能见度低于120米的摄像头在第1个出现摄像头的方位就是团雾的流向;
2个摄像头依次出现能见度小于120米的时间间隔为t 1,则流速为V 1=200/t 1,根据流速、流向进行提前预警;
当出现n(n>2)个摄影头出现小于120米时,出现的时间间隔t1、t2…t n-1,团雾的流速
Figure PCTCN2021108214-appb-000005
提前预警信息随团雾的流动进行更新。
一条高速公路现有团雾多发路段的都安装此系统,可组成高速公路全程的团雾夜间监测系统、进而可组成区域甚至全国的团雾夜间监测系统。
实施例二
本实施例提供了基于视频图像的高速公路夜间团雾监测系统;
基于视频图像的高速公路夜间团雾监测系统,包括:
获取模块,其被配置为:获取高速公路路边太阳能灯的夜间图像;所述夜间图像是由安装在高速公路路边的每台摄像机,对安装在每台摄像机附近指定的若干个太阳能灯,每间隔设定时间拍摄一次得到的;
匹配模块,其被配置为:将高速公路电子地图与夜间图像进行太阳能灯位置匹配;将每个太阳能灯的实际安装位置显示在夜间图像上;
图像处理模块,其被配置为:获取夜间图像灰度值的均值和方差,得到均值与方差的求和结果;获取每个太阳能灯实际安装位置对应的夜间图像像素的灰度值;根据所述灰度值和所述求和结果,得出太阳能灯的识别结果;
能见度预警模块,其被配置为:将能被识别出来的最远处太阳能灯距离当前摄像机的距离作为能见度值,根据能见度值给出预警信号;
团雾预警模块,其被配置为:识别团雾的流向和流速,对团雾进行提前预警。
此处需要说明的是,上述获取模块、匹配模块、图像处理模块、能见度预警模块和团雾预警模块对应于实施例一中的步骤S101至S105,上述模块与对应的步骤所实现的示例和应用场景相同,但不限于上述实施例一所公开的内容。需要说明的是,上述模块作为系统的一部分可以在诸如一组计算机可执行指令的计算机系统中执行。
上述实施例中对各个实施例的描述各有侧重,某个实施例中没有详述的部分可以参见其他实施例的相关描述。
所提出的系统,可以通过其他的方式实现。例如以上所描述的系统实施例 仅仅是示意性的,例如上述模块的划分,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,例如多个模块可以结合或者可以集成到另外一个系统,或一些特征可以忽略,或不执行。
实施例三
本实施例还提供了一种电子设备,包括:一个或多个处理器、一个或多个存储器、以及一个或多个计算机程序;其中,处理器与存储器连接,上述一个或多个计算机程序被存储在存储器中,当电子设备运行时,该处理器执行该存储器存储的一个或多个计算机程序,以使电子设备执行上述实施例一所述的方法。
应理解,本实施例中,处理器可以是中央处理单元CPU,处理器还可以是其他通用处理器、数字信号处理器DSP、专用集成电路ASIC,现成可编程门阵列FPGA或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
存储器可以包括只读存储器和随机存取存储器,并向处理器提供指令和数据、存储器的一部分还可以包括非易失性随机存储器。例如,存储器还可以存储设备类型的信息。
在实现过程中,上述方法的各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。
实施例一中的方法可以直接体现为硬件处理器执行完成,或者用处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器、闪存、只读存储器、可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器,处理器读取存储器中的信息,结合其 硬件完成上述方法的步骤。为避免重复,这里不再详细描述。
本领域普通技术人员可以意识到,结合本实施例描述的各示例的单元及算法步骤,能够以电子硬件或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行,取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能,但是这种实现不应认为超出本发明的范围。
实施例四
本实施例还提供了一种计算机可读存储介质,用于存储计算机指令,所述计算机指令被处理器执行时,完成实施例一所述的方法。
以上所述仅为本发明的优选实施例而已,并不用于限制本发明,对于本领域的技术人员来说,本发明可以有各种更改和变化。凡在本发明的精神和原则之内,所作的任何修改、等同替换、改进等,均应包含在本发明的保护范围之内。

Claims (10)

  1. 基于视频图像的高速公路夜间团雾监测方法,其特征是,包括:
    获取高速公路路边太阳能灯的夜间图像;所述夜间图像是由安装在高速公路路边的每台摄像机,对安装在每台摄像机附近指定的若干个太阳能灯,每间隔设定时间拍摄一次得到的;
    将高速公路电子地图与夜间图像进行太阳能灯位置匹配;将每个太阳能灯的实际安装位置显示在夜间图像上;
    获取夜间图像灰度值的均值和方差,得到均值与方差的求和结果;获取每个太阳能灯实际安装位置对应的夜间图像像素的灰度值;根据所述灰度值和所述求和结果,得出太阳能灯的识别结果;
    将能被识别出来的最远处太阳能灯距离当前摄像机的距离作为能见度值,根据能见度值给出预警信号;
    识别团雾的流向和流速,对团雾进行提前预警。
  2. 如权利要求1所述的基于视频图像的高速公路夜间团雾监测方法,其特征是,获取高速公路路边太阳能灯的夜间图像;步骤之前还包括:
    调用高速公路电子地图;将摄像机的实际安装位置与在每台摄像机附近指定的若干个太阳能灯的实际安装位置均匹配到电子地图上,并根据太阳能灯距离摄像机的远近,按照由近到远的顺序对电子地图上的太阳能灯依次进行编号。
  3. 如权利要求1所述的基于视频图像的高速公路夜间团雾监测方法,其特征是,在高速公路的设定路段的路边安装若干台摄像机,相邻摄像机之间间隔200米,每台摄像机距离地面设定距离;在高速公路路边的地面上,每个摄像机旁边的若干个设定位置处安装太阳能灯;其中,摄像机的实际安装位置与太阳能灯的实际安装位置均为已知量。
  4. 如权利要求3所述的基于视频图像的高速公路夜间团雾监测方法,其特征是,在高速公路路边的地面上,每个摄像机旁边的若干个设定位置处安装太阳能灯,具体包括:
    在距离摄像机5米的位置安装第一个太阳能灯;在距离摄像机10米的位置安装第二个太阳能灯;在距离摄像机15米的位置安装第三个太阳能灯;在距离摄像机25米的位置安装第四个太阳能灯;在距离摄像机35米的位置安装第五个太阳能灯;在距离摄像机50米的位置安装第六个太阳能灯;在距离摄像机80米的位置安装第七个太阳能灯;在距离摄像机120米的位置安装第八个太阳能灯;在距离摄像机200米的位置安装第九个太阳能灯。
  5. 如权利要求3所述的基于视频图像的高速公路夜间团雾监测方法,其特征是,在高速公路路边的地面上,每个摄像机旁边的若干个设定位置处安装太阳能灯,其中,安装太阳能灯的位置设定的过程为:
    Figure PCTCN2021108214-appb-100001
    高速路段夜间限速取值为100,即v1=100,平均速度下降的梯度Δv为15%,速度的离散度取σ为±10%,车辆制动减速度a,取值为3.4m/s 2,路面坡度为1%,得能见度分级结果:
    能见度1级对应的能见度参考值为200米,第9个太阳能灯的安装位置为距离摄像头200米的位置处;
    能见度2级对应的能见度参考值为121米;对121米进行人为修正,得到能见度2级对应的能见度参考值为120米,第8个太阳能灯的安装位置为距离摄像头120米的位置处;
    能见度3级对应的能见度参考值为81米;对121米进行人为修正,得到能 见度3级对应的能见度参考值为80米,第7个太阳能灯的安装位置为距离摄像头80米的位置处;
    能见度4级对应的能见度参考值为54米;对54米进行人为修正,得到能见度4级对应的能见度参考值为50米,第6个太阳能灯的安装位置为距离摄像头50米的位置处;
    能见度5级对应的能见度参考值为37米;对37米进行人为修正,得到能见度5级对应的能见度参考值为35米,第5个太阳能灯的安装位置为距离摄像头35米的位置处;
    能见度6级对应的能见度参考值为26米;对26米进行人为修正,得到能见度6级对应的能见度参考值为25米,第4个太阳能灯的安装位置为距离摄像头25米的位置处;
    能见度7级对应能见度小于25米;第3个太阳能灯的安装位置为距离摄像头15米的位置处,第2个太阳能灯的安装位置为距离摄像头10米的位置处,第1个太阳能灯的安装位置为距离摄像头5米的位置处。
  6. 如权利要求1所述的基于视频图像的高速公路夜间团雾监测方法,其特征是,根据所述灰度值和所述求和结果,得出太阳能灯的识别结果;具体包括:
    判断每个太阳能灯实际安装位置对应的夜间图像像素的灰度值是否大于求和结果,如果大于,则认为已经识别出当前太阳能灯;否则,则认为未能识别出当前太阳能灯;则对下一个太阳能灯进行识别,直至所有太阳能灯被识别完毕;
    或者,
    所述直至所有太阳能灯被识别完毕步骤之后,所述将能被识别出来的最远 处太阳能灯距离当前摄像机的距离作为能见度值,根据能见度值给出预警信号步骤之前,还包括:
    如果出现识别处的太阳能灯编号中断的情况,则以后续三帧图像的处理进行验证,如果三帧图像的验证结果为只有一帧图像为序号识别中断,判读为存在误判,删除误判结果;
    如果三帧图像的验证结果为每一帧图像的编号均存在不连续的情况,则对中断位置的太阳能灯编号顺序进行判读,中断的位置判断为团雾出现的位置,中间的太阳能灯的距离之和判断为团雾的出现时的范围;
    或者,
    将能被识别出来的最远处太阳能灯距离当前摄像机的距离作为能见度值,根据能见度值给出预警信号;具体包括:
    当能见度值大于200米时,不发出预警信号;当能见度值大于120米且小于等于200米时,不发出预警信号;当能见度值大于80米且小于等于120米时,发出团雾预警信号;当能见度值大于50米且小于等于80米时,发出黄色预警信号;当能见度值大于35米且小于等于50米时,发出红色预警信号;当能见度值小于35米时,发出紧急预警信号。
  7. 如权利要求1所述的基于视频图像的高速公路夜间团雾监测方法,其特征是,所述识别团雾的流向和流速,对团雾进行提前预警;具体包括:
    当启动一个摄像头的能见度出现小于120m时,启动相邻摄像机的判读,以对团雾范围、流速、流向进行判读;如果n个摄像头的能见度都出现小于120米的情况,则团雾的范围为200×n到200×(n-1)之间;
    n个摄像头中第2个出现能见度低于120米的摄像头在第1个出现摄像头 的方位就是团雾的流向;
    2个摄像头依次出现能见度小于120米的时间间隔为t 1,则流速为V 1=200/t 1,根据流速、流向进行提前预警;
    当出现n个摄影头出现小于120米时,团雾的流速
    Figure PCTCN2021108214-appb-100002
    提前预警信息随团雾的流动进行更新。
  8. 基于视频图像的高速公路夜间团雾监测系统,其特征是,包括:
    获取模块,其被配置为:获取高速公路路边太阳能灯的夜间图像;所述夜间图像是由安装在高速公路路边的每台摄像机,对安装在每台摄像机附近指定的若干个太阳能灯,每间隔设定时间拍摄一次得到的;
    匹配模块,其被配置为:将高速公路电子地图与夜间图像进行太阳能灯位置匹配;将每个太阳能灯的实际安装位置显示在夜间图像上;
    图像处理模块,其被配置为:获取夜间图像灰度值的均值和方差,得到均值与方差的求和结果;获取每个太阳能灯实际安装位置对应的夜间图像像素的灰度值;根据所述灰度值和所述求和结果,得出太阳能灯的识别结果;
    能见度预警模块,其被配置为:将能被识别出来的最远处太阳能灯距离当前摄像机的距离作为能见度值,根据能见度值给出预警信号;
    团雾预警模块,其被配置为:识别团雾的流向和流速,对团雾进行提前预警。
  9. 一种电子设备,其特征是,包括:
    存储器,用于非暂时性存储计算机可读指令;以及
    处理器,用于运行所述计算机可读指令,
    其中,所述计算机可读指令被所述处理器运行时,执行上述权利要求1-7 任一项所述的方法。
  10. 一种存储介质,其特征是,非暂时性地存储计算机可读指令,其中,当所述非暂时性计算机可读指令由计算机执行时,执行权利要求1-7任一项所述方法的指令。
PCT/CN2021/108214 2021-07-15 2021-07-23 基于视频图像的高速公路夜间团雾监测方法及系统 WO2023283997A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110800026.4A CN113435405B (zh) 2021-07-15 2021-07-15 基于视频图像的高速公路夜间团雾监测方法及系统
CN202110800026.4 2021-07-15

Publications (1)

Publication Number Publication Date
WO2023283997A1 true WO2023283997A1 (zh) 2023-01-19

Family

ID=77760558

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/108214 WO2023283997A1 (zh) 2021-07-15 2021-07-23 基于视频图像的高速公路夜间团雾监测方法及系统

Country Status (2)

Country Link
CN (1) CN113435405B (zh)
WO (1) WO2023283997A1 (zh)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1752946A1 (en) * 2005-08-08 2007-02-14 ELME IMPIANTI S.r.l. Device for detecting fixed or mobile obstacle
CN105303844A (zh) * 2015-10-26 2016-02-03 南京本来信息技术有限公司 基于激光的夜间高速公路团雾自动检测装置及其检测方法
CN108932859A (zh) * 2018-07-18 2018-12-04 上海市政工程设计研究总院(集团)有限公司 一种全范围实时监测的高速公路团雾预警及诱导系统
CN109377726A (zh) * 2018-10-29 2019-02-22 江苏大学 一种基于车联网的高速公路团雾精确警示、诱导系统及方法
CN110598613A (zh) * 2019-09-03 2019-12-20 长安大学 一种高速公路团雾监测方法
CN111292529A (zh) * 2020-01-22 2020-06-16 长安大学 一种识别高速公路团雾分布的方法
CN112866636A (zh) * 2020-12-31 2021-05-28 北京文安智能技术股份有限公司 基于最远可视距离的团雾识别预警方法、系统和电子设备

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR2884637B1 (fr) * 2005-04-19 2007-06-29 Valeo Vision Sa Procede de detection de brouillard nocturne et systeme de mise en oeuvre de ce procede
CN101226597B (zh) * 2007-01-18 2010-04-14 中国科学院自动化研究所 一种基于热红外步态的夜间行人识别方法及系统
KR101713684B1 (ko) * 2016-09-21 2017-03-08 주식회사 에스카 시정상태의 변화에 강인한 복합 필터링 방식의 감시카메라 및 그것이 적용된 영상감시시스템
CN108663368B (zh) * 2018-05-11 2020-11-27 长安大学 一种实时监测高速公路路网夜间整体能见度的系统及方法
CN109241831B (zh) * 2018-07-26 2021-11-26 东南大学 一种基于图像分析的夜间雾天能见度分类方法
CN109165676A (zh) * 2018-07-27 2019-01-08 北京以萨技术股份有限公司 一种基于视频分析的全天候高速公路雾气等级监测方法
CN110097762B (zh) * 2019-03-25 2020-10-09 南京微达电子科技有限公司 一种道路视频图像低能见度刻度估算方法及系统
CN112183440A (zh) * 2020-10-13 2021-01-05 北京百度网讯科技有限公司 道路信息的处理方法、装置、电子设备和存储介质
CN112507795A (zh) * 2020-11-10 2021-03-16 武汉长江通信智联技术有限公司 一种采用机器识别技术估算大气能见度的系统及方法
CN112686164B (zh) * 2020-12-30 2022-06-28 日照市气象局 一种发光目标物视频团雾监测预警方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1752946A1 (en) * 2005-08-08 2007-02-14 ELME IMPIANTI S.r.l. Device for detecting fixed or mobile obstacle
CN105303844A (zh) * 2015-10-26 2016-02-03 南京本来信息技术有限公司 基于激光的夜间高速公路团雾自动检测装置及其检测方法
CN108932859A (zh) * 2018-07-18 2018-12-04 上海市政工程设计研究总院(集团)有限公司 一种全范围实时监测的高速公路团雾预警及诱导系统
CN109377726A (zh) * 2018-10-29 2019-02-22 江苏大学 一种基于车联网的高速公路团雾精确警示、诱导系统及方法
CN110598613A (zh) * 2019-09-03 2019-12-20 长安大学 一种高速公路团雾监测方法
CN111292529A (zh) * 2020-01-22 2020-06-16 长安大学 一种识别高速公路团雾分布的方法
CN112866636A (zh) * 2020-12-31 2021-05-28 北京文安智能技术股份有限公司 基于最远可视距离的团雾识别预警方法、系统和电子设备

Also Published As

Publication number Publication date
CN113435405A (zh) 2021-09-24
CN113435405B (zh) 2023-09-08

Similar Documents

Publication Publication Date Title
CN112837535A (zh) 交通信息处理方法、装置、系统、设备及存储介质
CN102298845B (zh) 一种远光灯视频检测方法及系统
CN109830117B (zh) 道路规划优化方法、装置、计算机设备及存储介质
CN112740295B (zh) 检测车辆行驶场景的复杂度的方法和装置
CN113345258B (zh) 基于边缘计算的道路通行保障方法、系统、设备及介质
CN113313943B (zh) 一种基于路侧感知的路口通行实时调度方法与系统
WO2023197408A1 (zh) 车速控制模型训练样本的确定方法及装置
CN110610153A (zh) 一种用于自动驾驶的车道识别方法及系统
CN113450571B (zh) 基于交通路口的行驶方向提醒方法、装置及存储介质
CN113192328B (zh) 一种道路运行风险防控系统及交通标识牌的协同布设方法
CN115019514B (zh) 一种基于车联网的公路巡查系统
CN109191492A (zh) 一种基于轮廓分析的智能视频黑烟车检测方法
WO2023283997A1 (zh) 基于视频图像的高速公路夜间团雾监测方法及系统
CN117198058B (zh) 一种基于遥感影像的道路交通智能监管系统
CN113963531A (zh) 用于行驶车辆保持安全车距的检测方法及其显示方式
CN117612364A (zh) 一种机动车的违章检测方法、装置、电子设备及存储介质
CN108665569A (zh) 一种车辆不停车收费支付系统及其方法
WO2023197409A1 (zh) 速度控制模型的生成方法、车辆控制方法及装置
CN104237808A (zh) 一种基于图像异常的电子警察系统补光灯故障检测方法
CN112101230A (zh) 公路隧道通行车辆前照灯开启检测方法及系统
CN116863707B (zh) 行车交通诱导方法、装置、设备及介质
CN110718064A (zh) 一种车辆违章检测方法和装置
CN116258993A (zh) 一种车辆增强辅助检测方法
CN113139459A (zh) 一种基于视频分析的道路出口道车流溢出实时检测方法
CN118038668A (zh) 城市交通路况的采集方法及系统

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE