CN114529876A - Intelligent checking system for violation of regulations of public transport vehicle - Google Patents
Intelligent checking system for violation of regulations of public transport vehicleDownload PDFInfo
- Publication number
- CN114529876A CN114529876ACN202111678227.8ACN202111678227ACN114529876ACN 114529876 ACN114529876 ACN 114529876ACN 202111678227 ACN202111678227 ACN 202111678227ACN 114529876 ACN114529876 ACN 114529876A
- Authority
- CN
- China
- Prior art keywords
- module
- violation
- video
- bus
- management
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- 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
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
Translated fromChinese技术领域technical field
本发明涉及公交车辆违章稽查领域，具体涉及一种公交车辆违章智能稽查系统。The invention relates to the field of public transportation vehicle violation inspection, in particular to a public transportation vehicle violation intelligent inspection system.
背景技术Background technique
目前，对车辆的路面违章监管主要还是依赖交警的违章监控手段，但是，从预防的角度，我们对驾驶安全性的要求要高于交规，如何进一步的提高公交驾驶员安全驾驶、文明驾驶的意识，规范驾驶员的驾驶行为，安全管理部提出了在重点路口、重点站点增加高清视频监控手段，通过人工智能对路口、站点各种违法违规行为进行自动识别，主动预警。信息管理部根据这一要求，分析此要求通过安装高清视频监控摄像头可以实现，但对违操行为进行主动预警需要开展相关技术攻关和系统开发。At present, the road violation supervision of vehicles mainly relies on the traffic police's violation monitoring methods. However, from the perspective of prevention, our requirements for driving safety are higher than traffic regulations. How to further improve the awareness of safe and civilized driving of bus drivers In order to regulate the driving behavior of drivers, the Safety Management Department proposed to add high-definition video surveillance methods at key intersections and key sites, and use artificial intelligence to automatically identify various violations of laws and regulations at intersections and sites, and proactively give early warnings. According to this requirement, the Information Management Department analyzed that this requirement can be achieved by installing high-definition video surveillance cameras, but active early warning of violations requires relevant technical research and system development.
在实际运营中，大部分驾驶员虽能按章进站，但运营中仍存在以下几方面的问题有待提高与完善：In actual operation, although most drivers can enter the station according to the regulations, there are still problems in the following aspects that need to be improved and improved:
(一)部分驾驶员尚存在各类不文明驾驶的违规违纪行为(1) Some drivers still have all kinds of uncivilized driving violations of laws and disciplines
其中主要包括以下几类行为：These mainly include the following types of behaviors:
路口：路口实线变道、路口不按规定车道行驶、超速通过路口、路口未减速(刹车灯不亮)、路口未礼让行人、路口加塞、连续变道等(7类)；Crossroads: solid line change at the intersection, not driving in the specified lane at the intersection, speeding through the intersection, failing to slow down at the intersection (the brake light is not on), failing to yield to pedestrians at the intersection, blocking the intersection, changing lanes continuously, etc. (7 categories);
站点：车辆斜停、压线停站、未依次进出站、进出站未打方向灯、机动车道违规上下客、进站车速大于15公里、出站后连续变道等(7类)。Stations: Vehicles parked at an angle, stopped on the line, not entering and exiting the station sequentially, entering and leaving the station without turning on the signal, illegally picking up and dropping off passengers at the motor vehicle lane, entering the station at a speed of more than 15 kilometers, changing lanes continuously after exiting the station, etc. (7 categories).
(二)缺乏全方位记录监督驾驶员违规违纪行为的有效方法(2) There is a lack of effective methods for comprehensively recording and supervising drivers' violations of laws and disciplines
目前，集团仍以抽查、人工记录等方式在全市范围内进行违规违纪行为的记录、监督，其覆盖范围小，且检查人员数量配比较全市运营车辆有较大不足，仅能覆盖重点线路、区域、车站。监督记录的覆盖面、效率有所不足。At present, the group still records and supervises violations of laws and disciplines throughout the city by means of spot checks and manual records. The coverage is small, and the number of inspectors is insufficient compared with the vehicles operating in the city, which can only cover key routes and areas. ,station. The coverage and efficiency of supervision records are insufficient.
(三)缺乏针对公交车业务规范的自动识别技术手段(3) Lack of automatic identification technical means for bus business specifications
面对全市每日运送近百万人次的运营车辆，现有自动技术手段尚无法有效判别公交车驾驶行为。以现有路面摄像头为例，多为交管部门为普通道路流量管理及违法行为抓拍所设，其拍摄对象及判断依据均为针对普通社会车辆。一方面，现有路面设备的管理方多为市政部门，无法与集团共享视频数据源；另一方面，现有路面设备的仪器本身技术规范亦无法满足集团对日常公交车辆驾驶违纪行为的管理。In the face of the city's daily transport of nearly one million passengers, the existing automatic technology is still unable to effectively determine the bus driving behavior. Taking the existing road cameras as an example, most of them are set up by the traffic control department for the management of ordinary road traffic and the capture of illegal acts. On the one hand, the managers of the existing road equipment are mostly municipal departments, which cannot share video data sources with the group; on the other hand, the technical specifications of the existing road equipment itself cannot meet the group's management of daily bus driving violations.
发明内容SUMMARY OF THE INVENTION
本发明所要解决的技术问题是一种能够解决上述问题的公交车辆违章智能稽查系统，更进一步提高公交车辆的安全管理规范、提升整体的信息化、智能化水平，拟通过建设路面视频信息采集系统及公交车专用违规违纪算法系统的方式，结合人工智能算法及大数据分析技术。The technical problem to be solved by the present invention is an intelligent inspection system for bus violations that can solve the above problems, further improves the safety management standard of bus vehicles, and enhances the overall level of informatization and intelligence. And the method of the bus-specific violation and discipline algorithm system, combined with artificial intelligence algorithm and big data analysis technology.
本发明是通过以下技术方案来实现的：一种公交车辆违章智能稽查系统，包括有前端路面视频信息采集系统和后端公交车专用违规违纪行为算法分析系统、数据库，前端路面视频信息采集系统包括有路面视频监控采集设备；后端公交车专用违规违纪行为算法分析系统包括有边缘计算分析前端、中心管理端、应用端、移动端；中心管理段和相连接，边缘计算分析前端包括有多个边缘分析终端，边缘计算分析前端和路面视频监控采集设备连接。The present invention is realized by the following technical solutions: an intelligent inspection system for violation of regulations of public transport vehicles, including a front-end road video information collection system and a back-end bus dedicated algorithm analysis system and database for violation of regulations and disciplines, and the front-end road video information collection system includes: There are road video monitoring and collection equipment; the back-end bus-specific violation algorithm analysis system includes edge computing analysis front-end, central management end, application end, and mobile end; the central management section is connected to the connection, and the edge computing analysis front end includes multiple The edge analysis terminal, the edge computing analysis front-end and the road video surveillance and acquisition equipment are connected.
作为优选的技术方案，中心管理端包括有中心路由、异常处理中心、视频处理服务器、视频应用处理服务器，异常处理中心、视频处理服务器、视频应用处理服务器、移动端、中心端均连接中心路由。As a preferred technical solution, the central management terminal includes a central routing, an exception processing center, a video processing server, and a video application processing server, and the exception processing center, video processing server, video application processing server, mobile terminal, and central terminal are all connected to the central routing.
作为优选的技术方案，中心管理端和边缘计算分析前端之间通过4G网络或者5G网络连接。As a preferred technical solution, the central management terminal and the edge computing analysis front-end are connected through a 4G network or a 5G network.
作为优选的技术方案，边缘计算分析前端采用边缘计算技术，为前端路面视频信息采集和判定。As a preferred technical solution, the edge computing analysis front-end adopts edge computing technology to collect and determine the front-end road video information.
作为优选的技术方案，中心管理端对于前端判定违章信息进行分级分类管理，人工复判处置和对于所有边缘终端进行统一维护和自巡检。As a preferred technical solution, the central management terminal performs hierarchical and classified management on the front-end judgment violation information, manual re-judgment and disposal, and unified maintenance and self-inspection for all edge terminals.
作为优选的技术方案，应用端对于违章行为判定后，推送至监控大屏和监控岗位；最终实现实时抓取、实时判定、实时分类、实时处置、留证提醒。As a preferred technical solution, after the application terminal determines the illegal behavior, it will be pushed to the monitoring screen and monitoring post; finally, real-time capture, real-time determination, real-time classification, real-time disposal, and certificate retention reminders are realized.
作为优选的技术方案，数据库采用MYSQL作为系统数据库。As a preferred technical solution, the database adopts MYSQL as the system database.
作为优选的技术方案，路面视频监控采集设备内设置有通信模块、视频流管理模块、算法综合管理模块、视频数据记录模块、项目配置模块、日志模块；路面视频监控采集设备和边缘分析终端通过以太网方式与路由器相连。As a preferred technical solution, the road video monitoring and collection equipment is provided with a communication module, a video stream management module, an algorithm comprehensive management module, a video data recording module, a project configuration module, and a log module; connected to the router via the Internet.
作为优选的技术方案，边缘分析终端内包括目标识别算法模块、逻辑判定模块、站点建模模块、车牌识别模块、违章截图和记录模块、自动推送和上报模块、断点续传模块、设备自巡检模块、摄像机连接和调用模块。As a preferred technical solution, the edge analysis terminal includes a target recognition algorithm module, a logic judgment module, a site modeling module, a license plate recognition module, a violation screenshot and recording module, an automatic push and reporting module, a breakpoint resume module, and equipment self-inspection. Check module, camera connection and call module.
本发明的有益效果是：The beneficial effects of the present invention are:
1、可解决公交运营车辆在路面驾驶违规行为无法识别的问题，为精细化管理提供手段；1. It can solve the problem of unidentifiable driving violations of public transport vehicles on the road, and provide means for refined management;
2、是可解决公交运营车辆在路面驾驶违规数据无法记录的问题，为数据中台平台提供数据更多维度的数据资产；2. It is a data asset that can solve the problem that the illegal data of public transportation vehicles driving on the road cannot be recorded, and provide data with more dimensions for the data middle-end platform;
3、是可提高视频设备的资产复用效率，为盘活固定资产、提高信息化管理水平提供得力抓手。3. It can improve the asset reuse efficiency of video equipment, and provide a powerful handle for revitalizing fixed assets and improving the level of information management.
附图说明Description of drawings
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative efforts.
图1为本发明的整体系统架构图；1 is an overall system architecture diagram of the present invention;
图2为本发明的前端设备软件架构设计图；Fig. 2 is the front-end equipment software architecture design diagram of the present invention;
图3为本发明的Kafka系统架构图；Fig. 3 is the Kafka system architecture diagram of the present invention;
图4为本发明的深度学习算法流程图；Fig. 4 is the deep learning algorithm flow chart of the present invention;
图5为本发明的构建公交车目标检测网络结构图；Fig. 5 is the structure diagram of constructing bus target detection network of the present invention;
图6为本发明的主界面的显示图。FIG. 6 is a display diagram of the main interface of the present invention.
具体实施方式Detailed ways
本说明书中公开的所有特征，或公开的所有方法或过程中的步骤，除了互相排斥的特征和/或步骤以外，均可以以任何方式组合。All features disclosed in this specification, or all disclosed steps in a method or process, may be combined in any way except mutually exclusive features and/or steps.
本说明书包括任何附加权利要求、摘要和附图中公开的任一特征，除非特别叙述，均可被其他等效或具有类似目的的替代特征加以替换。即，除非特别叙述，每个特征只是一系列等效或类似特征中的一个例子而已。This specification, including any feature disclosed in any accompanying claims, abstract and drawings, may, unless expressly recited, be replaced by other equivalent or alternative features serving a similar purpose. That is, unless expressly stated otherwise, each feature is but one example of a series of equivalent or similar features.
在本发明的描述中，需要理解的是，术语“一端”、“另一端”、“外侧”、“上”、“内侧”、“水平”、“同轴”、“中央”、“端部”、“长度”、“外端”等指示的方位或位置关系为基于附图所示的方位或位置关系，仅是为了便于描述本发明和简化描述，而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作，因此不能理解为对本发明的限制。In the description of the present invention, it should be understood that the terms "one end", "the other end", "outside", "upper", "inside", "horizontal", "coaxial", "central", "end" ”, “length”, “outer end”, etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, which are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying the indicated device or Elements must have a particular orientation, be constructed and operate in a particular orientation and are therefore not to be construed as limitations of the invention.
此外，在本发明的描述中，“多个”的含义是至少两个，例如两个，三个等，除非另有明确具体的限定。In addition, in the description of the present invention, "plurality" means at least two, such as two, three, etc., unless expressly and specifically defined otherwise.
本发明使用的例如“上”、“上方”、“下”、“下方”等表示空间相对位置的术语是出于便于说明的目的来描述如附图中所示的一个单元或特征相对于另一个单元或特征的关系。空间相对位置的术语可以旨在包括设备在使用或工作中除了图中所示方位以外的不同方位。例如，如果将图中的设备翻转，则被描述为位于其他单元或特征“下方”或“之下”的单元将位于其他单元或特征“上方”。因此，示例性术语“下方”可以囊括上方和下方这两种方位。设备可以以其他方式被定向旋转90度或其他朝向，并相应地解释本文使用的与空间相关的描述语。Terms such as "upper," "upper," "lower," "lower," and the like used herein to indicate relative spatial positions are for ease of illustration to describe one element or feature as shown in the drawings relative to another A unit or feature relationship. The term spatially relative position may be intended to encompass different orientations of the device in use or operation in addition to the orientation shown in the figures. For example, if the device in the figures is turned over, elements described as "below" or "beneath" other elements or features would then be oriented "above" the other elements or features. Thus, the exemplary term "below" can encompass both an orientation of above and below. The device may be otherwise oriented, rotated 90 degrees or at other orientations and the spatially relative descriptors used herein interpreted accordingly.
在本发明中，除非另有明确的规定和限定，术语“设置”、“套接”、“连接”、“贯穿”、“插接”等术语应做广义理解，例如，可以是固定连接，也可以是可拆卸连接，或成一体；可以是机械连接，也可以是电连接；可以是直接相连，也可以通过中间媒介间接相连，可以是两个元件内部的连通或两个元件的相互作用关系，除非另有明确的限定。对于本领域的普通技术人员而言，可以根据具体情况理解上述术语在本发明中的具体含义。In the present invention, unless otherwise expressly specified and limited, the terms "arrangement", "socket connection", "connection", "penetration", "plug connection" and other terms should be understood in a broad sense, for example, it may be a fixed connection, It can also be detachable connection or integrated; it can be mechanical connection or electrical connection; it can be directly connected or indirectly connected through an intermediate medium, it can be the internal communication of two elements or the interaction of two elements relationship, unless otherwise expressly qualified. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.
如图1至图6所示，一种公交车辆违章智能稽查系统，包括有前端路面视频信息采集系统和后端公交车专用违规违纪行为算法分析系统、数据库，前端路面视频信息采集系统包括有路面视频监控采集设备；后端公交车专用违规违纪行为算法分析系统包括有边缘计算分析前端、中心管理端、应用端、移动端；中心管理段和相连接，边缘计算分析前端包括有多个边缘分析终端，边缘计算分析前端和路面视频监控采集设备连接。As shown in Figures 1 to 6, an intelligent inspection system for bus violations includes a front-end road video information collection system and a back-end bus-specific violation algorithm analysis system and database. The front-end road video information collection system includes a road surface video information collection system. Video surveillance and collection equipment; the back-end bus-specific algorithm analysis system for violations of discipline and discipline includes edge computing analysis front-end, central management end, application end, and mobile end; Terminals, edge computing analysis front-ends and road video surveillance and acquisition equipment are connected.
其中，前端设备采用的是Nvidia Jetson Nano组件,它具有小巧，高算力且低功耗等特点。NVIDIA Jetson Nano是个通用性极高的嵌入式高性能设备，适合绝大多数应用场景。非常合适作为连接摄像头的硬件设备，可以为视频AI解析提供有力支持。Among them, the front-end equipment adopts Nvidia Jetson Nano components, which have the characteristics of small size, high computing power and low power consumption. NVIDIA Jetson Nano is a highly versatile embedded high-performance device suitable for most application scenarios. It is very suitable as a hardware device for connecting cameras and can provide strong support for video AI analysis.
其中，中心管理端包括有中心路由、异常处理中心、视频处理服务器、视频应用处理服务器，异常处理中心、视频处理服务器、视频应用处理服务器、移动端、中心端均连接中心路由。Among them, the central management terminal includes a central router, an exception processing center, a video processing server, and a video application processing server. The exception processing center, video processing server, video application processing server, mobile terminal, and central terminal are all connected to the central routing.
其中，中心管理端和边缘计算分析前端之间通过4G网络或者5G网络连接。中心管理端对于前端判定违章信息进行分级分类管理，人工复判处置和对于所有边缘终端进行统一维护和自巡检。Among them, the central management terminal and the edge computing analysis front-end are connected through a 4G network or a 5G network. The central management terminal performs hierarchical and classified management on the front-end judgment violation information, manual re-judgment and disposal, and unified maintenance and self-inspection for all edge terminals.
其中，边缘计算分析前端采用边缘计算技术，为前端路面视频信息采集和判定。在部署的视频采集源多处，实现进出站违章算法4项(包括实线进出站、超速进站、横距过大、出站连续变道)、公交车专用车辆身份识别算法1项。Among them, the edge computing analysis front-end adopts edge computing technology to collect and determine the front-end road video information. In the deployed video collection sources, 4 algorithms for entry and exit violations (including entering and exiting the station on a solid line, entering and exiting the station overspeed, excessive horizontal distance, and continuous lane change at the exit) and 1 identification algorithm for bus-specific vehicles are implemented.
其中，中心管理端对于前端判定违章信息进行分级分类管理，人工复判处置和对于所有边缘终端进行统一维护和自巡检。Among them, the central management terminal performs hierarchical and classified management on the front-end judgment violation information, manual re-judgment and disposal, and unified maintenance and self-inspection for all edge terminals.
其中，应用端对于违章行为判定后，推送至监控大屏和监控岗位；最终实现实时抓取、实时判定、实时分类、实时处置、留证提醒。Among them, after the application side determines the illegal behavior, it pushes it to the monitoring big screen and monitoring post; finally realizes real-time capture, real-time determination, real-time classification, real-time disposal, and reminder of certificate retention.
其中，数据库采用MYSQL作为系统数据库。Among them, the database uses MYSQL as the system database.
其中，路面视频监控采集设备的软件设计采用模块化设计，实现模块之间的松耦合，易管理等特点。由于对于不同的项目，需要集成不同的算法模块，这套软件架构更加易于算法模块的落地调试。实现微小调整就能适应不同的应用场景。同时兼顾稳定性和代码的小巧灵活性，软件本身对CPU和内存的低占用，把更多的系统资源让步给算法模块。同时实现了实时视频记录及图像的压缩等模块。代码共分为通信模块，视频流管理模块，算法综合管理模块，视频数据记录模块，项目配置模块，日志模块。Among them, the software design of the road video surveillance and acquisition equipment adopts a modular design to achieve loose coupling between modules and easy management. Since different projects need to integrate different algorithm modules, this software architecture is easier to debug the algorithm modules. Small adjustments can be made to adapt to different application scenarios. At the same time, taking into account the stability and the small and flexible code, the software itself occupies low CPU and memory, giving more system resources to the algorithm module. At the same time, modules such as real-time video recording and image compression are implemented. The code is divided into communication module, video stream management module, algorithm comprehensive management module, video data recording module, project configuration module, log module.
其中，通信模块：与云端进行通信，上传视频解析中产生的视频及图像数据。Among them, the communication module: communicates with the cloud, and uploads the video and image data generated in the video analysis.
视频流管理模块：对图像采集，对采集频率设置及对图像编码。Video stream management module: image acquisition, setting of acquisition frequency and image encoding.
算法综合管理模块：基于Yolo的深度神经网络的对象识别和定位算法。Algorithm comprehensive management module: object recognition and localization algorithm based on Yolo's deep neural network.
视频数据记录模块：根据视频算法解析出的事件来记录相应的视频及图片。Video data recording module: record the corresponding video and pictures according to the events parsed by the video algorithm.
项目配置模块：控制配置算法及软件的各个模块的配置。Project configuration module: Control the configuration algorithm and the configuration of each module of the software.
日志模块：软件在运行时的日志信息，方便软件调试及问题定位。Log module: the log information of the software when it is running, which is convenient for software debugging and problem location.
其中，边缘分析终端内包括目标识别算法模块、逻辑判定模块、站点建模模块、车牌识别模块、违章截图和记录模块、自动推送和上报模块、断点续传模块、设备自巡检模块、摄像机连接和调用模块。Among them, the edge analysis terminal includes target recognition algorithm module, logic judgment module, site modeling module, license plate recognition module, illegal screenshot and recording module, automatic push and reporting module, breakpoint resume module, equipment self-inspection module, camera Connect and call modules.
其中，目标识别算法模块包含封装后人工智能车辆和行人等目标检测算法，并调用人工智能算法完成公交车目标检测。Among them, the target recognition algorithm module includes target detection algorithms such as artificial intelligence vehicles and pedestrians after packaging, and calls the artificial intelligence algorithm to complete the bus target detection.
逻辑判定模块，建立追踪器等配合算法完成目标的轨迹和3类违章事件的识别和判定。Logical decision module, establish tracker and other algorithms to complete the identification and judgment of target trajectory and 3 types of violation events.
站点建模模块。根据每个站点摄像机物理位置，划定ROI检测区域，测速区域和站点相机监控点位等。Site Modeling Module. According to the physical location of each site camera, the ROI detection area, the speed measurement area and the site camera monitoring point are delineated.
车牌识别模块，抓拍公交车正面照片，使用车牌识别算法，识别公交车牌信息。The license plate recognition module captures the front photo of the bus, and uses the license plate recognition algorithm to identify the bus license plate information.
违章截图和记录模块，根据算法和逻辑判定的违章事件，每个违章事件截取一张违章瞬间图片，图片上应包含车辆车牌和违章类型信息。Violation screenshot and record module, according to the illegal events determined by algorithm and logic, each illegal event intercepts a momentary picture of the violation, and the picture should contain the vehicle license plate and the type of violation information.
同时对于包含该违章事件的完整进出站过程，由软件进行录像和重新压缩编码，以720p分辨率录像，进行按事件存储，整体事件压缩后，文件大小不大于30mb。At the same time, for the complete inbound and outbound process including the violation event, the software will record and re-compress and encode it, record it in 720p resolution, and store it by event. After the overall event is compressed, the file size is not more than 30mb.
自动推送和上报模块，对于识别完成的违章事件和相关照片视频，核查运营车牌数据库后，确认为公交违章事件后，自动推送事件到中心管理服务器。The automatic push and reporting module, for the identified violations and related photos and videos, checks the operating license plate database, and automatically pushes the events to the central management server after confirming that it is a bus violation.
断点续传模块，能与中心服务器同步，自动判断完整事件材料是否传输完成，如因网络等问题中断，在恢复连接或服务后可以自动进行断点续传。The breakpoint resume module can synchronize with the central server and automatically determine whether the complete event material is transmitted. If it is interrupted due to network problems, it can automatically resume the breakpoint after the connection or service is restored.
设备自巡检模块，边缘端软件可以通过心跳信息的发送，与中心端软件同步，上报边缘硬件设备的工作状态，并支持正常运行情况下的远程自动被管理功能。Equipment self-inspection module, the edge software can synchronize with the central software by sending heartbeat information, report the working status of edge hardware devices, and support the remote automatic management function under normal operation.
摄像机连接和调用模块，支持rtsp调用主流摄像机视频流，支持onvif协议调用控制主流监控摄像机，支持通过api自动调用和控制球机转动和追踪目标。The camera connection and calling module supports rtsp to call mainstream camera video streams, supports onvif protocol calls to control mainstream surveillance cameras, and supports automatic calling and control of dome camera rotation and tracking targets through api.
本技术方案中，系统是跨平台的，系统的整体架构基于J2EE技术实现。对 UNIX、LINUX系统和Windows系统都有良好的支持。应用软件将能够跨平台运行，同时支持IBMAIX、HPUNIX、SOLORAS，LINIX， WINDOWSSERVER。而且可以在不同的层次(例如数据库层、应用层、发布层、通讯层、GIS支持层等)上采用不同的操作系统。In this technical solution, the system is cross-platform, and the overall architecture of the system is realized based on J2EE technology. It has good support for UNIX, LINUX system and Windows system. Application software will be able to run cross-platform, while supporting IBMAIX, HPUNIX, SOLORAS, LINIX, WINDOWSSERVER. Moreover, different operating systems can be used at different layers (eg database layer, application layer, publishing layer, communication layer, GIS support layer, etc.).
数据库选用MYSQL作为系统数据库，业务数据、分析数据、矢量地理信息数据均通过数据库存储和提供服务，同时应用软件各层面均支持可配置多地址设置，充分考虑并行服务器状态的运行需求。数据集成在数据中心实时数据基础上，通过实时通讯接口进一步提高数据时效性和完备性，通过数据抽取软件平台进行数据抽取和转换，确保数据鲜活性、一致性，以满足分析结果的动态和实时性。系统安全结合完整的用户/角色/权限管理及相关机制，确保系统应用安全性，确保不同层面的不同业务需求。The database uses MYSQL as the system database. Business data, analysis data, and vector geographic information data are all stored and provided through the database. At the same time, all levels of the application software support configurable multi-address settings, fully considering the running requirements of parallel server status. The data is integrated on the basis of the real-time data of the data center, and the timeliness and completeness of the data are further improved through the real-time communication interface. real-time. System security combines complete user/role/authority management and related mechanisms to ensure system application security and different business needs at different levels.
本技术方案在投入到具体使用时，由于每个公交站点都要安装至少一个前端设备，就会导致数据的高并发，高吞吐量，为了保证数据的实时性，高效性，稳定性，数据的传输采用了Kafka技术。When this technical solution is put into specific use, since each bus station must install at least one front-end device, it will lead to high data concurrency and high throughput. The transmission adopts Kafka technology.
Kafka是一种高吞吐量的分布式发布订阅消息系统，有如下特性：Kafka is a high-throughput distributed publish-subscribe messaging system with the following features:
通过O的磁盘数据结构提供消息的持久化，这种结构对于即使数以TB的消息存储也能够保持长时间的稳定性能。Provides message persistence through O's on-disk data structure, which can maintain long-term stable performance for even terabytes of message storage.
高吞吐量：即使是非常普通的硬件Kafka也可以支持每秒数百万的消息。High throughput: Even very modest hardware Kafka can support millions of messages per second.
支持通过Kafka服务器和消费机集群来分区消息。Supports partitioning of messages through clusters of Kafka servers and consumers.
支持Hadoop并行数据加载。Support Hadoop parallel data loading.
本技术方案在采用深度学习的方法对行驶公交车进行检测，基于深度学习的公交检测技术存在以下优点：In this technical solution, the deep learning method is used to detect the running bus, and the bus detection technology based on the deep learning has the following advantages:
1.相对于传统算法，深度学习学习能力更强，检测精度更高；1. Compared with traditional algorithms, deep learning has stronger learning ability and higher detection accuracy;
2.深度学习的神经网络层数很多，宽度很广，理论上可以映射到任意函数，能解决相对复杂的问题；2. The neural network of deep learning has a large number of layers and a wide width. In theory, it can be mapped to any function and can solve relatively complex problems;
3.深度学习高度依赖数据，数据量越大，其表现越好，甚至在图像识别、面部识别等部分领域已经超过了人类的表现；3. Deep learning is highly dependent on data. The larger the amount of data, the better its performance, even surpassing human performance in some fields such as image recognition and facial recognition;
4.由于深度学习的优异表现，有很多框架可以使用，如TensorFlow、Pytorch 等。4. Due to the excellent performance of deep learning, there are many frameworks that can be used, such as TensorFlow, Pytorch, etc.
本技术方案系统总体分为两部分：一是前端路面视频信息采集系统。二是后端公交车专用违规违纪行为算法分析系统。其中包括针对路口违规行为识别算法7项、进出站违纪行为算法7项、公交车专用车辆身份识别算法2项、路面车辆流量统计算法1项。The technical solution system is generally divided into two parts: one is the front-end road video information collection system. The second is the back-end bus-specific algorithm analysis system for violations of discipline and discipline. These include 7 algorithms for identifying illegal behaviors at intersections, 7 algorithms for disciplinary violations at entry and exit stations, 2 algorithms for identification of special bus vehicles, and 1 algorithm for road traffic flow statistics.
系统建设后，一是可解决公交运营车辆在路面驾驶违规行为无法识别的问题，为集团精细化管理提供手段；二是可解决公交运营车辆在路面驾驶违规数据无法记录的问题，为集团数据中台平台提供数据更多维度的数据资产；三是可提高视频设备的资产复用效率，为集团盘活固定资产、提高信息化管理水平提供得力抓手。After the construction of the system, firstly, it can solve the problem that the illegal driving behavior of public transport vehicles on the road cannot be identified, and provide means for the group's refined management; The platform provides data assets with more dimensions of data; thirdly, it can improve the asset reuse efficiency of video equipment, and provide a powerful tool for the group to revitalize fixed assets and improve the level of information management.
以上所述，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何不经过创造性劳动想到的变化或替换，都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应该以权利要求书所限定的保护范围为准。The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited to this, and any changes or substitutions that are not conceived of without creative work should be included within the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope defined by the claims.
Claims (9)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111678227.8ACN114529876A (en) | 2021-12-31 | 2021-12-31 | Intelligent checking system for violation of regulations of public transport vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111678227.8ACN114529876A (en) | 2021-12-31 | 2021-12-31 | Intelligent checking system for violation of regulations of public transport vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114529876Atrue CN114529876A (en) | 2022-05-24 |
Family
ID=81620638
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111678227.8APendingCN114529876A (en) | 2021-12-31 | 2021-12-31 | Intelligent checking system for violation of regulations of public transport vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114529876A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114979111A (en)* | 2022-06-09 | 2022-08-30 | 王盛涵 | Intelligent intersection police system based on edge calculation and monitoring method thereof |
| CN116386296A (en)* | 2023-03-10 | 2023-07-04 | 启明信息技术股份有限公司 | System and method for reporting vehicle status alarm data of commercial vehicle recorder |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101438492B1 (en)* | 2013-05-14 | 2014-09-12 | 서울여자대학교 산학협력단 | System for recognizing video using violation car detection and method therefor |
| CN205899808U (en)* | 2016-08-16 | 2017-01-18 | 山西省交通科学研究院 | Bus stop detecting system that breaks rules and regulations |
| CN109686099A (en)* | 2018-12-24 | 2019-04-26 | 航天信息股份有限公司 | A kind of bus zone illegal traffic vehicle supervision method and system |
| CN112289036A (en)* | 2020-09-02 | 2021-01-29 | 侯晓峰 | Scene type violation attribute identification system and method based on traffic semantics |
- 2021
- 2021-12-31CNCN202111678227.8Apatent/CN114529876A/enactivePending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101438492B1 (en)* | 2013-05-14 | 2014-09-12 | 서울여자대학교 산학협력단 | System for recognizing video using violation car detection and method therefor |
| CN205899808U (en)* | 2016-08-16 | 2017-01-18 | 山西省交通科学研究院 | Bus stop detecting system that breaks rules and regulations |
| CN109686099A (en)* | 2018-12-24 | 2019-04-26 | 航天信息股份有限公司 | A kind of bus zone illegal traffic vehicle supervision method and system |
| CN112289036A (en)* | 2020-09-02 | 2021-01-29 | 侯晓峰 | Scene type violation attribute identification system and method based on traffic semantics |
Non-Patent Citations (1)
| Title |
|---|
| 佟守愚, 程三伟, 李江, 付萍: "基于视频技术的交通违章处理系统的设计与实现", 计算机测量与控制, no. 10, 25 October 2005 (2005-10-25)* |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114979111A (en)* | 2022-06-09 | 2022-08-30 | 王盛涵 | Intelligent intersection police system based on edge calculation and monitoring method thereof |
| CN116386296A (en)* | 2023-03-10 | 2023-07-04 | 启明信息技术股份有限公司 | System and method for reporting vehicle status alarm data of commercial vehicle recorder |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111275980A (en) | Big data application platform based on Internet + intelligent traffic video monitoring management system | |
| CN104200671B (en) | A kind of virtual bayonet socket management method based on large data platform and system | |
| CN112258842A (en) | Traffic monitoring method, device, equipment and storage medium | |
| CN104616501B (en) | Vehicle peccancy parking detecting system based on intelligent vision and method | |
| CN117319609A (en) | Internet of things big data intelligent video monitoring system and method | |
| CN103065459B (en) | The intelligent transportation integration control platform system of sing on web geographic information system technology | |
| CN101692310B (en) | Comprehensive video monitoring system of intelligent traffic | |
| US10223911B2 (en) | Video data and GIS mapping for traffic monitoring, event detection and change prediction | |
| CN107454364B (en) | Distributed real-time image acquisition and processing system in video monitoring field | |
| CN106056517A (en) | Smart city management system | |
| CN102081844A (en) | Traffic video behavior analyzing and alarming server | |
| CN201535951U (en) | Intelligent traffic integrated video monitoring system | |
| CN110751373A (en) | Communication vehicle scheduling method and system for emergency rescue and communication vehicle | |
| CN102708603A (en) | GIS (Geographic Information System)-based vehicle-mounted recorder for monitoring vehicle | |
| CN114529876A (en) | Intelligent checking system for violation of regulations of public transport vehicle | |
| CN112185121A (en) | Traffic accurate law enforcement method and equipment based on 5G | |
| CN115248880A (en) | Smart city security monitoring system | |
| CN104835007A (en) | Gridded intelligent linkage type campus security management integrated system | |
| CN104660969A (en) | System and method for achieving high-definition intelligent toll-gate management based on GIS map and video | |
| CN110264716A (en) | A kind of intelligent transportation system and application method based on Internet of Things | |
| CN105118291A (en) | Road traffic flow statistic comprehensive monitoring system | |
| CN103093579B (en) | Debris flow or landslide alarm system based on videos | |
| CN109859488B (en) | Cloned taxi detection method and detection system | |
| CN210166932U (en) | Road maintenance intelligent management system | |
| CN206039847U (en) | Smart Card Networking System |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |