WO2021022456A1 - Monitoring system and monitoring method for reducing vagrant conflicts - Google Patents

Monitoring system and monitoring method for reducing vagrant conflicts Download PDF

Info

Publication number
WO2021022456A1
WO2021022456A1 PCT/CN2019/099308 CN2019099308W WO2021022456A1 WO 2021022456 A1 WO2021022456 A1 WO 2021022456A1 CN 2019099308 W CN2019099308 W CN 2019099308W WO 2021022456 A1 WO2021022456 A1 WO 2021022456A1
Authority
WO
WIPO (PCT)
Prior art keywords
homeless
vagrants
management center
data
vagrant
Prior art date
Application number
PCT/CN2019/099308
Other languages
French (fr)
Chinese (zh)
Inventor
刘浩源
孙立晶
田丙奇
Original Assignee
唐山哈船科技有限公司
唐山圣因海洋科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 唐山哈船科技有限公司, 唐山圣因海洋科技有限公司 filed Critical 唐山哈船科技有限公司
Priority to PCT/CN2019/099308 priority Critical patent/WO2021022456A1/en
Publication of WO2021022456A1 publication Critical patent/WO2021022456A1/en

Links

Images

Classifications

    • 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
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/20Analysis of motion
    • G06T7/246Analysis of motion using feature-based methods, e.g. the tracking of corners or segments

Definitions

  • the present invention relates to the technical field of urban management, in particular to a monitoring system and a monitoring method for reducing conflicts among vagrants.
  • vagrants The city’s management of homeless vagrants is a social problem, which can easily cause many social problems, such as social security issues. vagrants often have their own scope of activities, and they are often unfriendly to newcomers who invade their scope. , Prone to conflicts.
  • the purpose of the present invention is to provide a monitoring system and a monitoring method for reducing conflicts among vagrants, which can track each vagrant, can grasp the activities of vagrants in the city, and can perform when the trajectory of the vagrants changes. Continue to track and observe, and feed back its real-time information to the social security department to prevent conflicts among the homeless, which is conducive to social security management and urban safety construction.
  • a monitoring system for reducing conflicts among vagrants includes a data collection device and a cloud management center, the data collection device is set on a road facility, and the data collection device Including camera devices, used to take pictures of homeless people in the city;
  • the cloud management center includes a wireless communication module for receiving information sent by all data collection devices;
  • Including the storage module used to record the face, body, clothing, walking posture, and frequent areas of all the vagrants in the city.
  • the road facilities include communities, parks, telephone poles along the road, advertising stands, guardrails, and other facilities that can be used as installation supports.
  • the adjacent camera devices meet the requirement that there is an overlap area between the two, perform external parameter calibration on the overlap area, establish an association matrix based on the external parameter calibration result, and use the association matrix mapping relationship to determine the tracking under the two cameras Whether the target is the same wanderer.
  • a method of monitoring using a monitoring system that reduces conflicts among homeless people includes the following steps:
  • the data collection device processes the video data collected by the camera device through the image analysis algorithm, obtains information such as the face, clothing, limbs, and walking posture of the homeless, saves it in the storage device, and sends it through the wireless communication device. Go to the cloud management center, so that each vagrant corresponds to a number, and establish a database of urban vagrants;
  • the image analysis algorithm includes data preprocessing, single-camera vagrant trajectory tracking, and cross-camera association.
  • the data preprocessing of the image analysis algorithm includes video streaming and framing, vagrant detection, and feature extraction.
  • the image is divided into frame images, and the wanderer detection and feature extraction are carried out through the image recognition algorithm.
  • the single-camera pedestrian trajectory tracking of the image analysis algorithm can achieve multi-target tracking, including the steps: the pedestrian frame detected in each frame of the image is tracked by the tracking algorithm Perform feature extraction and matching to obtain the trajectory; among them, pedestrian features are calculated by similarity, and an 8-dimensional vector is used to describe the state of the trajectory at a certain moment, which respectively represents the center position, aspect ratio, height, and corresponding in image coordinates of the pedestrian frame Use the Kalman filter to predict and update the trajectory.
  • the Kalman filter uses a constant velocity model and a linear observation model.
  • the cross-camera association in the image analysis algorithm is: calibrate the overlapping area of adjacent camera devices with external parameters, establish an association matrix based on the results of the external parameter calibration, and use the association matrix mapping relationship to determine whether the two cameras are under Whether the tracking target is the same wanderer;
  • the cloud management center obtains the video of the vagrant taken by the camera device, and analyzes the trajectory of each vagrant through the trajectory analysis algorithm;
  • the trajectory analysis algorithm is: store the trajectory data of the wanderers captured by each camera in the memory in the form of data frames, determine the number of data frames corresponding to each wanderer according to image recognition, and divide each wanderer The number of data frames corresponding to the person can be arranged according to the shooting time to analyze the trajectory of the homeless person;
  • S3 According to the trajectories of the wanderers analyzed in S2, analyze the areas where they frequently haunt and stay for a long time, and record the analysis results in the storage module, and build a map of wanderers' activities, including those that appear at different times Location, summarize the activity rules according to the activity map;
  • the present invention can grasp the activity situation of the homeless in the city, can carry out continuous tracking and observation when the activity trajectory of the homeless person changes, and feedback its real-time information to the public security department, In order to prevent conflicts between homeless people, it is conducive to social security management and urban safety construction.
  • Figure 1 is a schematic diagram of setting up a homeless activity map according to the present invention
  • Figure 2 is a schematic diagram of the treatment of the new arrivals of the present invention.
  • a monitoring system to reduce conflicts between vagrants the system includes a data collection device and a cloud management center, the data collection device is set on the road facilities, so The data collection device includes a camera device, which is used to take pictures of wanderers in the city;
  • the cloud management center includes a wireless communication module for receiving information sent by all data collection devices;
  • Including the storage module used to record the face, body, clothing, walking posture, and frequent areas of all the vagrants in the city.
  • the road facilities include communities, parks, telephone poles along the road, advertising racks, guardrails and other facilities that can be used as installation supports.
  • the adjacent camera devices meet the requirement that there is an overlap area between the two, perform external parameter calibration on the overlap area, establish an association matrix based on the external parameter calibration result, and use the association matrix mapping relationship to determine the tracking under the two cameras Whether the target is the same wanderer.
  • a method of monitoring using a monitoring system that reduces conflict among homeless people includes the following steps:
  • the data collection device processes the video data collected by the camera device through the image analysis algorithm, obtains information such as the face, clothing, limbs, and walking posture of the homeless, saves it in the storage device, and sends it through the wireless communication device. Go to the cloud management center, so that each tramp corresponds to a number, and establish a database of urban tramp;
  • the video data taken by the vagrant can be obtained in the following ways. First, after the citizen informs the vagrant, the staff call the surveillance video of the location where the vagrant appears, and intercept the video data containing the vagrant image for processing ; The second is that the staff finds the wanderers through real-time monitoring, and intercepts the video data containing the wanderer images for processing;
  • the image analysis algorithm includes data preprocessing, single-camera vagrant trajectory tracking, and cross-camera association.
  • the data preprocessing of the image analysis algorithm includes video streaming and framing, vagrant detection, and feature extraction.
  • the image is divided into frame images, and the wanderer detection and feature extraction are carried out through the image recognition algorithm.
  • the single-camera pedestrian trajectory tracking of the image analysis algorithm can achieve multi-target tracking, including the steps: the pedestrian frame detected in each frame of the image is tracked by the tracking algorithm Perform feature extraction and matching to obtain the trajectory; among them, pedestrian features are calculated by similarity, and an 8-dimensional vector is used to describe the state of the trajectory at a certain moment, which respectively represents the center position, aspect ratio, height, and corresponding in image coordinates of the pedestrian frame Use the Kalman filter to predict and update the trajectory.
  • the Kalman filter uses a constant velocity model and a linear observation model.
  • the cross-camera association in the image analysis algorithm is: calibrate the overlapping area of adjacent camera devices with external parameters, establish an association matrix based on the results of the external parameter calibration, and use the association matrix mapping relationship to determine whether the two cameras are under Whether the tracking target is the same wanderer;
  • the cloud management center obtains the video of the vagrant taken by the camera device, and analyzes the trajectory of each vagrant through the trajectory analysis algorithm;
  • the trajectory analysis algorithm is: store the trajectory data of the wanderers captured by each camera in the memory in the form of data frames, determine the number of data frames corresponding to each wanderer according to image recognition, and divide each wanderer The number of data frames corresponding to the person can be arranged according to the shooting time to analyze the trajectory of the homeless person;
  • S3 According to the trajectories of the wanderers analyzed in S2, analyze the areas where they frequently haunt and stay for a long time, and record the analysis results in the storage module, and build a map of wanderers' activities, including those that appear at different times Location, summarize the activity rules according to the activity map;
  • the dwelling time of the vagrant at a certain location can be judged. The greater the density, the longer the dwelling time at the location. Within the time limit, if the time spent at the place exceeds the set time threshold, the place can be considered as an activity area frequently haunted by the homeless;
  • a homeless person notified by a citizen or a staff member through monitoring is an unrecorded newcomer, first find the homeless person through video surveillance, and process the video data collected by the camera device through image analysis algorithms to obtain the homeless person Information such as face, clothing, limbs, walking posture, etc., is then found through the trajectory analysis algorithm, the tramp is continuously tracked, and the information is transmitted to the public security department in real time until he leaves or his activity pattern is stable;
  • vagrants notified by the citizens or the vagrants discovered by the staff through monitoring are vagrants recorded in the vagrants database, but are not in their frequent activity areas, first find the vagrants through the trajectory analysis algorithm, and perform Continue to track and transmit its information to the public security department in real time until it leaves or its activity is stable.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Human Resources & Organizations (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Alarm Systems (AREA)

Abstract

A monitoring system and a monitoring method for reducing vagrant conflicts. The system comprises a data acquisition device and a cloud management center. The data acquisition device is provided on a road facility. The data acquisition device comprises a camera device, a data processing device, and a wireless communication device. The cloud management center comprises a wireless communication module, a data processing module, and a storage module. By tracking the trajectory of each vagrant by means of the monitoring system, the activities of vagrants in a city can be mastered, continuous tracking and observation can be performed when the activity trajectories of the vagrants change, and real-time information of the vagrants can be fed back to a social security department, so as to prevent conflicts between the vagrants, thereby facilitating the social security management and urban security construction.

Description

一种减少流浪者冲突的监测系统及监测方法A monitoring system and monitoring method for reducing conflicts among wanderers 技术领域Technical field
本发明涉及城市管理技术领域,具体为一种减少流浪者冲突的监测系统及监测方法。The present invention relates to the technical field of urban management, in particular to a monitoring system and a monitoring method for reducing conflicts among vagrants.
背景技术Background technique
城市对无家可归的流浪者的管理是社会的难题,容易造成很多社会问题,例如社会治安问题,流浪者往往都有自己的活动范围,对于侵入其范围的新来者,往往并不友好,容易发生冲突。The city’s management of homeless vagrants is a social problem, which can easily cause many social problems, such as social security issues. vagrants often have their own scope of activities, and they are often unfriendly to newcomers who invade their scope. , Prone to conflicts.
如何摸清流浪者的情况,给出流浪者活动地图,并及时发现新来者,对城市管理很重要。How to find out the situation of the homeless, give a map of the activities of the homeless, and find the newcomers in time is very important to urban management.
发明内容Summary of the invention
本发明的目的在于提供一种减少流浪者冲突的监测系统及监测方法,能够对每个流浪者进行轨迹跟踪,能够掌握城市中流浪者的活动情况,在流浪者的活动轨迹出现变化时能够进行持续的跟踪观察,并将其实时的信息反馈给社会治安部门,以防止流浪者之间发生冲突,有利于社会治安管理和城市安全建设。The purpose of the present invention is to provide a monitoring system and a monitoring method for reducing conflicts among vagrants, which can track each vagrant, can grasp the activities of vagrants in the city, and can perform when the trajectory of the vagrants changes. Continue to track and observe, and feed back its real-time information to the social security department to prevent conflicts among the homeless, which is conducive to social security management and urban safety construction.
为实现上述目的,本发明提供如下技术方案:一种减少流浪者冲突的监测系统,所述系统包括数据采集装置和云端管理中心,所述数据采集装置设置在道路设施上,所述数据采集装置包括摄像装置,用于拍摄城市中的流浪者;In order to achieve the above objective, the present invention provides the following technical solution: a monitoring system for reducing conflicts among vagrants, the system includes a data collection device and a cloud management center, the data collection device is set on a road facility, and the data collection device Including camera devices, used to take pictures of homeless people in the city;
包括数据处理装置,用于数据的整合、分析、以及处理;Including data processing devices for data integration, analysis, and processing;
包括无线通讯装置,用于与云端管理中心进行无线通讯;Including a wireless communication device for wireless communication with the cloud management center;
所述云端管理中心包括无线通讯模块,用于接收所有数据采集装置发送的信息;The cloud management center includes a wireless communication module for receiving information sent by all data collection devices;
包括数据处理模块,用于数据的整合、分析、以及处理;Including data processing modules for data integration, analysis, and processing;
包括存储模块,用于记录城市内所有流浪者的面部、肢体、衣着、走路姿势、以及经常出没区域等信息。Including the storage module, used to record the face, body, clothing, walking posture, and frequent areas of all the vagrants in the city.
优选的,所述道路设施包括社区、公园、道路边的电线杆、广告架、护栏等能够作为安装支撑的设施。Preferably, the road facilities include communities, parks, telephone poles along the road, advertising stands, guardrails, and other facilities that can be used as installation supports.
优选的,相邻的所述摄像装置满足两两之间有重叠区域,对重叠区域做外参标定,通过外参标定结果建立关联矩阵,使用所述关联矩阵映射关系判断两个摄像头下的跟踪目标是否为同一流浪者。Preferably, the adjacent camera devices meet the requirement that there is an overlap area between the two, perform external parameter calibration on the overlap area, establish an association matrix based on the external parameter calibration result, and use the association matrix mapping relationship to determine the tracking under the two cameras Whether the target is the same wanderer.
一种使用减少流浪者冲突的监测系统进行监测的方法,包括以下步骤:A method of monitoring using a monitoring system that reduces conflicts among homeless people includes the following steps:
S1:数据采集装置通过图像分析算法对摄像装置采集的视频数据进行处理,获取流浪者的面部、衣着、肢体、走路姿势等信息,将其保存在存储装置中,同时通过无线通讯装置将其发送至云端管理中心,使每个流浪者均对应一个编号,建立城市流浪者资料库;S1: The data collection device processes the video data collected by the camera device through the image analysis algorithm, obtains information such as the face, clothing, limbs, and walking posture of the homeless, saves it in the storage device, and sends it through the wireless communication device. Go to the cloud management center, so that each vagrant corresponds to a number, and establish a database of urban vagrants;
所述图像分析算法:包括数据预处理、单摄像头流浪者轨迹跟踪和跨摄像头关联,所述图像分析算法的数据预处理包括视频取流切帧、流浪者检测和特征提取,获取监控视频将其切分成帧图像,经过图像识别算法进行流浪者检测和特征提取,所述图像分析算法的单摄像头行人轨迹跟踪可实现多目标跟踪,包括步骤:通过跟踪算法对每帧图像中检测到的行人框进行特征提取和匹配,获取轨迹;其中行人特征用相似度计算,使用一个8维向量去刻画轨迹在某时刻的状态,分别表示行人框的中心位置、纵横比、高度、以及在图像坐标中对应的速度信息,使用卡尔曼滤波器预测更新轨迹,所述卡尔曼滤波器采用匀速模型和线性观测模型,对于每条轨迹记录轨迹从上次匹配成功到当前的时间,当大于设定时间阈值时该轨迹终止;所述图像分析算法中跨摄像头关联为:对相邻摄像装置的重叠区域做外参标定,通过外参标定结果建立关联矩阵,使用 所述关联矩阵映射关系判断两个摄像装置下的跟踪目标是否为同一流浪者;The image analysis algorithm includes data preprocessing, single-camera vagrant trajectory tracking, and cross-camera association. The data preprocessing of the image analysis algorithm includes video streaming and framing, vagrant detection, and feature extraction. The image is divided into frame images, and the wanderer detection and feature extraction are carried out through the image recognition algorithm. The single-camera pedestrian trajectory tracking of the image analysis algorithm can achieve multi-target tracking, including the steps: the pedestrian frame detected in each frame of the image is tracked by the tracking algorithm Perform feature extraction and matching to obtain the trajectory; among them, pedestrian features are calculated by similarity, and an 8-dimensional vector is used to describe the state of the trajectory at a certain moment, which respectively represents the center position, aspect ratio, height, and corresponding in image coordinates of the pedestrian frame Use the Kalman filter to predict and update the trajectory. The Kalman filter uses a constant velocity model and a linear observation model. For each trajectory, the time from the last successful match to the current time is recorded, when it is greater than the set time threshold The trajectory is terminated; the cross-camera association in the image analysis algorithm is: calibrate the overlapping area of adjacent camera devices with external parameters, establish an association matrix based on the results of the external parameter calibration, and use the association matrix mapping relationship to determine whether the two cameras are under Whether the tracking target is the same wanderer;
S2:云端管理中心获得摄像装置拍摄的流浪者的视频,通过轨迹分析算法分析出每个流浪者的活动轨迹;S2: The cloud management center obtains the video of the vagrant taken by the camera device, and analyzes the trajectory of each vagrant through the trajectory analysis algorithm;
所述轨迹分析算法为:将每个摄像装置所拍摄的流浪者的轨迹数据以数据帧的形式存储在内存中,根据图像识别确定每个流浪者所对应的的数据帧数,将每个流浪者对应的数据帧数按照拍摄的时间进行排列即可以分析出流浪者的活动轨迹;The trajectory analysis algorithm is: store the trajectory data of the wanderers captured by each camera in the memory in the form of data frames, determine the number of data frames corresponding to each wanderer according to image recognition, and divide each wanderer The number of data frames corresponding to the person can be arranged according to the shooting time to analyze the trajectory of the homeless person;
S3:根据S2中分析出的流浪者的活动轨迹对其经常出没并长时间停留的区域进行分析,并将分析结果记录在存储模块中,并以此建立流浪者活动地图,包括不同时间出现的位置,根据活动地图归纳活动规律;S3: According to the trajectories of the wanderers analyzed in S2, analyze the areas where they frequently haunt and stay for a long time, and record the analysis results in the storage module, and build a map of wanderers' activities, including those that appear at different times Location, summarize the activity rules according to the activity map;
S4:当发现新的流浪者或者流浪者离开其经常活动的区域时,对该流浪者持续进行跟踪,将其信息实时传送至社会治安部门,直到其离开或者其活动规律稳定。S4: When a new homeless person or homeless person is found to leave the area where they are often active, continue to track the homeless person and transmit his information to the public security department in real time until he leaves or his activity is stable.
与现有技术相比,本发明的有益效果如下:Compared with the prior art, the beneficial effects of the present invention are as follows:
本发明通过对每个流浪者进行轨迹跟踪,能够掌握城市中流浪者的活动情况,在流浪者的活动轨迹出现变化时能够进行持续的跟踪观察,并将其实时的信息反馈给社会治安部门,以防止流浪者之间发生冲突,有利于社会治安管理和城市安全建设。By tracking the trajectory of each homeless person, the present invention can grasp the activity situation of the homeless in the city, can carry out continuous tracking and observation when the activity trajectory of the homeless person changes, and feedback its real-time information to the public security department, In order to prevent conflicts between homeless people, it is conducive to social security management and urban safety construction.
附图说明Description of the drawings
图1为本发明架设流浪者活动地图的示意图;Figure 1 is a schematic diagram of setting up a homeless activity map according to the present invention;
图2为本发明的新来流浪者处理的示意图。Figure 2 is a schematic diagram of the treatment of the new arrivals of the present invention.
具体实施方式detailed description
下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清 楚、完整地描述,显然,所描述的实施例仅仅是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,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,都属于本发明保护的范围。The technical solutions in the embodiments of the present invention will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.
请参阅图1至图2,本发明提供一种技术方案:一种减少流浪者冲突的监测系统,所述系统包括数据采集装置和云端管理中心,所述数据采集装置设置在道路设施上,所述数据采集装置包括摄像装置,用于拍摄城市中的流浪者;Please refer to Figures 1 to 2, the present invention provides a technical solution: a monitoring system to reduce conflicts between vagrants, the system includes a data collection device and a cloud management center, the data collection device is set on the road facilities, so The data collection device includes a camera device, which is used to take pictures of wanderers in the city;
包括数据处理装置,用于数据的整合、分析、以及处理;Including data processing devices for data integration, analysis, and processing;
包括无线通讯装置,用于与云端管理中心进行无线通讯;Including a wireless communication device for wireless communication with the cloud management center;
所述云端管理中心包括无线通讯模块,用于接收所有数据采集装置发送的信息;The cloud management center includes a wireless communication module for receiving information sent by all data collection devices;
包括数据处理模块,用于数据的整合、分析、以及处理;Including data processing modules for data integration, analysis, and processing;
包括存储模块,用于记录城市内所有流浪者的面部、肢体、衣着、走路姿势、以及经常出没区域等信息。Including the storage module, used to record the face, body, clothing, walking posture, and frequent areas of all the vagrants in the city.
具体来说,所述道路设施包括社区、公园、道路边的电线杆、广告架、护栏等能够作为安装支撑的设施。Specifically, the road facilities include communities, parks, telephone poles along the road, advertising racks, guardrails and other facilities that can be used as installation supports.
优选的,相邻的所述摄像装置满足两两之间有重叠区域,对重叠区域做外参标定,通过外参标定结果建立关联矩阵,使用所述关联矩阵映射关系判断两个摄像头下的跟踪目标是否为同一流浪者。Preferably, the adjacent camera devices meet the requirement that there is an overlap area between the two, perform external parameter calibration on the overlap area, establish an association matrix based on the external parameter calibration result, and use the association matrix mapping relationship to determine the tracking under the two cameras Whether the target is the same wanderer.
一种使用减少流浪者冲突的监测系统进行监测的方法,包括以下步骤:A method of monitoring using a monitoring system that reduces conflict among homeless people includes the following steps:
S1:数据采集装置通过图像分析算法对摄像装置采集的视频数据进行处理,获取流浪者的面部、衣着、肢体、走路姿势等信息,将其保存在存储装置中,同时通过无线通讯装置将其发送至云端管理中心,使每个流浪者均对应一个编号,建立城市流浪者资料库;S1: The data collection device processes the video data collected by the camera device through the image analysis algorithm, obtains information such as the face, clothing, limbs, and walking posture of the homeless, saves it in the storage device, and sends it through the wireless communication device. Go to the cloud management center, so that each tramp corresponds to a number, and establish a database of urban tramp;
对流浪者所拍摄的视频数据的获取,可以通过以下方式,一是市民在告知流浪者的情况后,工作人员调取流浪者出现地点的监控视频,并截取包含流浪者画面的视频数据进行处理;二是工作人员通过实时监控,发现流浪者,截取包含流浪者画面的视频数据进行处理;The video data taken by the vagrant can be obtained in the following ways. First, after the citizen informs the vagrant, the staff call the surveillance video of the location where the vagrant appears, and intercept the video data containing the vagrant image for processing ; The second is that the staff finds the wanderers through real-time monitoring, and intercepts the video data containing the wanderer images for processing;
所述图像分析算法:包括数据预处理、单摄像头流浪者轨迹跟踪和跨摄像头关联,所述图像分析算法的数据预处理包括视频取流切帧、流浪者检测和特征提取,获取监控视频将其切分成帧图像,经过图像识别算法进行流浪者检测和特征提取,所述图像分析算法的单摄像头行人轨迹跟踪可实现多目标跟踪,包括步骤:通过跟踪算法对每帧图像中检测到的行人框进行特征提取和匹配,获取轨迹;其中行人特征用相似度计算,使用一个8维向量去刻画轨迹在某时刻的状态,分别表示行人框的中心位置、纵横比、高度、以及在图像坐标中对应的速度信息,使用卡尔曼滤波器预测更新轨迹,所述卡尔曼滤波器采用匀速模型和线性观测模型,对于每条轨迹记录轨迹从上次匹配成功到当前的时间,当大于设定时间阈值时该轨迹终止;所述图像分析算法中跨摄像头关联为:对相邻摄像装置的重叠区域做外参标定,通过外参标定结果建立关联矩阵,使用所述关联矩阵映射关系判断两个摄像装置下的跟踪目标是否为同一流浪者;The image analysis algorithm includes data preprocessing, single-camera vagrant trajectory tracking, and cross-camera association. The data preprocessing of the image analysis algorithm includes video streaming and framing, vagrant detection, and feature extraction. The image is divided into frame images, and the wanderer detection and feature extraction are carried out through the image recognition algorithm. The single-camera pedestrian trajectory tracking of the image analysis algorithm can achieve multi-target tracking, including the steps: the pedestrian frame detected in each frame of the image is tracked by the tracking algorithm Perform feature extraction and matching to obtain the trajectory; among them, pedestrian features are calculated by similarity, and an 8-dimensional vector is used to describe the state of the trajectory at a certain moment, which respectively represents the center position, aspect ratio, height, and corresponding in image coordinates of the pedestrian frame Use the Kalman filter to predict and update the trajectory. The Kalman filter uses a constant velocity model and a linear observation model. For each trajectory, the time from the last successful match to the current time is recorded, when it is greater than the set time threshold The trajectory is terminated; the cross-camera association in the image analysis algorithm is: calibrate the overlapping area of adjacent camera devices with external parameters, establish an association matrix based on the results of the external parameter calibration, and use the association matrix mapping relationship to determine whether the two cameras are under Whether the tracking target is the same wanderer;
S2:云端管理中心获得摄像装置拍摄的流浪者的视频,通过轨迹分析算法分析出每个流浪者的活动轨迹;S2: The cloud management center obtains the video of the vagrant taken by the camera device, and analyzes the trajectory of each vagrant through the trajectory analysis algorithm;
所述轨迹分析算法为:将每个摄像装置所拍摄的流浪者的轨迹数据以数据帧的形式存储在内存中,根据图像识别确定每个流浪者所对应的的数据帧数,将每个流浪者对应的数据帧数按照拍摄的时间进行排列即可以分析出流浪者的活动轨迹;The trajectory analysis algorithm is: store the trajectory data of the wanderers captured by each camera in the memory in the form of data frames, determine the number of data frames corresponding to each wanderer according to image recognition, and divide each wanderer The number of data frames corresponding to the person can be arranged according to the shooting time to analyze the trajectory of the homeless person;
S3:根据S2中分析出的流浪者的活动轨迹对其经常出没并长时间停留的区 域进行分析,并将分析结果记录在存储模块中,并以此建立流浪者活动地图,包括不同时间出现的位置,根据活动地图归纳活动规律;S3: According to the trajectories of the wanderers analyzed in S2, analyze the areas where they frequently haunt and stay for a long time, and record the analysis results in the storage module, and build a map of wanderers' activities, including those that appear at different times Location, summarize the activity rules according to the activity map;
因为每4帧为一秒,根据数据帧数在某一拍摄地点的密度可判断出流浪者在某一地点的停留时间,密度越大,说明在该地点的停留时间越久,若流浪者在一定的时间期限内,在该地点停留的时间超过了设定的时间阀值,则可以认为该地点为该流浪者经常出没的活动区域;Because every 4 frames is one second, according to the density of the number of data frames in a certain shooting location, the dwelling time of the vagrant at a certain location can be judged. The greater the density, the longer the dwelling time at the location. Within the time limit, if the time spent at the place exceeds the set time threshold, the place can be considered as an activity area frequently haunted by the homeless;
S4:当发现新的流浪者或者流浪者离开其经常活动的区域时,对该流浪者持续进行跟踪,将其信息实时传送至社会治安部门,直到其离开或者其活动规律稳定,S4: When a new homeless person or a homeless person is found to leave the area where they are often active, continue to track the homeless person and transmit its information to the public security department in real time until he leaves or his activity pattern is stable.
市民告知的流浪者或者工作人员通过监控发现的流浪者为未经记录的新来者时,首先通过视频监控找到该流浪者,通过图像分析算法对摄像装置采集的视频数据进行处理,获取流浪者的面部、衣着、肢体、走路姿势等信息,然后通过轨迹分析算法找到该流浪者,对该流浪者进行持续的跟踪,将其信息实时传送至社会治安部门,直到其离开或者其活动规律稳定;When a homeless person notified by a citizen or a staff member through monitoring is an unrecorded newcomer, first find the homeless person through video surveillance, and process the video data collected by the camera device through image analysis algorithms to obtain the homeless person Information such as face, clothing, limbs, walking posture, etc., is then found through the trajectory analysis algorithm, the tramp is continuously tracked, and the information is transmitted to the public security department in real time until he leaves or his activity pattern is stable;
市民告知的流浪者或者工作人员通过监控发现的流浪者为记录在流浪者资料库中的流浪人员,但是不在其经常活动的区域时,首先通过轨迹分析算法找到该流浪者,对该流浪者进行持续的跟踪,将其信息实时传送至社会治安部门,直到其离开或者其活动规律稳定。When the vagrants notified by the citizens or the vagrants discovered by the staff through monitoring are vagrants recorded in the vagrants database, but are not in their frequent activity areas, first find the vagrants through the trajectory analysis algorithm, and perform Continue to track and transmit its information to the public security department in real time until it leaves or its activity is stable.
尽管已经示出和描述了本发明的实施例,对于本领域的普通技术人员而言,可以理解在不脱离本发明的原理和精神的情况下可以对这些实施例进行多种变化、修改、替换和变型,本发明的范围由所附权利要求及其等同物限定。Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, and substitutions can be made to these embodiments without departing from the principle and spirit of the present invention. And variations, the scope of the present invention is defined by the appended claims and their equivalents.

Claims (4)

  1. 一种减少流浪者冲突的监测系统,所述系统包括数据采集装置和云端管理中心,其特征在于:所述数据采集装置设置在道路设施上,所述数据采集装置包括摄像装置,用于拍摄城市中的流浪者;A monitoring system for reducing conflicts among wanderers, the system includes a data acquisition device and a cloud management center, and is characterized in that: the data acquisition device is set on a road facility, and the data acquisition device includes a camera device for photographing a city Wanderers in
    包括数据处理装置,用于数据的整合、分析、以及处理;Including data processing devices for data integration, analysis, and processing;
    包括无线通讯装置,用于与云端管理中心进行无线通讯;Including a wireless communication device for wireless communication with the cloud management center;
    所述云端管理中心包括无线通讯模块,用于接收所有数据采集装置发送的信息;The cloud management center includes a wireless communication module for receiving information sent by all data collection devices;
    包括数据处理模块,用于数据的整合、分析、以及处理;Including data processing modules for data integration, analysis, and processing;
    包括存储模块,用于记录城市内所有流浪者的面部、肢体、衣着、走路姿势、以及经常出没区域等信息。Including the storage module, used to record the face, body, clothing, walking posture, and frequent areas of all the vagrants in the city.
  2. 根据权利要求1所述的一种减少流浪者冲突的监测系统,其特征在于:所述道路设施包括社区、公园、道路边的电线杆、广告架、护栏等能够作为安装支撑的设施。The monitoring system for reducing conflicts among homeless people according to claim 1, characterized in that: the road facilities include communities, parks, telephone poles along the road, advertising stands, guardrails and other facilities that can be used as installation support.
  3. 根据权利要求1所述的一种减少流浪者冲突的监测系统,其特征在于:相邻的所述摄像装置满足两两之间有重叠区域。The monitoring system for reducing conflicts among vagrants according to claim 1, wherein the adjacent camera devices satisfy the overlapping area between two.
  4. 一种使用权利要求1-3所述的减少流浪者冲突的监测系统进行监测的方法,其特征在于,包括以下步骤:A method for monitoring using the monitoring system for reducing conflicts among homeless persons according to claims 1-3, characterized in that it comprises the following steps:
    S1:数据采集装置通过图像分析算法对摄像装置采集的视频数据进行处理,获取流浪者的面部、衣着、肢体、走路姿势等信息,将其保存在存储装置中,同时通过无线通讯装置将其发送至云端管理中心,使每个流浪者均对应一个编号,建立城市流浪者资料库;S1: The data collection device processes the video data collected by the camera device through the image analysis algorithm, obtains information such as the face, clothing, limbs, and walking posture of the homeless, saves it in the storage device, and sends it through the wireless communication device. Go to the cloud management center, so that each tramp corresponds to a number, and establish a database of urban tramp;
    S2:云端管理中心获得摄像装置拍摄的流浪者的视频,通过轨迹分析算法 分析出每个流浪者的活动轨迹;S2: The cloud management center obtains the video of the vagrant taken by the camera device, and analyzes the trajectory of each vagrant through the trajectory analysis algorithm;
    S3:根据S2中分析出的流浪者的活动轨迹对其经常出没并长时间停留的区域进行分析,并将分析结果记录在存储模块中,并以此建立流浪者活动地图,包括不同时间出现的位置,根据活动地图归纳活动规律;S3: According to the trajectories of the wanderers analyzed in S2, analyze the areas where they frequently haunt and stay for a long time, and record the analysis results in the storage module, and build a map of wanderers' activities, including those that appear at different times Location, summarize the activity rules according to the activity map;
    S4:当发现新的流浪者或者流浪者离开其经常活动的区域时,对该流浪者持续进行跟踪,将其信息实时传送至社会治安部门,直到其离开或者其活动规律稳定。S4: When a new homeless person or homeless person is found to leave the area where they are often active, continue to track the homeless person and transmit his information to the public security department in real time until he leaves or his activity is stable.
PCT/CN2019/099308 2019-08-05 2019-08-05 Monitoring system and monitoring method for reducing vagrant conflicts WO2021022456A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/099308 WO2021022456A1 (en) 2019-08-05 2019-08-05 Monitoring system and monitoring method for reducing vagrant conflicts

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/099308 WO2021022456A1 (en) 2019-08-05 2019-08-05 Monitoring system and monitoring method for reducing vagrant conflicts

Publications (1)

Publication Number Publication Date
WO2021022456A1 true WO2021022456A1 (en) 2021-02-11

Family

ID=74502523

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/099308 WO2021022456A1 (en) 2019-08-05 2019-08-05 Monitoring system and monitoring method for reducing vagrant conflicts

Country Status (1)

Country Link
WO (1) WO2021022456A1 (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102164270A (en) * 2011-01-24 2011-08-24 浙江工业大学 Intelligent video monitoring method and system capable of exploring abnormal events
US20120008868A1 (en) * 2010-07-08 2012-01-12 Compusensor Technology Corp. Video Image Event Attention and Analysis System and Method
CN102724482A (en) * 2012-06-18 2012-10-10 西安电子科技大学 Intelligent visual sensor network moving target relay tracking system based on GPS (global positioning system) and GIS (geographic information system)
CN105787469A (en) * 2016-03-25 2016-07-20 广州市浩云安防科技股份有限公司 Method and system for pedestrian monitoring and behavior recognition
CN106341661A (en) * 2016-09-13 2017-01-18 深圳市大道智创科技有限公司 Patrol robot
CN107370983A (en) * 2016-05-13 2017-11-21 腾讯科技(深圳)有限公司 Acquisition methods and device for the whereabouts track of video monitoring system
CN109472233A (en) * 2018-11-01 2019-03-15 济南创视睿智能科技有限公司 A kind of behaviortrace system

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120008868A1 (en) * 2010-07-08 2012-01-12 Compusensor Technology Corp. Video Image Event Attention and Analysis System and Method
CN102164270A (en) * 2011-01-24 2011-08-24 浙江工业大学 Intelligent video monitoring method and system capable of exploring abnormal events
CN102724482A (en) * 2012-06-18 2012-10-10 西安电子科技大学 Intelligent visual sensor network moving target relay tracking system based on GPS (global positioning system) and GIS (geographic information system)
CN105787469A (en) * 2016-03-25 2016-07-20 广州市浩云安防科技股份有限公司 Method and system for pedestrian monitoring and behavior recognition
CN107370983A (en) * 2016-05-13 2017-11-21 腾讯科技(深圳)有限公司 Acquisition methods and device for the whereabouts track of video monitoring system
CN106341661A (en) * 2016-09-13 2017-01-18 深圳市大道智创科技有限公司 Patrol robot
CN109472233A (en) * 2018-11-01 2019-03-15 济南创视睿智能科技有限公司 A kind of behaviortrace system

Similar Documents

Publication Publication Date Title
CN109819208B (en) Intensive population security monitoring management method based on artificial intelligence dynamic monitoring
Wheeler et al. Face recognition at a distance system for surveillance applications
WO2020042419A1 (en) Gait-based identity recognition method and apparatus, and electronic device
CN106650620B (en) A kind of target person identification method for tracing using unmanned plane monitoring
EP3333762A1 (en) Crowd analytics via one shot learning
CN107766819B (en) Video monitoring system and real-time gait recognition method thereof
CN107529221A (en) A kind of follow-up analysis system and method for combination video monitoring and Wi Fi positioning
US20170032182A1 (en) System for adaptive real-time facial recognition using fixed video and still cameras
CN111242025B (en) Real-time action monitoring method based on YOLO
CN106341661B (en) Patrol robot
CN111726586A (en) Production system operation standard monitoring and reminding system
CN110175587B (en) Video tracking method based on face recognition and gait recognition algorithm
CN107845234A (en) A kind of anti-anti- method of wandering away of system and scenic spot of wandering away in scenic spot
CN111401296B (en) Behavior analysis method, device and apparatus
CN109684494A (en) A kind of scenic spot looking-for-person method, system and cloud server
CN110633648A (en) Face recognition method and system in natural walking state
Prakash et al. Detecting and tracking of multiple moving objects for intelligent video surveillance systems
CN110674761A (en) Regional behavior early warning method and system
TWI779029B (en) A distributed object tracking system
CN110378292A (en) Three dimension location system and method
Behera et al. Multi-camera based surveillance system
CN109508657B (en) Crowd gathering analysis method, system, computer readable storage medium and device
WO2021022456A1 (en) Monitoring system and monitoring method for reducing vagrant conflicts
CN109858400A (en) Database matching system is captured in recognition of face
CN113963373A (en) Video image dynamic detection and tracking algorithm based system and method

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: 19940926

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19940926

Country of ref document: EP

Kind code of ref document: A1