阅读说明：本技术 基于智能视频分析技术的多人物跟踪检测方法 (Multi-person tracking detection method based on intelligent video analysis technology ) 是由 张加兵 胡晓晖 徐加兴 于 2018-07-23 设计创作，主要内容包括：本发明提供的基于智能视频分析技术的多人物跟踪检测方法,其主要特征在于,包括：第一步：设定主摄像机和从摄像机,并设定监控区域；第二步：采集监控区域的视频图像,并由主摄像机进行预处理；第三步：主摄像机检测视频信息,并根据运动目标移动情况,启动联动跟踪模式；第四步：摄像机采用检测人物头部的形式,对同一个目标进行运动跟踪检测；第五步：当运动人物目标离开监控区域时,主摄像机结束联动跟踪模式。本发明提供的基于智能视频分析技术的多人物跟踪检测方法,通过主摄像机启动联动跟踪模式,摄像机以检测人物头部的形式,对同一个运动人物目标进行实时跟踪,有效地避免当人物交叉重叠或者静止时跟丢人物目标的情况,具有重要的应用价值。(The invention provides a multi-person tracking detection method based on an intelligent video analysis technology, which is mainly characterized by comprising the following steps of: the first step is as follows: setting a master camera and a slave camera, and setting a monitoring area; the second step is that: collecting a video image of a monitoring area, and preprocessing the video image by a main camera; the third step: the main camera detects video information and starts a linkage tracking mode according to the moving condition of a moving target; the fourth step: the camera adopts a form of detecting the head of a person to perform motion tracking detection on the same target; the fifth step: and when the moving person target leaves the monitoring area, the main camera finishes the linkage tracking mode. According to the multi-person tracking detection method based on the intelligent video analysis technology, the linkage tracking mode is started through the main camera, the camera tracks the same moving person target in real time in the form of detecting the head of the person, the situation that the person is crossed and overlapped or lost when the person is static is effectively avoided, and the method has important application value.)

1. A multi-person tracking detection method based on an intelligent video analysis technology is mainly characterized by comprising the following steps:

the first step is as follows: setting a master camera and a slave camera, and setting a monitoring area;

the second step is that: collecting a video image of a monitoring area, and preprocessing the video image by a main camera;

the third step: the main camera detects video information and starts a linkage tracking mode according to the moving condition of a moving target;

the fourth step: the camera adopts a form of detecting the head of a person to perform motion tracking detection on the same target;

the fifth step: and when the moving person target leaves the monitoring area, the main camera finishes the linkage tracking mode.

2. The multi-person tracking detection method based on the intelligent video analysis technology as claimed in claim 1, which is mainly characterized in that: in the step of setting the master camera and the slave camera and setting the monitoring area, the master camera can only be 1, and the monitoring areas set by the cameras can be overlapped in a crossed manner.

3. The multi-person tracking detection method based on the intelligent video analysis technology as claimed in claim 1, which is mainly characterized in that: in the steps of collecting video images of a monitoring area and preprocessing by a main camera, a color image is converted into a gray image.

4. The multi-person tracking detection method based on the intelligent video analysis technology as claimed in claim 1, which is mainly characterized in that: and in the step of detecting video information by the main camera and starting a linkage tracking mode according to the moving condition of the moving target, the main camera analyzes the video to ensure that the moving person target is tracked in real time.

5. The multi-person tracking detection method based on the intelligent video analysis technology as claimed in claim 1, which is mainly characterized in that: in the step of detecting the head of a person by a camera in a manner of detecting the head of the person and performing motion tracking detection on the same target, the head detection of the person is divided into a plurality of sub-detection processes such as overhead detection, side detection, front detection, back-brain detection and the like.

Technical Field

The invention belongs to the technical field of security monitoring, and particularly relates to a multi-person tracking and detecting method based on an intelligent video analysis technology.

Background

In large-scale shopping malls, airports, vehicle exhibitions, museums, squares and other public places, people are often crowded, and the safety of the public places is a big matter about the life and property safety of people, so that in the large-scale public places with crowded people, a plurality of monitoring cameras are often arranged so as to observe the field conditions in time. Because the public places are often crowded, the phenomenon of cross overlapping between people is very serious, and general monitoring cameras are difficult to monitor each person in an area in real time, so that a plurality of potential safety hazards exist.

Disclosure of Invention

In view of this, the multi-person tracking and detecting method based on the intelligent video analysis technology provided by the invention can effectively solve the above problems.

The invention provides a multi-person tracking detection method based on an intelligent video analysis technology, which comprises the following steps:

the first step is as follows: setting a master camera and a slave camera, and setting a monitoring area;

the second step is that: collecting a video image of a monitoring area, and preprocessing the video image by a main camera;

the third step: the main camera detects video information and starts a linkage tracking mode according to the moving condition of a moving target;

the fourth step: the camera adopts a form of detecting the head of a person to perform motion tracking detection on the same target;

the fifth step: and when the moving person target leaves the monitoring area, the main camera finishes the linkage tracking mode.

The invention has the beneficial effects that: according to the multi-person tracking detection method based on the intelligent video analysis technology, the linkage tracking mode is started through the main camera, the camera tracks the same moving person target in real time in the form of detecting the head of the person, the person target is shot from different angles, the whole motion track can be tracked, the situation that the person is lost when the person is overlapped in a crossed mode or is static is effectively avoided, the detection accuracy is high, the real-time performance is good, the requirements of users are fully met, and the multi-person tracking detection method has important application value.

Drawings

In order to more clearly illustrate the patented embodiments or prior art solutions of the present invention, the drawings used in the description of the embodiments or prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained by those skilled in the art without inventive effort.

FIG. 1 is a schematic flow chart of the present invention.

Detailed Description

The present invention is further described in terms of the following examples, which are intended to illustrate and not limit the scope of the invention, which are set forth in the claims, and which are intended to be illustrative and not restrictive.

It should be noted that the drawings provided in the present embodiment are only schematic illustrations of the basic idea of the invention, and only the components related to the invention are shown in the drawings, and the layout of the components may be more complicated in practical implementation.

The invention provides a multi-person tracking detection method based on an intelligent video analysis technology, which comprises the following steps:

step S101: setting a master camera and a slave camera, and setting a monitoring area;

step S102: collecting a video image of a monitoring area, and preprocessing the video image by a main camera;

step S103: the main camera detects video information and starts a linkage tracking mode according to the moving condition of a moving target;

step S104: the camera adopts a form of detecting the head of a person to perform motion tracking detection on the same target;

step S105: and when the moving person target leaves the monitoring area, the main camera finishes the linkage tracking mode.

Further, in step S101, a master camera and a slave camera are set, and only 1 master camera is set in the monitoring area, and the monitoring areas set by the respective cameras may be overlapped with each other.

Further, in step S102, a video image of the monitored area is collected, and in the preprocessing performed by the main camera, the color image is first converted into a grayscale image.

Further, in step S103, the main camera detects video information, and starts a linkage tracking mode according to the moving situation of the moving object, and the main camera analyzes the video to ensure real-time tracking of the moving person object.

Further, in step S104, the camera detects the head of the person, and in the motion tracking detection of the same target, the detection of the head of the person is divided into a plurality of sub-detection processes, such as top detection, side detection, front detection, back-head detection, and the like.

The foregoing embodiments are provided merely for illustrating the principles of the invention and its advantages, rather than for limiting the invention, and it will be apparent to those skilled in the art that modifications and variations can be made in the above embodiments without departing from the spirit and scope of the invention, and it is intended that all equivalent modifications and variations can be made by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.