Method and system for sensing moving objects in video scene

A technology for moving objects and video scenes, applied in the field of video analysis, to achieve the effect of continuous perception

Active Publication Date: 2013-04-03
UNIV OF SCI & TECH OF CHINA
View PDF7 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method and system for the perception of moving objects in video scenes, which solves the problem of capturing and tracking moving objects in complex scenes, and realizes the continuous perception of the entire movement process of moving objects

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and system for sensing moving objects in video scene
  • Method and system for sensing moving objects in video scene
  • Method and system for sensing moving objects in video scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0019] figure 1 A flow chart of a method for detecting a moving object in a video scene provided by Embodiment 1 of the present invention mainly includes the following steps:

[0020] Step 101, capturing a moving target.

[0021] The invention can be used to capture the moving target in the video stream captured by the camera in real time, and can also be used to capture the moving target in the video file.

[0022] The following is an example of how to capture a moving target by combining the inter-frame difference method and the background difference method.

[0023] First, frame data is extracted from video data (video stream or video file) and converted to RGB (tri-color) images. For example, for the DH-IPC-HF3101P bullet camera, use the data callback function (void CALLBACK DecCBFun(long nPort, char*pBuf, long nSize, FRAME_INFO*pFramelnfo, long nReserved1, long nReserved2) of its SDK (Software Development Kit) Extract frame data and convert the extracted frame data (YV...

Embodiment 2

[0047] figure 2 A schematic diagram of a system for detecting moving objects in a video scene provided by Embodiment 2 of the present invention, as shown in figure 2 As mentioned, the system mainly includes:

[0048] The moving target capture module 21 is used to detect the foreground pixels of the image using the inter-frame difference method and the background difference method, and fuse the results of both detections to obtain a foreground image that includes a moving target and its moving region;

[0049] The moving target tracking module 22 is used to extract a foreground block representing a certain moving target position in the foreground image, and track the foreground block until it leaves the video scene;

[0050] The moving object information generation module 23 is configured to generate summary information including the attributes and motion of the moving object corresponding to the foreground block according to the moving state of the moving object corresponding...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a method and a system for sensing moving objects in a video scene. The method includes capturing the moving objects; detecting foreground pixel of an image by means of interframe difference method and background difference method, integrating detecting results of the two methods, and acquiring a foreground image containing the moving objects and moving areas thereof; tracking the moving objects: extracting a foreground block indicating a position of a certain moving object in the foreground image, and tracking the foreground block until the foreground block is out of the video scene; and generating moving object information: generating abstract information containing attributions of the moving objects and moving conditions according to moving conditions of the moving object, corresponding to the foreground block, in the video scene. By the method for sensing the moving objects in the video scene, continuous sensing of the moving objects during integral moving process is realized.

Description

technical field [0001] The invention relates to the field of video analysis, in particular to a method and system for sensing moving objects in a video scene. Background technique [0002] With the proposal and promotion of Safe City, Internet of Things, and Smart City, video surveillance has been greatly developed and has been widely used in urban security monitoring, traffic scene monitoring, etc. Among them, the real-time perception of moving targets appearing in the scene, and the acquisition of target attribute information such as the target's trajectory, appearance time, and target color are the basic and important contents of intelligent video surveillance. [0003] However, in the prior art, the video monitoring technology cannot accurately perceive the moving object in the scene, therefore, cannot accurately obtain the attribute information of the moving object in the scene. Contents of the invention [0004] The object of the present invention is to provide a me...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06T7/20
Inventor 陈宗海赵宇宙张陈斌郭明玮项俊平
Owner UNIV OF SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products