Video summary generation method that can solve multi-target collision and occlusion problems

A video summarization and multi-target technology, applied in the field of video summarization generation, can solve the problems of many times of target traversal and position adjustment, time-consuming summarization generation process, complex data structure, etc., and achieve the goal of maintaining the consistency of target timing and natural and smooth look and feel Effect

Active Publication Date: 2020-12-11
CHINA CHANGFENG SCI TECH IND GROUPCORP
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The data structure of this method is complex, and the number of target traversal and position adjustments during collision detection is large, which makes the summary generation process time-consuming

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
  • Video summary generation method that can solve multi-target collision and occlusion problems
  • Video summary generation method that can solve multi-target collision and occlusion problems
  • Video summary generation method that can solve multi-target collision and occlusion problems

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention provides a collision and solve multi-objective occlusion video summary generation method, comprising background reconstruction module, object detection module, a target tracking module, the processing module after the target track, the target trajectory generation module, the video summary generation module, the bACKGROUND said reconstruction module is a Gaussian mixture model adaptive to video image processing, which is determined for each pixel is foreground or background, foreground and background images obtained, and real-time reconstruction of the background model; using the object detection module bACKGROUND detecting a new image into the foreground of the scene module obtained by reconstruction of all lumps and agglomerates will be smaller (probably caused by noise) that has been tracked and the pellet discarded overlapping clumps, and the image edge detection and motion coincidence detection screening, discarding substandard agglomerates, agglo...

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 provides a video synopsis generation method capable of solving the multi-target collision and occlusion problem. The method comprises a background reconstruction module, a target detection module, a target tracking module, a target trajectory post-processing module, a target trajectory generation module and a video synopsis generation module. The method is an object-based dynamic video synopsis generation method; the method carries out intelligent analysis processing on surveillance videos, carries out detection and tracking on targets in a source video and extracts trajectory information of target positions and sizes and the like, and generates a concentrated video comprising all of the targets through trajectory combination and optimization; and the method can reduce video space redundancy and time redundancy.

Description

Technical field [0001] The present invention belongs to the technical field of intelligent video surveillance and image analysis, relates to a type of video collision solve multi-objective problem and occlusion digest generation method. Background technique [0002] Video surveillance system technology as a widely used means of prevention is playing an increasingly important role in the construction of a comprehensive prevention and control system of social security in the city. However, a growing number of various types of cameras day and night camera, the "visible" problem has been satisfactorily resolved, but the vast amounts of video data, look up like a needle in a haystack, traditional tactics to sea-based video Find the clues investigators have been unable to cope with large video data era. With the continuous expansion of the scale of the system, how quickly and accurately navigate and find clues in the mass video, has become urgent to solve the problem. [0003] Video Su...

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
Patent Type & Authority Patents(China)
IPC IPC(8): H04N21/8549G06T7/246
CPCG06T7/20G06T2207/10016G06T2207/30242H04N21/8549
Inventor 张丹普张晓林王亚静
Owner CHINA CHANGFENG SCI TECH IND GROUPCORP
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