Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Characteristic point analysis based multi-target separation predicting method

A prediction method and multi-objective technology, applied in the field of video surveillance image processing, can solve problems such as failure, achieve the effect of solving mutual interference, realizing recognition and tracking monitoring

Inactive Publication Date: 2008-04-09
SEU INTELLIGENCE SYST CO LTD
View PDF0 Cites 45 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Now, above-mentioned prior art just seems powerless
In addition, in the above two matching algorithms (linear one-step filter prediction or Kalman filter method), the search for the target object is solved by moving the object in the front and rear frames with the closest distance, which often fails in the case of multiple targets and fast movement

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
  • Characteristic point analysis based multi-target separation predicting method
  • Characteristic point analysis based multi-target separation predicting method
  • Characteristic point analysis based multi-target separation predicting method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The main steps of the multi-target separation prediction method of this embodiment are shown in Figure 1, and its basic process is: after completing a matching and filtering step according to the prior art, use the Harris operator to find out the angle in each moving target object. points, and then calculate and save the activity feature vector according to the results of motion detection, clustering and the first matched filtering. According to the combination of activity feature vectors, the general composite objects with similar characteristics are merged. Finally, a judgment is made on the moving target object and combined with the activity feature vector for secondary matching.

[0030] FIG. 2 is a logic block diagram of specific steps of secondary prediction in the embodiment of FIG. 1 . First, according to the number and similarity of the active feature vectors, find the corresponding object of the target object in the previous frame in the current frame. If the...

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 relates to a multi-target division prognostication method based on feature analysis and belongs to video monitoring image processing technical field. The method includes extracting background, determining motion detecting threshold, performing clustering on the motion detection and processing into rectangles, performing first matching and wave filtering, determining corner points, forming vectors, and performing second matching. With the invention, no influence on the analysis prognostication results occurs even if the target object is shielded locally; therefore problem of interference among mobile targets which cannot be solved with the prior arts is solved. By applying the invention on a video monitoring system, recognition, tracking and monitoring on adjacent targets can be realized effectively.

Description

technical field [0001] The invention relates to a method for identifying adjacent multi-targets in a surveillance video, in particular to a method for matching and separating adjacent multi-targets by using image feature point analysis, and belongs to the technical field of video surveillance image processing. Background technique [0002] At present, the processing of video images to achieve various monitoring purposes such as identification and tracking of target objects has been widely used in many fields. In the prior art, a commonly used method for detecting moving objects in video images is background subtraction. The detection and tracking of background subtraction generally includes the following steps: [0003] 1. Separation of the background - Extract the background by eliminating the interference caused by the foreground movement, and then separate the background from the foreground to achieve the purpose of capturing the target object in the picture. [0004] B...

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): H04N7/18G06T7/00G06K9/46G06K9/62
Inventor 王向宏
Owner SEU INTELLIGENCE SYST CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com