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

Dynamic image moving object detection method

A technology of moving targets and detection methods, which is applied in the fields of computer vision and image processing, and can solve the problems that the Chan-Vese algorithm cannot obtain results, etc.

Inactive Publication Date: 2013-06-26
CHANGSHU RES INSTITUE OF NANJING UNIV OF SCI & TECH
View PDF2 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the wall of the target with a hollow area is relatively thick, the Chan-Vese algorithm often cannot get the correct result

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
  • Dynamic image moving object detection method
  • Dynamic image moving object detection method
  • Dynamic image moving object detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] In order to test the implementation effect of the present invention, specific examples of the present invention will be described below.

[0072] Experiments were carried out using actual image sequences, figure 2 is the image of the previous frame of two adjacent frames, image 3 It is the next frame image of two adjacent frames.

[0073] The result is as Figure 4~6 shown, where Figure 4 is the difference result of two frames of images, Figure 5 In order to improve the segmentation results of the Chan-Vese algorithm, Figure 6 For improved results after region growing.

[0074] It can be seen that through Gaussian filtering, image difference and active contour algorithm segmentation, the two moving persons in the image sequence can be correctly detected. However, due to some small changes in the background and some noise interference during the shooting process, a small amount of background is also detected, and the detection effect is further improved by reg...

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 dynamic image moving object detection method. The method includes firstly, reading two images of time-consecutive frame and respectively subjecting the images to Gaussian filtering; secondly, calculating consecutive frame differential images to obtain a binary image with moving information; thirdly, utilizing the improved Chan-Vese algorithm to detect the moving object of the image; and finally, utilizing the improved region growing algorithm to detect the accuracy of the moving object. The two consecutive frame differential images are used as a seed pixel point set of the moving object, the Sobel edge detection operator is used for detecting the pixels around the seed pixel, the pixels around the seed pixel are marked as moving object pixels if the pixels around the seed pixel are detected as edge pixels, the detected edge pixels and the moving object detection result are mixed, and accordingly the moving object can be detected accurately.

Description

technical field [0001] The invention relates to the fields of computer vision and image processing, especially the technology for detecting moving objects in dynamic images. Background technique [0002] Moving object detection is a research subject with application value that arises with the development of video technology, and has important applications in the fields of object tracking, video surveillance, and precision guidance. Dynamic image moving object detection refers to removing the static background from the video stream, detecting the moving object and the moving information it carries, and the effective segmentation of the moving object is very critical for post-processing such as object classification and tracking. [0003] Under the condition of a still camera, the key to moving target detection is the description model of the background image, that is, the background model. Background modeling is a basic problem in computer vision. Many scholars at home and ab...

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 李萌
Owner CHANGSHU RES INSTITUE OF NANJING UNIV OF SCI & TECH
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