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

A Dynamic Background Matching Method for Moving Object Detection

A dynamic background and matching method technology, applied in the field of image processing, can solve the problems of cumbersome steps, unsatisfactory and low efficiency in occasions with very high real-time requirements, and achieve the effect of simplifying the background modeling algorithm and high background matching accuracy

Active Publication Date: 2022-01-28
SOUTHWEAT UNIV OF SCI & TECH
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Most of the existing dynamic background modeling and matching algorithms are relatively complex. For example, the widely used mixed Gaussian background modeling requires a lot of calculations on the image, and the efficiency is low. It is not ideal in some occasions with very high real-time requirements.
The traditional background matching method generally needs to extract the corner points, and then match the corner points on the two frames of images, and filter out the unreasonable matching points
This method is cumbersome and time-consuming, and it is difficult to meet the real-time requirements

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
  • A Dynamic Background Matching Method for Moving Object Detection
  • A Dynamic Background Matching Method for Moving Object Detection
  • A Dynamic Background Matching Method for Moving Object Detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] It only needs to perform an overall translation traversal operation on the five matching area blocks to find the best matching offset. Figure 5 (a) and (b) are two images separated by 3 frames, Figure 5 (c) is a schematic diagram of superimposing the background at the same position after being translated by using 5 matching area blocks for translation matching calculation.

[0043] In this method, 4+1 image areas are used as matching blocks, among which 4 area matching blocks are close to the four corners of the image, and 1 area matching block is randomly selected. In order to ensure that the selected matching block contains certain texture information and avoid directly selecting the position of the pixel block to select a large area of ​​the same pixel, resulting in inaccurate background matching, edge detection is first performed on each frame of the processed image. Remove the outermost image that may move out of the field of view, and search for the first edge ...

Embodiment 2

[0046] The image difference method mentioned in step S2 includes inter-frame difference and multi-frame difference multiplication method.

[0047] The steps of target detection in the step S2 are:

[0048] Select the current frame, the previous frame and the previous two frames of the image;

[0049] Match the background of the previous frame to the current frame, and perform inter-frame difference;

[0050] Match the background of the previous two frames to the previous frame, and perform inter-frame difference;

[0051] Multiply the two inter-frame difference results;

[0052] Perform linear filtering, morphological erosion and expansion, and size filtering to separate the target.

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 background matching method for moving target detection, which relates to the technical field of image processing. Only four matching blocks at four corners of an image and one random matching block are used for background matching, and local matching of images is sufficient. To achieve the overall matching of the background. In the occasions where the computing power of the hardware is relatively low, the method provided by the present application can also be used to realize simple target detection in a dynamic background. The present invention provides a dynamic background matching method for moving target detection. After the background matching is performed, the frame difference method is used to detect the moving target, and the target can be successfully and quickly detected when the camera shakes, rotates and pitches greatly. Use simple local area blocks for matching, maintain high background matching accuracy, and simplify the background modeling algorithm.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a dynamic background matching method for moving object detection. Background technique [0002] With the reduction of hardware costs such as cameras and the improvement of manufacturing processes, various applications based on video cameras have been widely developed. Most of these applications involve the detection, tracking and identification of targets. [0003] For most video images, the content in the image can be roughly divided into two parts, the background and the foreground. The background refers to an image that occupies most of the image, is far away from the camera, and is still or gradually changing. The relative positional relationship between objects in the background image is generally fixed. The foreground refers to the target object that is relatively close to the camera and has obvious relative motion and change with the background image. There is...

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): G06V40/20G06V10/30G06V10/34G06V10/74G06K9/62
CPCG06V40/20G06V10/20G06V10/759G06V10/751G06V2201/07G06F18/22
Inventor 胡荣春马娟郑克龙
Owner SOUTHWEAT 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