Multi-frame morphology area detection method based on frame difference

A detection method and morphological technology, applied in image data processing, television, instruments, etc., can solve the problems of inaccurate extraction of moving object information and low computational complexity, achieve high anti-interference and detection accuracy, eliminate The effect of background noise

Active Publication Date: 2010-06-02
北京蓝色星际科技股份有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method has very high adaptability to the dynamic background environment and low computational complexity, but the extraction of detected moving object information is not very accurate and is suitable for rapid preliminary detection

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
  • Multi-frame morphology area detection method based on frame difference
  • Multi-frame morphology area detection method based on frame difference
  • Multi-frame morphology area detection method based on frame difference

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] Below just in conjunction with accompanying drawing and the present invention will be further described.

[0029] The present invention is a multi-frame morphological region detection method based on frame difference. The working flow chart of the method is as follows figure 1 shown.

[0030] First: read the current frame information, and when the cumulative frame is greater than 2, carry out the first step of the present invention: start to detect the frame difference; its purpose is to detect the initial possible moving area and to be accurate in real time for the next step Get ready for probing. The specific steps are: set the gray value of a certain pixel point (x, y) as I(x, y, t) and I(x, y) for two consecutive frames of 256-level grayscale images at time t and t+1 , t+1), by setting the automatic threshold Td to calculate the change of the gray value of the two frames of images to obtain the foreground change area. The setting of the automatic threshold can be ...

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 present invention belongs to the technical field of video image processing and particularly relates to a multi-frame morphological area detecting method based on frame difference. The method has the steps as follows: current frame information is read, when the accumulation of cumulative frames is more than two, in the first step, frame difference detection is started and is used for detectingan initial possible movement area and preparing well for the next step of exact real time detection; in second step, multi-frame morphological detection is processed in terms of the result of the frame difference detection; firstly, area block detection is processed and is used for finishing the conversion from point to block the detection; secondly, multi-frame structure treatment is processed, an expansion one level and an expansion two level results are obtained by lengthways expanding the information of adjacent frames for more than one time and by the morphological detections of more thanone time, so as to distinguish background interference from foreground movement information to overcome the influence caused by environmental change and also reserve continuous information between frames while eliminating the random information between the frames. The multi-frame morphological area detecting method based on the frame difference has very high anti-jamming performance and detectionaccuracy.

Description

technical field [0001] The invention belongs to the technical field of video image processing, in particular to a multi-frame morphological region detection method based on frame difference. Background technique [0002] In recent years, object movement detection technology has been widely used in many fields, especially in the field of video surveillance. Since this technology is still in the early stage of development, it still needs to be improved in various aspects to adapt to various complex environmental conditions. [0003] At present, there are three representative methods in some commonly used processing methods for moving object detection, which are background difference method, optical flow method and frame difference method. [0004] The background difference method is the most commonly used method, which is usually applied in a static background environment. Its principle is to use a background model as a reference to compare with the current frame image to det...

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): G06T7/00H04N7/26G06T7/20H04N19/159
Inventor 吕楠
Owner 北京蓝色星际科技股份有限公司
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap