Unlock instant, AI-driven research and patent intelligence for your innovation.

Video scene change detection method and system

A technology of transformation detection and video scene, which is applied in the field of image processing, can solve problems such as low accuracy rate, difficulty in determining the threshold value, unsuitable detection of scene transformation of outdoor surveillance cameras, etc., and achieve the effect of improving accuracy and good robustness

Active Publication Date: 2020-05-01
GUANGZHOU HONGDU INFORMATION TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The difference detection method based on the histogram between video frames is mainly to calculate the histogram of the video frame, calculate the difference between them, and judge whether a scene change occurs according to the set threshold. Also according to the above analysis, the accuracy rate is not high. And the threshold is difficult to determine
[0003] In summary, the above algorithm is not suitable for scene change detection of outdoor surveillance cameras

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 scene change detection method and system
  • Video scene change detection method and system
  • Video scene change detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0043] refer to figure 1 , a video scene change detection method, comprising the following steps:

[0044] Acquisition step: Acquire a reference image and a current image; the reference image is a normal picture taken by the camera, and the picture may be an image retained when the normal state was detected last time, or an image saved when the camera is installed. The current image can be obtained by decoding a video stream.

[0045] Extracting step: extracting the SIFT feature of the reference image to obtain the first feature number; extracting the SIFT feature of the current image to obtain the second feature number; the extraction of the SIFT feature is a prior art. Among them, SIFT, namely scale-invariant feature transform (Scale-invariant feature transform, SIFT), is a description used in the field of image processing. This descriptio...

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 video scene change detection method and system. The method comprises the following steps: obtaining a reference image and a current image; extracting SIFT features of the reference image and the current image to obtain a first feature number and a second feature number; judging whether the first feature number and the second feature number meet a first condition or not, If yes, obtaining a detection result according to the first feature number and the second feature number; otherwise, filtering interference features in the current image and the reference image throughan RANSAC algorithm based on homograaphy transformation, and accumulating the same feature number of the current image and the reference image after filtering; and obtaining a detection result according to the same feature number. According to the method, SIFT features are extracted for comparison, so that the method has good robustness for various weather conditions; when SIFT feature comparisoncannot be satisfied, the interference brought by the dynamic moving target is filtered by using the algorithm so that the detection accuracy can be enhanced. The method can be widely applied to the field of image processing.

Description

technical field [0001] The invention relates to image processing technology, in particular to a video scene change detection method and system. Background technique [0002] When the camera scene is changed, the camera is turned due to human or other reasons, so that the monitoring area deviates from the designated monitoring area. At present, relevant detection methods include detection based on video coding, detection based on the difference of histograms between video frames, etc., but the detection accuracy of these methods is not high, and detection based on video coding is mainly based on the dynamic threshold of the number of coded bits and based on AC image similarity with AC energy, but this method is technically complex, difficult to implement and has low accuracy. Outdoor camera scenes are complex, affected by weather factors such as light, smog, and rain, as well as changing factors such as people, vehicles, and objects. Therefore, it is difficult to accurately ...

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): G06K9/62G06K9/46G06K9/00
CPCG06V20/52G06V10/462G06F18/22Y02T10/40
Inventor 曾雄伟方榆代青平
Owner GUANGZHOU HONGDU INFORMATION TECH