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

An online extraction method of surveillance video feature frames

An extraction method and monitoring video technology, which is applied in the direction of instruments, calculations, character and pattern recognition, etc., can solve problems such as unsuitable monitoring video

Inactive Publication Date: 2019-02-12
SHANDONG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, existing video frame extraction methods based on scene change and lens change detection cannot be applied to surveillance video

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
  • An online extraction method of surveillance video feature frames
  • An online extraction method of surveillance video feature frames
  • An online extraction method of surveillance video feature frames

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0035] A monitoring video feature frame online extraction method, comprising the steps as follows: firstly, the video sequence is subjected to timing change point detection; and the detected change points are used to divide the video into video segments containing different contents, and then use The clustering method completes the extraction of key frames. Wherein said video is the video of N frame: F={f 1 , f 2 ,..., f N}, f i Represent the video frame at time i, extract the key frame F={f in the video r1 , f r2 ,..., f rk}, and arranged in time sequence to get.

[0036] Preferably, according to the present invention, the method for detecting timing change points of a video sequence includes the following steps:

[0037] Step (1-1): Establish a sliding window model

[0038] Initialize the start frame n of video change point detection 1 = 1 and the frame length L of the corresponding sliding window 1 =L 0 ;

[0039] Step (1-2)

[0040] Carry out change point dete...

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 provides an online extraction method of a monitoring video feature frame. Under the framework of incremental sliding window technology, this method first detects the timing change points of the video sub-sequence, and uses the detected change points to divide the video into video segments containing different contents, and then uses the aggregated The class method completes the extraction of key frames. This method does not require any artificial preset parameters, and can realize completely unsupervised key frame extraction of surveillance video.

Description

technical field [0001] The invention relates to an online extraction method for monitoring video feature frames, belonging to the technical field of intelligent monitoring. Background technique [0002] Video summarization (video summarization) technology allows users to grasp the events that occurred during the observation time by browsing the video feature frames within a limited time. However, existing video frame extraction methods based on scene change and lens change detection cannot be applied to surveillance video. Contents of the invention [0003] Aiming at the deficiencies of the prior art, the present invention provides an online extraction method for feature frames of surveillance video. Under the framework of incremental sliding-window technology, this method first detects the timing change points of the video subsequence, and uses the detected change points to divide the video into video segments containing different contents, and then obtains The clusteri...

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): G06K9/00
CPCG06V20/47
Inventor 卢国梁刘阳闫鹏王亮
Owner SHANDONG UNIV