A Key Frame Extraction Method Based on Dictionary Selection

An extraction method and key frame technology, applied in the field of video analysis, can solve the problems of reducing the utilization rate of monitoring system equipment, waste, transmission, and storage consumption time and space, so as to save transmission time and storage space, improve utilization rate, and improve The effect of monitoring efficiency

Active Publication Date: 2016-12-28
SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The transmission and storage of surveillance video with a large amount of redundant information consumes a lot of time and space, which reduces the equipment utilization rate of the surveillance system and forms a huge waste

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 Key Frame Extraction Method Based on Dictionary Selection
  • A Key Frame Extraction Method Based on Dictionary Selection
  • A Key Frame Extraction Method Based on Dictionary Selection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0025] The present invention is a kind of key frame extracting method based on dictionary selection, comprises the following steps:

[0026] For each frame of the original video, the improved VIBE background modeling method is used to judge whether each frame is a foreground frame or a background frame, and the foreground video segment with continuous foreground frames is extracted;

[0027] Secondary segmentation of the foreground video segment using the video semantic segmentation method;

[0028] For each segmented video segment, features are extracted from each frame, and the feature set of the video segment forms a dictionary;

[0029] Keyframes are extracted using a dictionary selection method.

[0030] Wherein, the background modeling method is an improved VIBE background modeling method using RGB values ​​and LBP values.

[0031] Th...

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 relates to a method for extracting key frames based on dictionary selection, comprising the following steps: using the VIBE background modeling method for each frame of the original video to determine whether each frame is a foreground frame or a background frame, and extracting the foreground with continuous foreground frames Video segment; use the video semantic segmentation method to segment the foreground video segment twice to obtain the video segment; extract the features of each video segment, and form a dictionary of the feature set of the video segment; use the dictionary selection method to extract key frames. The present invention uses key frames to replace complete video, improves monitoring efficiency, saves transmission time and storage space of monitoring video, reduces waste of resources, and improves utilization rate of equipment.

Description

technical field [0001] The invention relates to the field of video analysis, in particular to a key frame extraction method based on dictionary selection. Background technique [0002] With the development of modern society increasing the security requirements, surveillance probes all over the society have recorded a large number of surveillance videos. Usually we transmit the surveillance video from the probe to the surveillance center, use manual inspection of the surveillance video and store the complete surveillance video. However, most of the surveillance videos are still background images, and only those frames with foreground objects are necessary for surveillance personnel to watch, and even these foreground frames, many of them are similar, that is, the content is redundant. As the time spent watching videos increases, monitors will become fatigued, thereby missing important information. The transmission and storage of surveillance video with a large amount of red...

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): G06T7/00H04N7/18
Inventor 丛杨黄疆坪唐延东
Owner SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI
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