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

Video decompression method and system based on Hog features and lgb classifier

A classifier and decompression technology, used in closed-circuit television systems, digital video signal modification, instruments, etc., can solve problems such as inability to adapt to needs and diverse video use cases, achieve repetition rate compression and simplification, and improve compression performance , the effect of saving storage space

Inactive Publication Date: 2020-01-10
INSPUR ARTIFICIAL INTELLIGENCE RES INST CO LTD SHANDONG CHINA
View PDF10 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Traditional video compression algorithms, including MPEG-4, H.264, and H.265, mostly follow the predictive coding structure, which is hard-coded and cannot adapt to the growing demand and diverse video use cases

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 decompression method and system based on Hog features and lgb classifier
  • Video decompression method and system based on Hog features and lgb classifier

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] combined with figure 1 , the present embodiment proposes a video decompression method based on the Hog feature and the lgb classifier, and the implementation process of the method includes:

[0058] S10, converting the monitoring video of the unmanned convenience store into a multi-frame image through OpenCV technology;

[0059] S20, select the first frame image of the original surveillance video, use the Hog feature and the lgb classifier to detect pedestrians, remove the pedestrian position, and form a background image without moving objects;

[0060] S30. Use the Hog feature and the lgb classifier to detect pedestrians, find out the position of the pedestrian, and cut it out as a pedestrian picture to save, and encode it with the frame number label and the position information in the video image;

[0061] S40, comparing each frame image contained in the original video with the background image to make a difference, storing the residual data in a linked list, and com...

Embodiment 2

[0079] combined with figure 2 , the present embodiment proposes a video decompression system based on Hog ​​features and lgb classifiers, the system is based on Hog ​​features and lgb classifiers, including:

[0080] Video splitting module 1 is used to convert the monitoring video of the unmanned convenience store into a multi-frame image through OpenCV technology;

[0081] The background processing module 2 is used to select the first frame image of the original surveillance video, utilizes the Hog feature and the lgb classifier to perform pedestrian detection, removes the pedestrian position, and forms a background picture without moving objects;

[0082] Pedestrian processing module 3 is used to utilize Hog feature and lgb classifier to do pedestrian detection, find out the pedestrian position, and cut it out and save it as a pedestrian picture, encode with frame number label and position information in the video image;

[0083] Contrast storage module 4 is used for compa...

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 decompression method and system based on Hog features and an lgb classifier, and relates to the technical field of video decompression. The method comprises the steps of converting a monitoring video of an unmanned convenience store into a plurality of frames of images; selecting a first frame image of the original monitoring video, performing pedestrian detection by using the Hog features and the lgb classifier, and removing the pedestrian positions to form a background picture without a moving object; carrying out the pedestrian detection by using the Hog features and the lgb classifier to find out the pedestrian positions, and cutting the pedestrian positions as the pedestrian pictures to be stored and named; comparing each frame of image contained in theoriginal video with the background image to obtain a difference value, storing the residual data in a linked list, and compressing the residual data; taking out the background picture, and decoding and restoring the background of each frame of image according to the residual data in the linked list; taking out the pedestrian images in the linked list to cover each frame of background image, and decoding and restoring all frames of images; and splicing all the covered frame images into a video according to the bit rate and the code rate of the original video to complete the video restoration.

Description

technical field [0001] The invention relates to the technical field of video decompression, in particular to a video decompression method and system based on Hog ​​features and lgb classifiers. Background technique [0002] Video surveillance is an important part of the security system. The traditional surveillance system includes front-end cameras, transmission cables, and video surveillance platforms. [0003] An unmanned convenience store refers to all or part of the business processes in the store, which are intelligently and automatically processed through technical means, with reduced or no manual intervention. The surveillance video in the unmanned convenience store is running 24 hours a day, and the storage space of the formed video is very huge, which requires a lot of money to store. Video compression can reduce the space occupied by video and save storage resources. . The background scene of the surveillance video of the convenience store is basically fixed, an...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62H04N7/18H04N19/423
CPCH04N7/18H04N19/423G06V40/20G06V20/40G06F18/214
Inventor 吴振东李锐于治楼
Owner INSPUR ARTIFICIAL INTELLIGENCE RES INST CO LTD SHANDONG CHINA
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