Video compression method and system for indoor monitoring scene

A video compression and scene technology, which is applied in closed-circuit television systems, video data retrieval, digital video signal modification, etc., can solve the problem of reducing the storage space of indoor surveillance video, and achieve the reduction of video storage cost, low cost, and video storage volume Effect

Inactive Publication Date: 2020-01-21
INSPUR ARTIFICIAL INTELLIGENCE RES INST CO LTD SHANDONG CHINA
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical task of the present invention is to provide a video compression method and system for indoor monitoring scenes, to solve how to effectively compress the indoor monitoring video for the characteristics of fixed indoor monitoring video cameras, single video background, and small light source changes, and reduce indoor monitoring video. storage space, improve video compression performance issues

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 compression method and system for indoor monitoring scene
  • Video compression method and system for indoor monitoring scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] as attached figure 1 As shown, the video compression method for indoor monitoring scene of the present invention, the method steps are as follows:

[0052] S1. Selection of key frame / background image: select the first video frame as a key frame / background image in the video frame segment where no person can be detected, and save it in image format; the specific steps are as follows:

[0053] S101. Use the YOLO3 framework to perform target detection on each frame of video, and use whether a person is detected in the video as a judgment criterion;

[0054] S102. Divide the entire video into several video segments without personnel and video segments with personnel without disrupting the sequence of the original video frames;

[0055] S103. Use the first video frame of each video frame segment without personnel as a key frame / background frame, and compress and save it in a jpg format.

[0056] S2. Use the target detection based on YOLO3 to predict the bounding box and pr...

Embodiment 2

[0065] as attached figure 2 As shown, the video compression system for indoor monitoring scene of the present invention, the system includes,

[0066] The selection module of the key frame / background image is used to select the first video frame as the key frame / background image in the video frame segment where no person can be detected, and save it in image format;

[0067] The bounding box prediction and prediction classification module is used to use the target detection based on YOLO3 to perform bounding box prediction and prediction classification on each frame of video images, and to detect each frame of images in the surveillance video through the target detection technology, and the The subjects are framed with anchor frames, and then the subjects framed by the frame are classified and predicted;

[0068] The cutout and compression saving module is used to cut out the bounding box predicted to be a person and compress and save the cutout person image in jpg format; t...

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 compression method and a video compression system for an indoor monitoring scene, belongs to the field of video compression, and aims to solve the technical problem ofhow to perform effective video compression on an indoor monitoring video and improve video compression performance. The technical scheme is as follows: the method comprises the following steps: S1, selecting a key frame; S2, performing bounding box prediction and prediction classification on each frame of video image by using YOLO3-based target detection; S3, carrying out image matting on the bounding box predicted to be the person in the step S2, and carrying out compression storage on the matted person image in a jpg image format; S4, storing the number of frames and the position coordinateinformation of the personnel image in the original image in the form of a personnel image filename while storing the personnel image; S5, decompressing and reconstructing video. The system comprises akey frame selection module, a bounding box prediction and prediction classification module, an image matting and compression storage module, a personnel image storage module and a video decompressionand reconstruction module.

Description

technical field [0001] The invention relates to the field of video compression, in particular to a video compression method and system for indoor monitoring scenes. Background technique [0002] As the scope of use of surveillance cameras continues to expand, and the definition of surveillance cameras is getting higher and higher, more and more videos are captured, and the quality of videos is getting higher and higher, which leads to a significant increase in the storage time required for video storage. Bit rate, especially in schools, banks, office buildings and other fields, the state has stricter requirements on the storage time of surveillance video. Since surveillance videos are usually shot continuously for a long time, the video duration is very long and the volume is huge. However, due to the limitation of storage space, it is necessary to periodically overwrite the previous recorded video when storing the surveillance video. In this way, when it is necessary to ch...

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): G06F16/75G06F16/783H04N7/18H04N19/42H04N19/85
CPCG06F16/75G06F16/7837H04N7/18H04N19/42H04N19/85
Inventor 安程治李锐于治楼
Owner INSPUR ARTIFICIAL INTELLIGENCE RES INST CO LTD SHANDONG CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why 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