Monitoring video behavior detection method based on multipath neural network

A technology for monitoring video and detection methods, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as inapplicable products, low recognition accuracy and efficiency, achieve novel methods, and improve accuracy and efficiency , strong operational effect

Active Publication Date: 2018-06-22
深圳市网联安瑞网络科技有限公司
View PDF10 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There are various technologies for behavior detection and analysis in the current monitoring video, but for the various behavior analysis existing in the prior art, its recognition accuracy and efficiency are all low, and it is not suitab

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
  • Monitoring video behavior detection method based on multipath neural network
  • Monitoring video behavior detection method based on multipath neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiment is only one embodiment of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0040] For the sake of simplicity, common technical knowledge known to those skilled in the art is omitted in the following content.

[0041] Refer to attached figure 1 And attached figure 2 , the behavior detection method of the surveillance video includes:

[0042] S1. Collect several surveillance videos as training materials.

[0043] In the specific implementation, the network surveillance camera is fixed, and a large number of surveillance videos are shot a...

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 monitoring video behavior detection method based on a multipath neural network. The method comprises the steps that a plurality of monitoring videos are collected to serve astraining materials; according to regional distances in the monitoring videos, the training materials are uniformly cut to obtain at least two groups of regional videos, wherein the number of the regional videos in each group is equal; segment checking is performed on the regional videos to obtain the training materials; key frames and optical flow graphs are extracted from the videos; the deep multipath neural network is adopted to process the training materials to obtain a training model; and the training model is utilized to perform behavior recognition on a to-be-detected video file. Through the monitoring video behavior detection method, the accuracy and efficiency of behavior detection can be effectively improved; and the video file is divided into multiple regions for training and recognition of a behavior model, different networks are adopted according to different distances, and the problem that the behavior detection efficiency is influenced because coverage is broad and shooting content is small far away and large nearby in the video file is effectively solved.

Description

technical field [0001] The invention relates to the field of video behavior detection, in particular to a monitoring video behavior detection method based on a multi-channel neural network. Background technique [0002] Surveillance video is an important part of the security protection system. It is a comprehensive system with strong prevention capabilities. Surveillance video is widely used in many occasions because of its intuition, accuracy, timeliness and rich information content. There are various technologies for behavior detection and analysis in the current monitoring video, but for the various behavior analysis existing in the prior art, its recognition accuracy and efficiency are all low, and it is not suitable for products; the monitoring video provided by the present invention The behavior detection method of the company aims to improve the accuracy and efficiency of behavior analysis, so that video behavior analysis technology can be truly commercialized. Cont...

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): G06K9/00G06K9/62G06T7/215G06N3/04G06N3/08
CPCG06T7/215G06N3/08G06T2207/30232G06T2207/10016G06T2207/20084G06T2207/20081G06V20/46G06V20/40G06V20/52G06N3/044G06N3/045G06F18/2414G06F18/214
Inventor 贾宇沈宜邹严董弋粲
Owner 深圳市网联安瑞网络科技有限公司
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