Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A surveillance video multi-dimensional pedestrian behavior intelligent analysis system and method

A technology for behavior analysis and video surveillance, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as poor adaptability, reduce labor costs, improve intelligent performance, and improve accuracy.

Active Publication Date: 2021-03-16
CHENGDU UNIV OF INFORMATION TECH +1
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] Aiming at the problems existing in the above-mentioned background technology, the present invention proposes a reasonable concept that can effectively solve the problem of poor adaptability of existing methods due to single applicable scenarios, pedestrian behavior dimensions and recognized pedestrian behavior types. A monitoring video multi-dimensional pedestrian behavior intelligent analysis system and method that can support various complex monitoring scenarios and pedestrian behavior dimensions, and greatly improve the accuracy, versatility and efficiency of pedestrian behavior recognition in 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
  • A surveillance video multi-dimensional pedestrian behavior intelligent analysis system and method
  • A surveillance video multi-dimensional pedestrian behavior intelligent analysis system and method
  • A surveillance video multi-dimensional pedestrian behavior intelligent analysis system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Apparently, the described embodiments are part of the embodiments of the present invention, but not all of them.

[0048] In order to deal with the algorithmic heterogeneity of the pedestrian behavior analysis model, that is, the pedestrian behavior analysis model of different scenes under different pedestrian behavior dimensions contains different pedestrian behavior feature extraction and description algorithms, and meets the requirements of computing hardware (such as the usual deep learning network needs Use the image processor GPU to carry out parallel accelerated calculation), the monitoring video multi-dimensional pedestrian behavior intelligent analysis system of the present invention uses the micro-service architecture design, each pedestrian behavior analysis model is used as an independent service, ado...

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 present invention relates to a monitoring video multi-dimensional pedestrian behavior intelligent analysis system and method, the system includes an individual behavior analysis module, a small group behavior analysis module, a group behavior analysis module, a scene analysis module, a pedestrian behavior dimension evaluation module, and an intelligent gateway , application logic integration module and video source management module. The method is as follows: obtaining the monitoring video data stream, extracting video frames from the monitoring video data stream, using key video frame data to classify scenes and select pedestrian behavior dimensions; merging scene and pedestrian behavior dimension information; performing pedestrian behavior analysis module selection Decision-making and management data transmission; through the pedestrian behavior analysis model of a scene integrated in the pedestrian behavior analysis module under the selected behavior dimension, intelligent behavior recognition is carried out, and the final pedestrian behavior recognition result is output. The invention can support pedestrian behavior recognition in various complex monitoring scenarios and pedestrian behavior dimensions.

Description

technical field [0001] The invention relates to the technical fields of computer science, machine vision and artificial intelligence, in particular to a monitoring video multi-dimensional pedestrian behavior intelligent analysis system and method. Background technique [0002] Intelligent video analysis technology has very important applications in the fields of current security monitoring, entertainment, human-computer interaction and automatic driving. Pedestrian behavior analysis and recognition is one of the key technical difficulties. For example, by identifying the behavior or movement trend of pedestrians in the surveillance video to determine whether there is any abnormal behavior, so as to realize functions such as intelligent alarm for public emergencies. Therefore, intelligent video surveillance has an urgent application demand in the field of public security. In addition, automatic driving decision-making can also be assisted by identifying pedestrian behavior ...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V40/20G06V20/40G06V20/52G06N3/045
Inventor 许源平张朝龙冯暄咬登国许志杰龚梅乔少杰郭本俊李婵玉黄健
Owner CHENGDU UNIV OF INFORMATION TECH
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
Eureka Blog
Learn More
PatSnap group products