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

Video personnel tracking and counting method based on artificial intelligence

A technology of artificial intelligence and counting methods, applied in computing, computer parts, instruments, etc., to solve problems such as occlusion or coverage, difficulty, and increase in video analysis technology

Active Publication Date: 2020-05-15
福建省星云大数据应用服务有限公司
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the surveillance video scene observed from a squint perspective, the features of the head are complex, and often appear to be blocked or covered by other people, which adds great difficulties to the video analysis technology

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 personnel tracking and counting method based on artificial intelligence
  • Video personnel tracking and counting method based on artificial intelligence
  • Video personnel tracking and counting method based on artificial intelligence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] figure 1 It is an artificial intelligence-based video personnel tracking and counting method of the present invention. The personnel increment is calculated through the change of the side identification position of the same pedestrian in adjacent frames, and the method based on convolutional neural network feature extraction and online update of parameters is used. A tracker is used to match multiple pedestrians in adjacent frames, detect common occlusion patterns and compensate for the increase in the number of people. The method includes the following steps:

[0068] Step 1: Initialize the video frame number n=1, segment the video object of the nth frame to obtain the pedestrian connected domain set Calculate the eigenvector of the jth pedestrian and motion vector Set the longest number of untracked matches for the jth pedestrian

[0069] The calculation method of the pedestrian's feature vector and motion vector is introduced below.

[0070] The feature vect...

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 personnel tracking and counting method based on artificial intelligence. According to the method, learning features extracted by a convolutional neural network and artificial features extracted by geometric calculation are comprehensively utilized, a tracker capable of updating network parameters on line is utilized to perform multi-target matching between video image sequences, and personnel increment is calculated according to changes of inner and outer side identification positions of the same pedestrian in adjacent frames. A sparse auto-encoder is used to learn from massive public video data sets to obtain a set of feature sets, and the feature sets are used as filters of the convolutional neural network, so that the online updating efficiency of the convolutional neural network is improved. In addition, a common personnel shielding mode is also considered, and counting errors caused by shielding are compensated. The method provided by the inventionhas robustness, real-time performance, relatively high precision and relatively strong anti-shielding capability, is suitable for personnel counting under video big data, and can be integrated into avideo monitoring software system.

Description

【Technical field】 [0001] The invention belongs to the technical field of intelligent video monitoring and analysis, in particular to an artificial intelligence-based video personnel tracking and counting method. 【Background technique】 [0002] Generally, there are two options for detecting and counting the number of people in a building. One is to sum up the number of people detected in the surveillance video of each floor and each area of ​​the building as the total number of people in the building. This line of thinking requires building video surveillance to be fully covered. In addition, because the number of people detected by each surveillance video has a certain error, the error of the summation is relatively large. The second is to subtract the cumulative number of people leaving from the cumulative number of people detected in the surveillance video of all entrances and exits of the building to obtain the total number of people in the building. This idea involves...

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): G06K9/00G06K9/34G06K9/62
CPCG06V20/53G06V10/267G06V10/754G06F18/241
Inventor 邹建红高元荣陈雯珊王辉陈哲张兴王宇奇陈彬陈凡千孙建锋
Owner 福建省星云大数据应用服务有限公司
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