Method for detecting, tracking and identifying object abandoning/stealing event

A recognition method and object technology, applied in character and pattern recognition, computer parts, image data processing, etc., can solve the problems of monitoring personnel being unable to do it, monitoring, monitoring personnel's slack thinking, etc., to achieve real-time object retention/stealing The effect of event recognition

Inactive Publication Date: 2010-06-09
YUNNAN ZHENGZHUO INFORMATION TECH
View PDF0 Cites 34 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the functions of the current monitoring system are often relatively simple, and the monitoring personnel are often required to continuously monitor the screen, interpret the obtained video information, and then make corresponding decisions
But it is a heavy and tedious job for monitoring personnel to stare at many TV monitors for a long time, especially when there are many monitoring points, it is almost impossible for

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
  • Method for detecting, tracking and identifying object abandoning/stealing event
  • Method for detecting, tracking and identifying object abandoning/stealing event
  • Method for detecting, tracking and identifying object abandoning/stealing event

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] figure 1 Shown is a schematic diagram of the intelligent video surveillance system architecture. The intelligent video monitoring system includes three parts: video acquisition unit, intelligent event analysis and processing unit, and alarm unit. The video acquisition unit includes several cameras, which input video to the intelligent monitoring management server through the image acquisition card. The intelligent monitoring management server analyzes and processes the multi-channel video at the same time. After detecting the alarm event, it generates alarm information and outputs it to the alarm system for voice alarm. At the same time, information such as alarm information and evidence pictures are saved to the disk.

Embodiment 2

[0037] figure 2 It is a flow chart of the processing of moving object detection. The processing steps are as follows: 1) Foreground extraction. Foreground extraction adopts background difference method, and background modeling adopts adaptive background model based on main features. 2) Pixel-level preprocessing. The area detected by the foreground contains a lot of noise points, so the pixels need to be further processed, mainly including noise point removal and shadow removal. 3) Connected region analysis, which mainly solves the fusion and segmentation of foreground regions. 4) Regional preprocessing. Use morphology to remove holes and noise, and remove small foreground objects, because small foreground objects may be noise points caused by environmental influences. Finally, mark the moving target. 5) Feature extraction. Feature extraction is mainly to extract the position, size, centroid, contour, and color histogram of each moving target to provide feature informat...

Embodiment 3

[0061] image 3 Process flow chart for moving target tracking. The tracking algorithm first uses a Kalman filter to predict whether an obstruction will occur. In the case of no obstruction between targets, the connected component tracking method based on Kalman filter is adopted; in the case of obstruction between targets, the particle filter tracking method is adopted. Kalman filtering can only solve nonlinear and non-Gaussian systems. In the case of non-blocking, the time interval between two adjacent frames of images is short enough that it can be assumed that the target is moving at a uniform speed per unit time, so Kalman filtering can be used to achieve tracking. In the case of blocking, the posterior probability distribution of the tracking process is often nonlinear and non-Gaussian, which is suitable for particle filtering.

[0062] The condition for judging the occurrence of blocking is: whether there is a foreground connected area in the kth frame intersecting wit...

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 method for detecting, tracking and identifying an object abandoning/stealing event, which comprises the following steps of: 1) the detection of a moving object, namely, establishing an adaptive background model, extracting the moving object by utilizing a background difference and performing morphological processing and shadow processing to obtain a more complete and more accurate state of the moving object; 2) the tracking of the moving object, namely, realizing the inter-frame matching of the moving object through a recursion process of estimating, observing and correcting the state of the moving object, and tracking a moving track of the moving object; and 3) event identification, namely, giving a clear definition to the object abandoning/stealing event, judging the occurrence of the event according to the characteristics and the moving track of the moving object, if the event occurs, distinguishing an object abandoning event from an object stealing event, capturing evidence pictures for the identified abandoning and stealing events and giving an audible alarm.

Description

(1) Technical field [0001] The invention belongs to the technical field of intelligent video monitoring, in particular to the detection, tracking and identification of object retention / theft events. (2) Background technology [0002] Intelligent video monitoring system is an emerging research direction in the field of computer vision in recent years. It uses computer vision technology to analyze and understand the video data collected by cameras, and based on this to control the video monitoring system, so that the video The monitoring system has human-like intelligence, mainly involving scientific knowledge in pattern recognition, image processing, computer vision, artificial intelligence, etc. This technology includes moving target detection, moving target tracking, target classification, behavior understanding and description, etc. It is a challenging problem. In recent years, as the cost of hardware equipment (such as cameras, pan-tilts, etc.) required by the visual sur...

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): G06T7/20G06K9/00G08B13/196
Inventor 不公告发明人
Owner YUNNAN ZHENGZHUO 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
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