A method and system for detecting abnormal video surveillance behavior

A technology for video surveillance and detection methods, applied in image data processing, instrument, character and pattern recognition, etc., can solve the problems of false alarms, single discrimination criteria, and difficulty in tracking, and achieve the effect of increasing accuracy and refining classification.

Active Publication Date: 2018-05-18
SHANDONG HUAYU AEROSPACE TECH CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the method proposed in this paper, when obtaining the foreground pixels, only the background difference division method is used, and the continuously changing pixels are considered to be the foreground, and the continuous static pixels are the background. This criterion is too simple. For Complex backgrounds and changing scenes are likely to cause adverse consequences such as false alarms, missed alarms, and difficulty in tracking

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 method and system for detecting abnormal video surveillance behavior
  • A method and system for detecting abnormal video surveillance behavior
  • A method and system for detecting abnormal video surveillance behavior

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] Embodiment 1. A method for detecting abnormal behavior in video surveillance. The following combination figure 2 and figure 2 The method provided in this embodiment will be described in detail.

[0026] see figure 1 , S1. Acquire a video image sequence, and establish a background model by using a Gaussian mixture model according to the acquired video image sequence.

[0027] Specifically, first, the video surveillance equipment will collect video surveillance image data for a period of time, and transmit the collected video surveillance image data to the video processing device after compression and encoding, and the video processing equipment receives the compressed and encoded video surveillance image data After that, it is decoded, the compressed data encoding file is converted into an analog video surveillance image data file, and the video surveillance image is processed into a video image sequence, and the video image sequence is preprocessed, including conve...

Embodiment 2

[0069] Embodiment 2, a video surveillance abnormal behavior detection system. The following combination image 3 The system provided in this embodiment will be described in detail.

[0070] see image 3 The video surveillance abnormal behavior detection system provided in this embodiment includes a video image preprocessing module 302, a background model building module 302, a foreground area extraction module 303, a division module 304, a motion label calculation module 305, a feature extraction module 306, and a judgment module 307 , a category judging module 308 and an output module 309.

[0071] Wherein, the video image preprocessing 301 is mainly used to process the acquired video surveillance image into a video image sequence, and perform preprocessing on the video image sequence, and the preprocessing includes converting the color video image sequence into a grayscale video image sequences, as well as histogram equalization, median filtering, and gamma correction on ...

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 monitoring abnormal behavior detection method and a detection system thereof. The method comprises: obtaining a video image sequence, using a mixed Gaussian model to establish a background model; Extract the image of the foreground target area and divide it into several foreground target image blocks; use the background difference division method to calculate the motion label of each foreground target image block, and extract the five-dimensional feature parameters of each foreground target image block; use offline The SVM classifier judges whether the current foreground target image block is a normal behavior image block, and if it is a normal behavior image block, it ends; if it is an abnormal behavior image block, then it is judged that the abnormal behavior image block belongs to the abnormal behavior category. Through the present invention, the mixed Gaussian model is used for background modeling, the foreground area and the background area can be accurately segmented, and abnormal behaviors in video surveillance images can be accurately detected.

Description

technical field [0001] The invention relates to the technical field of abnormal behavior detection, in particular to a video monitoring abnormal behavior detection method and a detection system thereof. Background technique [0002] The purpose of video surveillance is to detect and analyze abnormal events or the behavior of monitored objects in the surveillance scene. At present, more mature video abnormal behavior detection includes behaviors such as crossing the border, invading restricted areas, wandering, staying, and fast movement. There are usually two types of implementation methods for abnormal behavior detection: (1) behaviors with small probability or contrary to prior rules are regarded as abnormal behaviors; (2) behaviors that do not match the patterns of known normal behaviors are regarded as abnormal behaviors . [0003] In recent years, the top international journal IEEEET-PAMI and the top international conferences on computer vision and pattern recognition...

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): G06T7/246G06K9/62
CPCG06T2207/10016G06T2207/30196G06T2207/30232G06F18/2411
Inventor 刁奇林巍宋磊刘建文
Owner SHANDONG HUAYU AEROSPACE TECH CO LTD
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