Crowd gathering event detection method and system
A technology for event detection and events, applied in image data processing, instruments, calculations, etc., can solve problems such as increased calculation amount and difficulty in obtaining historical samples, so as to reduce calculation complexity, improve monitoring efficiency, and reduce human and financial investment Effect
Inactive Publication Date: 2018-04-10
徐州光谱信息科技有限公司
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Moreover, it is difficult to obtain historical samples, and the amount of calculation is also increased by obtaining the history of moving targets
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0041] The present invention will be described in further detail below in conjunction with the accompanying drawings.
[0042] figure 1 A method for detecting crowd gathering events according to an embodiment of the present invention is schematically shown. Such as figure 1 As shown, the method includes:
[0043] Step S101: Perform moving object detection on video frame images to obtain binarized moving objects.
[0044] A crowd event is an abnormal event in which multiple people gather together. Two key issues need to be considered in its detection: behavior description and behavior modeling. Among them, behavior description is to select appropriate features to describe events, and the general selection of features includes: human target, clump, trajectory, energy and gray level of change. The present invention selects agglomerate and energy as the characteristics of the behavior description of the crowd abnormal event. After carrying out a moving object detection algori...
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
Login to View More Abstract
The present invention discloses an assembly event detection method, comprising: performing behavior description of video frame images and building a behavior modeling to obtain an assembly identification index; and determining the identification index, and determining the occurrence of the assembly event when the index is larger than a predetermined threshold value. The process of performing behavior description of video frame images and building the behavior modeling to obtain the assembly identification index comprises: obtaining a block mass of moving objects in the video frame images; calculating the video frame energy of the video frame images; building an background model based on kernel density estimation for each pixel point in the video frame images; obtaining information entropies of the video frame images according to the background model; and building an assembly event identification index model according to the video frame energy and the information entropies to obtain the assembly identification index. According to the assembly event detection method provided by the invention, the assembly anomalous events may be easily and quickly detected so as to energetically reduce the workload of the video monitoring personnel, greatly improve the work efficiency and reduce manpower and financial resources in the security field.
Description
technical field [0001] The invention relates to the fields of intelligent video processing and image processing, in particular to a method and system for detecting crowd gathering events. Background technique [0002] With the strong demand for security monitoring in society and the development of intelligent video surveillance systems, it is particularly important to detect abnormal behavior based on video streams (video event detection). Its core concept is to use computer technology and image processing methods to identify the events we are interested in from surveillance video images, which is a comprehensive and complex problem. At present, the identification of abnormal behavior mainly includes the detection and tracking of moving objects and the identification and judgment of abnormal behavior on surveillance video images. Crowd gathering behavior recognition is one of the most important aspects of abnormal behavior. Among them, crowd gathering behavior 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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/223
CPCG06T2207/10016
Inventor 曲平程实赵福洪沈学华陈晓勇
Owner 徐州光谱信息科技有限公司