An abnormal detection method for crowd movement trajectories in complex structured scenes
A technology of motion trajectory and complex structure, applied in image data processing, instrumentation, calculation, etc., can solve problems such as inaccuracy and low efficiency of crowd abnormal motion trajectory, achieve good robustness and meet actual needs
Active Publication Date: 2017-10-31
北交智轨(北京)科技有限公司
View PDF5 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0008] The purpose of the present invention is to provide a method for abnormal detection of crowd movement trajectories in complex structured scenes, which solves the problem of inefficiency and inaccuracy in the detection of abnormal crowd movement trajectories in surveillance video data of complex structured scenes
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
[0046] In order to illustrate the present invention more clearly, the present invention will be further described below in conjunction with preferred embodiments and accompanying drawings. Similar parts in the figures are denoted by the same reference numerals. Those skilled in the art should understand that the content specifically described below is illustrative rather than restrictive, and should not limit the protection scope of the present invention.
[0047] Such as figure 1 As shown, the abnormal detection method for the crowd movement track in the complex structured scene provided by this embodiment first extracts the key points of the crowd movement track in the complex structured scene in the surveillance video historical data—that is, the movement trend change point, These key points are usually located at road turning points, obstacles, etc., in complex structured scenes such as figure 2 shown. According to the key points of the crowd movement trajectory, the c...
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 invention discloses a method for abnormal detection of crowd movement trajectories in complex structured scenes, which comprises the following steps: extracting crowd movement trajectories in complex structured scenes from surveillance video historical data and segmenting crowd movement trajectories to obtain crowd classification Segmental motion trajectories; learn the multi-center clustering algorithm based on the maximum and minimum distances for the segmented motion trajectories of the crowd, and obtain the segmental motion trajectories of each crowd; extract the crowd motion trajectories in the complex structured scene in the current data of the surveillance video, and According to the segmented movement trajectories of each group of people, the anomaly detection based on the LOF algorithm is performed on the movement trajectories of the crowd in the complex structured scene in the current surveillance video data. Compared with other algorithms in the prior art, the technical solution of the present invention has high robustness, applicability, effectiveness and high efficiency for anomaly detection in complex structured scenes, and can well meet actual needs.
Description
technical field [0001] The invention relates to complex structured scene processing in intelligent video monitoring technology. More specifically, it relates to an anomaly detection method for crowd movement trajectories in complex structured scenes. Background technique [0002] In recent years, intelligent video surveillance has been widely used in many industries and related fields. At present, most medium-sized and above communities are equipped with safety monitoring. The forestry and animal husbandry department has set up fire alarm and fire monitoring to prevent forest fires. The transportation department has also set up road monitoring for the purpose of tracking illegal vehicles and observing road traffic. It has been reported (J.Vlahos..Surveillance society: New high-tech cameras are watching you..Popular Mechanics, 2008, Vol. 2, No. 3, Pages: 64-69.) pointed out that by 2008, there had been many More than 30 million video surveillance devices have been installed...
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): G06T7/20
Inventor 刘渭滨崔静邢薇薇卢伟
Owner 北交智轨(北京)科技有限公司