Method for detecting abnormal gathering behaviors in bus

Abstract

The invention relates to a method for detecting abnormal gathering behaviors in a bus. The method comprises the steps that S1, an infrared camera for shooting videos is arranged in the bus; s2, a video segment in the bus is acquired by using the infrared camera in the bus in S1, video frame image preprocessing is performed on the acquired video segment, and a video frame image is converted into adata set; s3, affine transformation processing is carried out on the video frame images in the S2, and modeling is carried out on the internal structure of the bus. The device for detecting the abnormal gathering behavior in the bus comprises a video acquisition module, a video analysis module, an abnormality judgment module and an abnormality alarm module; the video acquisition module is electrically connected with the video analysis module, the video analysis module is electrically connected with the abnormality judgment module, and the abnormality judgment module is electrically connected with the abnormality alarm module. Aiming at the problem that the detection algorithm in the bus lacks consideration of the actual background of the bus, the method practically considers the actual scene in the bus and accurately judges the abnormal gathering behavior.

Description

technical field [0001] The invention relates to a detection method for abnormal gathering behavior in a bus. Background technique [0002] In recent years, the state has vigorously advocated green transportation, making public travel the first choice for many citizens. As the most common green travel mode, buses are not only convenient, but also have the characteristics of large passenger flow, high density, and complex crowds. They are high-incidence scenarios for group incidents. At the same time, because of its relative closure and lack of other security monitoring methods, the danger of mass incidents is more prominent. [0003] In traditional research, only attention is paid to the use of surveillance video for scheduling drivers to get on and off or to track the location of criminals. The abnormal behavior of passengers has not received widespread attention. Due to the strong group influence in the bus, the detection of abnormal gathering behavior can prevent major ...

AI Technical Summary

Problems solved by technology

First of all, traditional processing mainly relies on manpower for later tracking and analysis, lacks real-time analysis and identification of monitoring scenes, and does not have the function of providing warnings for abnormal events that occur; secondly, the detection algorithms used in existing buses are not Consider the actual background of the bus, but mostly use the algorithm model trained with the public action data set, and do not consider the closed structure characteristics inside the bus, and its actual effect cannot be well guaranteed

Images