Video interaction event analysis method and device base on sequence space-time cube characteristics

Abstract

The invention relates to a video interaction event analysis method and device base on sequence space-time cube characteristics. The method includes the steps of dividing a monitoring video into a plurality of space-time cube sequences on the basis of a detection tracking result of the monitoring video, extracting object tracks, the appearance and local movement descriptors in each space-time cube, forming characteristic segments through the extracted descriptors, reconstructing the characteristic segments in all the space-time cubes to establish the sequence space-time cube characteristics, and conducting interaction event classification detection through the sequence space-time cube characteristics. The device comprises a preprocessing module, a video sequence dividing module, a space-time cube characteristic extraction module, a space-time characteristic reconstruction module and a sequence characteristic classification module. According to the method and the device, high-level semantic layer description is achieved for content of the monitoring video, length-variable sequence characteristic classification is achieved through a multi-core support vector machine based on a dynamic time alignment kernel function, and therefore intelligent detection is achieved for monitoring video stream interaction events.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and relates to a monitoring video interaction event analysis method, in particular to a monitoring video interaction event analysis method based on sequence space-time cube characteristics, and a device for realizing the method. Background technique [0002] As surveillance cameras are widely used in all aspects of people's lives, surveillance video data is growing explosively. How to intelligently analyze interesting events that occur in it is a challenging problem. Among the events of interest, some are multi-object interaction events, such as fights, robberies, homicides, and car crashes. In order to be able to report to the police in the early stage of the incident and assist in the investigation and evidence collection after the incident, the intelligent analysis method for such incidents is very critical. [0003] At present, the handling of such incidents mainly relies on witnesse...

AI Technical Summary

Problems solved by technology

This analysis method lacks the description of the local motion characteristics of the object, and cannot determine the specific type of a complex event by analyzing the causal relationship between each stage of the complex event.

Images