Monitoring video multi-granularity marking method based on generalized multi-labeling learning

Abstract

The invention discloses a monitoring video multi-granularity marking method based on generalized multi-marking learning. The monitoring video multi-granularity marking method of the invention takes the backdrop of public security video monitoring content analysis and carries out a research according to video characteristic multi-layer acquisition and multi-granularity representation theory and method. The monitoring video multi-granularity marking method comprises steps of analyzing and extracting characteristics of different layers of an object in a video on the basis of a multi-marking learning theory and a deep learning theory , constructing a generalized multi-mark classification algorithm on the basis of a multi-mark learning theory and a deep learning theory, and characterizing a multi-granularity representation model of video information on the basis of a granular computing theory and a nature language understanding technology. The monitoring video multi-granularity marking method, targeting the monitoring video content field, carries out a research going deep into the system, constructs a multi-mark learning algorithm through the deep learning theory and can provide an effective theory and method to multi-layer video information. Through simulating the way that human recognize and describe the image, the monitoring video multi-granularity marking method establishes the multi-granularity video representation theory and method, provides a new idea to the video content analysis, and lays theory and application foundations for pushing development of future video monitoring intelligentalization.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a monitoring video multi-granularity tagging method based on generalized multi-label learning. Background technique [0002] With the increasing maturity of video surveillance technology and the continuous popularization of surveillance equipment, video surveillance applications are becoming more and more extensive, and the amount of surveillance video data has shown explosive growth, which has become an important data object in the era of big data. For example, millions of surveillance probes all over Shanghai generate terabytes of video data per minute, providing valuable video resources for real-time grasp of social dynamics and protection of public safety. However, due to the unstructured nature of video data, its processing and analysis are relatively difficult. At present, the application of video data is still mainly based on manual analysis, supplemented by sim...

AI Technical Summary

Problems solved by technology

Video content annotation simplifies the description of video and lacks the description of object characteristics and the relationship between objects; although video content understanding may contain more information, it is difficult to define uniformly due to the complexity and changeability of real scenes. Some effects have been achieved in the scene, but it is still unable to serve the actual application

[0004] Therefore, the existence of these problems leads to the intelligent application of surveillance video is still at a low level

Aiming at problems such as the simplification of annotation in the existing video content representation methods, and the difficulty of accurately defining and describing the spatial relationship of each component, we need a structured method that can simultaneously label multiple objects in complex scenes, and can further label the characteristics of the object’s own components. Video representation method, that is, a generalized multi-label video content annotation method

Images