Semantic Description and Information Retrieval Research of Surveillance Video in Smart Transportation System

It is a hotspot to retrieve the desired information or find specific target inside the mass traffic video information. To achieve video content, it is necessary to build up a bridge between the low-level visual information and the high-level semantics. In this paper, firstly we propose a framework of intelligent traffic information semantic description. And then the semantic description framework of intelligent traffic information based on the standard of MPEG-7 is brought out. The framework can describe the multi-layer video information from the underlying visual features to the high-level semantic features, it can make up the gap of semantic and ultimately facilitate the users to retrieve mass video information. Finally, the accuracy and rapidity of the retrieval is demonstrated by the example of a traffic video semantic description and retrieval. It greatly reduces the working intensity of video processing workers because this method can handle most cases rapidly.