Method and system for rapid video data characteristic retrieval

Abstract

The invention discloses a method and system for rapid video data characteristic retrieval. The method includes the following steps: identifying video data with characteristic parameters in massive video data; extracting the characteristic parameters of the video data, and recording metadata of positions of the characteristic parameters in the video data; generating corresponding lists of the characteristic parameters, the metadata and names of the video data corresponding to the characteristic parameters and the metadata; storing the corresponding lists, extracted characteristic parameters and a characteristic metadata index database; and retrieving characteristic parameters matched with demand characteristics from the characteristic metadata index database according to the demand characteristics, and obtaining the video data corresponding to the characteristic parameters through the metadata. The method and system for the rapid video data characteristic retrieval identifies the massive video data, extracts the characteristic parameters and the positions of the characteristic parameters in the massive video data, compares demand characteristic parameters with the characteristic parameters directly to obtain the positions of the characteristic parameters in the video data rapidly, and accelerates retrieval speed.

Description

technical field [0001] The invention belongs to the processing of video data, in particular to a method and system for fast feature retrieval of video data. Background technique [0002] With the continuous development of security technology, the demand for data analysis and mining of surveillance video is also increasing. Existing technologies generally adopt two ways of real-time recognition and post-distributed recognition processing. Although the real-time recognition method can guarantee the timeliness of recognition, it is necessary to provide the features to be recognized in advance; the distributed recognition method is used in the later stage to analyze and search the feature points in the saved historical video files, so as to find the required points in the video. target information. [0003] Such as figure 1 As shown, the existing technical solution adopts a distributed system architecture, and one recognition control machine controls multiple recognition anal...

AI Technical Summary

Problems solved by technology

Although the existing technical solutions solve the image recognition work of a single large video file, there are still certain problems in the recognition of massive video data, including recognition efficiency and recognition speed.

[0004] 1. The existing technical solution is to carry out identification analysis only when identification is required, and the application scenarios that need to provide identification results immediately cannot meet the time requirements

[0005] 2. The existing technology only considers the recognition of a single video file, and there are performance problems for the rapid recognition of a large number of videos

[0006] 3. According to the existing technical scheme, for each identification task, it is necessary to perform identification and analysis on the video, and the efficiency is low

Images