Distributed Traffic Surveillance Video Data Storage and Fast Retrieval System

Abstract

The invention discloses a distributed system for storage and quick retrieval of traffic monitoring video data. The system comprises a video data storage module, a distributed video data semantic retrieval module, and a data communication module, wherein the video data storage module is connected to an HBase distributed columnar database and used to store video data into the HBase distributed columnar database; the distributed video data semantic retrieval module is used to establish a structuralized index model based on memory for video data semantics; and the data communication module is used for data communication among multiple video data producers, multiple video data storage modules and the distributed video data semantic retrieval module. According to the invention, data retrieval can be achieved quickly according to video semantic information; the retrieved video data can be acquired in batches quickly; and retrieval efficiency can be increased significantly during video data storage.

Description

technical field [0001] The invention relates to the technical field of video data storage and retrieval, in particular to a distributed traffic monitoring video data storage and fast retrieval system. Background technique [0002] In recent years, with the improvement of people's quality of life, cars are no longer out of reach, and have gradually become an indispensable consumer product for every household. Coupled with the rapid development of the automobile manufacturing industry and the country's policy to vigorously promote the development of the automobile industry, the number of automobiles in my country has increased year by year. Traditional surveillance video storage systems usually store video data in distributed databases, which can provide large-scale video data storage and retrieval services with high stability and high throughput by relying on the characteristics of redundant storage and data partitioning of distributed databases. [0003] However, distribute...

AI Technical Summary

Problems solved by technology

[0004] At present, there are some studies on video data storage, but most of them either only focus on the retrieval optimization of a specific field, such as retrieval for geographic information; or focus on the optimization of specific storage systems, which cannot meet the requirements of video data storage and retrieval Performance requirements and cannot fully fit with surveillance video data

However, some existing systems that focus on video data storage have retrieval performance problems and cannot meet the needs of fast retrieval of video data.

There are also some HBase-based retrieval systems that do not have the function of video semantic retrieval, and some systems that provide video semantic retrieval function do not optimize the index structure of HBase

In addition, the method of extracting and retrieving image features using MapReduce tasks requires the input information to be images, and cannot directly retrieve text semantic information.

Images