Application Research Of Big Data Technology In Metro Video Surveillance System

With the rapid development of society and science technology,the safety consciousness of people is more and more high,the people's standard of security also needs to increase rapidly,With the rapid development of internet technology,information technology,video compression technology,metropolitan area video monitoring system is applied to people's daily work and life,video monitoring plays a big role in protecting people's life and property safety,but with the passage of time,the amount of data produced by the city video surveillance system continues to grow,the traditional technology already cannot satisfy the demand of huge amounts of data.In fact,all walks of life are faced with the advent of the era of big data,big data has brought great challenges to many traditional technology,in order to adapt to the demand of the era of large data,the corresponding big data technology develop quickly,it also need to bring in big data technology in video surveillance system to deal with huge amounts of data.In this paper,based on the research of the technology related to big data,using cloud storage technology to storage and manage the huge amounts of data of metropolitan area video monitoring system,using the data mining technology to further analysis the huge amounts of data.First using the HDFS to storage the original data,at the same time introducing MongoDB to store metadata information.And then using the video data mining technology to analysis the original monitoring data,mainly includes two aspects: firstly,suspected vehicles analysis,using the information contained in video monitoring to design expert system for identification of suspected cases of vehicle,designing the system inference rules in the knowledge base;secondly,using association rules analysis the causes of road traffic accidents,and using information gain to select the main factors of accidents.