Big data processing framework of learning weather information and road traffic collision using distributed CEP from CCTV video: Cognitive image processing

Abstract

Nowadays, the many traffic information are extracted from CCTV. The road occupancy, vehicle speed, accident detection, traffic collision and weather information are calculated in CCTV. These are big data comes from varying sources, such as, social sites or mobile phone GPS signals and so on. The Hadoop and HBase can store and analyze these real-time big data in a distributed processing framework. This framework can be designed as flexible and scalable framework using distributed CEP that process massive real-time traffic data and ESB that integrates other services. In this paper, we propose a new architecture for distributed processing that enables big data processing on the road traffic data with specially weather information and its related information analysis. We tested the proposed framework on road traffic data gathering 41 CCTV from Icheon to Gangneung freeway section in Korea. And the forecasting method is introduced at intermediate local area between CCTV.