A Big Data Platform for Real-Time Video~Surveillance

Abstract

Nowadays, smart house facilities are strongly developed with the support of multiple security cameras to protect not only a house but also a building. A large amount of video data is produced by these cameras every day. Therefore, traditional data management systems face challenges in collecting, storing, and analyzing big video data. In such systems, it is difficult to find objects and their actions from video surveillance in the building because of either the consuming time or the lack of intelligent technology support. In this paper, we propose a novel big data platform for real-time video surveillance analysis based on the combination of distributed data frameworks and intelligent video processing libraries. The proposed platform is able to collect both real-time video streams and historical video data by using Kafka and Spark Structured Streaming frameworks. Furthermore, the proposed platform provides an intelligent video processing module for object detection by using OpenCV, YOLO, and Keras libraries. To evaluate the proposal, we deploy the proposed big data platform and implement a web interface to support end-user to analyze video surveillance. Through the results of the initial video querying implementation, we show the viability of the proposed platform.