Exploring Contextual Redundancy in Improving Object-Based Video Coding for Video Sensor Networks Surveillance

In recent years, intelligent video surveillance attempts to provide content analysis tools to understand and predict the actions via video sensor networks (VSN) for automated wide-area surveillance. In this emerging network, visual object data is transmitted through different devices to adapt to the needs of the specific content analysis task. Therefore, they raise a new challenge for video delivery: how to efficiently transmit visual object data to various devices such as storage device, content analysis server, and remote client server through the network. Object-based video encoder can be used to reduce transmission bandwidth with minor quality loss. However, the involved motion-compensated technique often leads to high computational complexity and consequently increases the cost of VSN. In this paper, contextual redundancy associated with background and foreground objects in a scene is explored. A scene analysis method is proposed to classify macroblocks (MBs) by type of contextual redundancy. The motion search is only performed on the specific type of context of MB which really involves salient motion. To facilitate the encoding by context of MB, an improved object-based coding architecture, namely dual-closed-loop encoder, is derived. It encodes the classified context of MB in an operational rate-distortion-optimized sense. The experimental results show that the proposed coding framework can achieve higher coding efficiency than MPEG-4 coding and related object-based coding approaches, while significantly reducing coding complexity.

I. Introduction

Intelligent video surveillance systems are attempted to incorporate content analysis processing tasks (e.g., motion detection [1], object tracking [2], behavior analysis [3], [6]) to understand events that happened in a site. Content analysis processing tasks can be further embedded or distributed within a camera network. Such camera network is called intelligent video sensor networks (VSN) [5] as shown in Fig. 1. In the intelligent VSN, each sensor node is tasked to capture video data and is capable of performing specific content analysis tasks to extract information from the video. The captured video and the extracted information are delivered to an aggregation node (AN). The role of the AN is to process the collected data and deliver important information to the base station (BS) [4], [5]. Intelligent VSN has been envisioned for a wide range of important applications, including security monitoring, environment tracking, and assisted living [5]. A design with distributed interactive video arrays for situation awareness of traffic and incident monitor was presented in [7]. A multicamera tracking system with a fully decentralized handover procedure between adjacent cameras was proposed in [8]. A distributed accident management system for assisted living was presented in [9]. Fig. 1.

Topology of intelligent video sensor networks. The many-to-one network requires large amounts of visual data to be compressed.