Towards an efficient distributed object recognition system in wireless smart camera networks

Abstract

We propose an efficient distributed object recognition system for sensing, compression, and recognition of 3-D objects and landmarks using a network of wireless smart cameras. The foundation is based on a recent work that shows the representation of scale-invariant image features exhibit certain degree of sparsity: If a common object is observed by multiple cameras from different vantage points, the corresponding features can be efficiently compressed in a distributed fashion, and the joint signals can be simultaneously decoded based on distributed compressive sensing theory. In this paper, we first present a public multiple-view object recognition database, called the Berkeley Multiview Wireless (BMW) database. It captures the 3-D appearance of 20 landmark buildings sampled by five low-power, low-resolution camera sensors from multiple vantage points. Then we review and benchmark state-of-the-art methods to extract image features and compress their sparse representations. Finally, we propose a fast multiple-view recognition method to jointly classify the object observed by the cameras. To this end, a distributed object recognition system is implemented on the Berkeley CITRIC smart camera platform. The system is capable of adapting to different network configurations and the wireless bandwidth. The multiple-view classification improves the performance of object recognition upon the traditional per-view classification algorithms.