Feature compression: A framework for multi-view multi-person tracking in visual sensor networks
Journal of Visual Communication and Image Representation, pp. 864-873, 2014.
•A decentralized approach for multi-view multi-person tracking in VSNs.•Likelihood functions are compressed to reduce communication in the network.•Comparison on well-known wavelet transforms to choose an appropriate domain.•Qualitatively and quantitatively, our framework outperforms the centralized approach.
Full Text (Upload PDF)
PPT (Upload PPT)