Cooperative image analysis in visual sensor networks

This work addresses the problem of enabling resource-constrained sensor nodes to perform visual analysis tasks. The focus is on visual analysis tasks that require the extraction of local visual features, which form a succinct and distinctive representation of the visual content of still images or videos. The extracted features are then matched against a feature data set to support applications such as object recognition, face recognition and image retrieval. Motivated by the fact that the processing burden imposed by common algorithms for feature extraction may be prohibitive for a single, resource-constrained sensor node, this paper proposes cooperative schemes to minimize the processing time of the feature extraction algorithms by offloading the visual processing task to neighboring sensor nodes. The optimal offloading strategy is formally characterized under different networking and communication paradigms. The performance of the proposed offloading schemes is evaluated using simulations and is validated through experiments carried out on a real wireless sensor network testbed. The results show that the proposed offloading schemes allow to reduce the feature extraction time up to a factor of 3 in the reference scenario. Visual sensor networks (VSNs) extend the application fields of traditional wireless sensor networks by adding the capability to acquire and process multimedia signals such as still images and video. VSNs can have a significant impact in scenarios in which visual analysis is currently infeasible, due to the mismatch between the transmission and computational resources and the complexity of the analysis tasks. As an example, in the context of smart cities, the availability of inexpensive visual nodes can enable a much more complete coverage of the urban landscape, reaching a wider area and limiting the costs of the required infrastructure to support applications for traffic monitoring, smart parking metering, environmental monitoring, hazardous situations monitoring, etc. [1,2]. Classical networked systems for visual analysis follow the compress-then-analyze paradigm, where image/video analysis is performed last and is decoupled from the acquisition , compression and transmission phases. In the case of VSNs, powerful smart cameras are substituted by vision-enabled, battery-operated sensing nodes with low-power microprocessors and radio chips. The traditional compress send then analyze paradigm may not fit well the computation and communication-related constraints imposed by these VSNs, as it requires large communication resources. For this reason, an alternative paradigm, named analyze-then-compress has been recently proposed leveraging the idea that most visual analysis tasks can be carried out based only on a succinct representation …