Visual sensor networks are one potential enabler for the evolution of the Internet of things. Due to their limited resources in terms of energy and bandwidth, it is crucial to identify appropriate approaches that take...
详细信息
Visual sensor networks are one potential enabler for the evolution of the Internet of things. Due to their limited resources in terms of energy and bandwidth, it is crucial to identify appropriate approaches that take into considerations such constraints and reduce the amount of data transmitted to the gathering point (sink). In this context, this paper describes the impact of a distributed smart-camera system that exploits an analyze-then-compress strategy, on a multi-view vehicle tracking at roundabouts application. In the tested system, part of the processing is shifted to the smart cameras, i.e., the object detection/classification and feature extraction, so that only the extracted features describing moving vehicles are transmitted instead of the whole image/video. features are further compacted by using a state-of-the-art distributedcoding technique, based upon an efficient clustering method that exploits the temporal and spatial (multiple views) correlations between features. The system is tested on a real-data scenario, by evaluating the bit-rate reduction capabilities in dependence of the channel conditions, as well as the matching accuracy of the reconstructed descriptors in the specific tracking application. Both feature-wise and object-wise matching are investigated. For the chosen application scenario, a bit-rate reduction of 30 - 35% is proved to be achievable in non-ideal channel conditions. Even more interestingly, such reduction is proved not to harm the matching accuracy (i.e., it is coherent with the target application), for which an F-score up to 0.923 is guaranteed.
In visual sensor networks, the analyze-then-compress paradigm, where each camera process data and extract local features, is proved to be an efficient approach to reduce the amount of transmitted information. The bitr...
详细信息
In visual sensor networks, the analyze-then-compress paradigm, where each camera process data and extract local features, is proved to be an efficient approach to reduce the amount of transmitted information. The bitrate can be further reduced by efficiently compressing the extracted features using a distributed feature coding technique. However, since the rate control is performed at the decoder, an abundant use of the feedback channel is needed to adjust the coding rate. Moreover, transmitting all extracted features, including irrelevant ones with no further contribution to the application accuracy, overloads the network. In this paper, we propose a novel feature selection and distributedcoding rate control strategies that cope with these issues. The proposed strategies are designed to significantly reduce the transmitted bitrate and the communication burden with the sink, which implicitly reduces the energy consumption and the decoding delay. We show that, wisely selecting at the camera sensors level only the features effectively contributing to the application accuracy reduces the amount of transmitted information up to 34% while preserving accuracy. Furthermore, the cameras can collaborate periodically, by exchanging small amount of information about their selected features, to estimate the minimum transmission rate required for each feature based on a linear fitting model that takes into consideration the inter-camera correlation and the channel conditions. Significant average bitrate savings, reaching up to 37.71%, are achieved.
暂无评论