Image sensing under unfavorable photographic conditions with a group of wireless image sensors

We investigate the problem of image sensing under unfavorable photographic conditions in a wireless image sensor network. In the scenes with deflective and/or reflective medium such as fogs, mirrors, glasses, degraded images are captured by those image sensors. Such degraded images often lack perceptual vividness and they offer a poor visibility of the scene contents. Notably, computation-intensive method to recover a better image based on single image [2] may not be applicable for wireless image sensors due to the limited computation capacities and the limited power resources (batteries) typically equipped at those wireless image sensors. In this paper, we propose a framework to recover better images under unfavorable photographic conditions in a wireless image sensor network, where an efficient decision fusion approach based on the reinforcement learning technique to infer the presence of an unfavorable photographic condition is achieved among image sensors on the fly and a subsequent light-weighted computation method based on multiple images is employed to recover better images. The preliminary results show the effectiveness of the proposed framework.