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.

Photo tourism [11] is a platform that allows users to transform unstructured online digital photos into a 3D experience. Nowadays, image sensors are being extensively used to allow images to be taken automatically and remotely, which facilitates the opportunity for live update of photo mosaics. In this paper, we present a novel framework for live photo mosaic with a group of wireless image sensor nodes, where the image data aggregation is accomplished in an efficient and distributed way. Essentially, we propose to conduct clustering and data compression at wireless image sensor network level while conserving the completeness of the feature point information [9] for reconstruction. Toward the realization of the whole system, we have built image sensor prototypes with commodity cameras and we validated our approach by indepth analysis, extensive simulations and field experiments.

Photo tourism [5] is a platform that allows users to transform unstructured online digital photos into a 3D experience. Nowadays, image sensors are being extensively used to allow images to be taken automatically and remotely, which facilitates the opportunity for live update of photo mosaics. In this paper, we present a novel framework for live photo mosaic with a group of wireless image sensor nodes, where the image data aggregation is accomplished in an efficient and distributed way. Essentially, we propose to conduct clustering and data compression at wireless sensor network level while conserving the completeness of the feature point information [3] for reconstruction. Toward the realization of the whole system, we have built image sensor prototypes with commodity cameras. We have also conducted preliminary experiments with our wireless image sensor prototypes.

Virtual environments (VEs) allow safe, repeatable, and controlled evaluations of obstacle avoidance and navigation performance of people with visual impairments using visual aids. Proper simulation of mobility in a VE requires an interface, which allows subjects to set their walking pace. Using conventional treadmills, the subject can change their walking speed by pushing the tread with their feet, while leveraging handrails or ropes (self-propelled mode). We developed a feedback-controlled locomotion interface that allows the VE workstation to control the speed of the treadmill, based on the position of the user. The position and speed information is also used to implement automated safety measures, so that the treadmill can be halted in case of erratic behavior. We compared the feedback-controlled mode to the self-propelled mode by using speed-matching tasks (follow a moving object or match the speed of an independently moving scene) to measure the efficacy of each mode in maintaining constant subject position, subject control of the treadmill, and subject pulse rates. Additionally, we measured the perception of speed in the VE on each mode. The feedback-controlled mode required less physical exertion than self-propelled. The average position of subjects on the feedback-controlled treadmill was always within a centimeter of the desired position. There was a smaller standard deviation in subject position when using the self-propelled mode than when using the feedback-controlled mode, but the difference averaged less than six centimeters across all subjects walking at a constant speed. Although all subjects underestimated the speed of an independently moving scene at higher speeds, their estimates were more accurate when using the feedback-controlled treadmill than the self-propelled.