A Bayesian Probabilistic Framework for Rain Detection

Abstract

Heavy rain deteriorates the video quality of outdoor imaging equipments. In order to improve video clearness, image-based and sensor-based methods are adopted for rain detection. In earlier literature, image-based detection methods fall into spatio-based and temporal-based categories. In this paper, we propose a new image-based method by exploring spatio-temporal united constraints in a Bayesian framework. In our framework, rain temporal motion is assumed to be Pathological Motion (PM), which is more suitable to time-varying character of rain steaks. Temporal displaced frame discontinuity and spatial Gaussian mixture model are utilized in the whole framework. Iterated expectation maximization solving method is taken for Gaussian parameters estimation. Pixels state estimation is finished by an iterated optimization method in Bayesian probability formulation. The experimental results highlight the advantage of our method in rain detection.

SpaceTime Environmental Image Information for Scene Understanding

“…[19][20][21][22][23][24] This is because rain, snow, and fog weather events, smoke, haze, or other changes in lighting and visibility can significantly obscure features, degrade object recognition, and modify the saliency and image context of an outdoor scene. [25][26][27][28][29][30][31][32] Naturally, scene-depicted environmental conditions can vary with time of day, season, and location. 33 Similar challenges can also extend to interpreting space-and time-changing scenes due to visual motion of objects within the field of view.…”