Removal of dynamic weather conditions based on variable time window

Dynamic weather conditions, which mainly include rain and snow, make prevailing algorithms for many applications of outdoor video analysis and computer vision lapse. To remove dynamic weather conditions, the authors propose a pixel-wise framework combining a detection method with a removal approach. Dynamic weather conditions are detected by a strategy-driven state transition, which integrates static initialisation using K -means clustering with dynamic maintenance of Gaussian mixture model. Moreover, a variable time window is presented for removal of rain and snow. Each component of the framework is addressed using detailed descriptions of corresponding algorithms. Experiments demonstrate the effectiveness of the method on detection and removal of dynamic weather conditions.

[1]  Hai Liu,et al.  Detecting and extracting natural snow from videos , 2010, Inf. Process. Lett..

[2]  Siu-Yeung Cho,et al.  Recognising human actions by analysing negative spaces , 2012 .

[3]  Xu Chen,et al.  Multimodal Video Indexing and Retrieval Using Directed Information , 2012, IEEE Transactions on Multimedia.

[4]  Patrick Bouthemy,et al.  Simultaneous Motion Detection and Background Reconstruction with a Conditional Mixed-State Markov Random Field , 2011, International Journal of Computer Vision.

[5]  Jérémie Bossu,et al.  Rain or Snow Detection in Image Sequences Through Use of a Histogram of Orientation of Streaks , 2011, International Journal of Computer Vision.

[6]  Radu Mihnea Udrea,et al.  Visual-oriented morphological foreground content grayscale frames interpolation method , 2009, J. Electronic Imaging.

[7]  Jin Keun Seo,et al.  Environmentally Robust Motion Detection for Video Surveillance , 2010, IEEE Transactions on Image Processing.

[8]  Takeo Kanade,et al.  Analysis of Rain and Snow in Frequency Space , 2008, International Journal of Computer Vision.

[9]  Shree K. Nayar,et al.  Vision and Rain , 2007, International Journal of Computer Vision.

[10]  Yaser Sheikh,et al.  Bayesian modeling of dynamic scenes for object detection , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  MANABU GOUKO,et al.  An Action Generation Model by Using Time Series Prediction and its Application to Robot Navigation , 2009, Int. J. Neural Syst..

[12]  Radu Mihnea Udrea,et al.  Iterative generalization of morphological skeleton , 2007, J. Electronic Imaging.

[13]  Wen-Kai Tai,et al.  Moving cast shadow detection by exploiting multiple cues , 2008 .

[14]  Avideh Zakhor,et al.  Applications of Video-Content Analysis and Retrieval , 2002, IEEE Multim..

[15]  Rajiv Kapoor,et al.  Fast tracking algorithm using modified potential function , 2012 .

[16]  Se-Young Oh,et al.  Robust segment-based object tracking using generalized hyperplane approximation , 2012, Pattern Recognit..

[17]  W. Eric L. Grimson,et al.  Learning Patterns of Activity Using Real-Time Tracking , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Guilherme N. DeSouza,et al.  Adaptive learning of multi-subspace for foreground detection under illumination changes , 2011, Comput. Vis. Image Underst..

[19]  Ashish Khare,et al.  Curvelet transform-based technique for tracking of moving objects , 2012 .

[20]  Javier Bajo,et al.  Stereo Video Surveillance Multi-agent System: New Solutions for Human Motion Analysis , 2011, Journal of Mathematical Imaging and Vision.