Global Intensity Correction in Dynamic Scenes

Changing image intensities causes problems for many computer vision applications operating in unconstrained environments. We propose generally applicable algorithms to correct for global differences in intensity between images recorded with a static or slowly moving camera, regardless of the cause of intensity variation. The proposed intensity correction is based on intensity-quotient estimation. Various intensity estimation methods are compared. Usability is evaluated with background classification as example application. For this application we introduced the PIPE error measure evaluating performance and robustness to parameter setting. Our approach retains local intensity information, is always operational and can cope with fast changes in intensity. We show that for intensity estimation, robustness to outliers is essential for dynamic scenes. For image sequences with changing intensity, the best performing algorithm (MofQ) improves foreground-background classification results up to a factor two to four on real data.

[1]  Glenn Healey,et al.  Radiometric CCD camera calibration and noise estimation , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Ingemar J. Cox,et al.  Dynamic histogram warping of image pairs for constant image brightness , 1995, Proceedings., International Conference on Image Processing.

[3]  Ronen Basri,et al.  Comparing images under variable illumination , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[4]  Hiroshi Watanabe,et al.  Global brightness-variation compensation for video coding , 1998, IEEE Trans. Circuits Syst. Video Technol..

[5]  Mahesan Niranjan,et al.  Realisable Classifiers: Improving Operating Performance on Variable Cost Problems , 1998, BMVC.

[6]  Gregory D. Hager,et al.  Efficient Region Tracking With Parametric Models of Geometry and Illumination , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Kentaro Toyama,et al.  Wallflower: principles and practice of background maintenance , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[8]  Azriel Rosenfeld,et al.  Detection and location of people in video images using adaptive fusion of color and edge information , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

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

[10]  Azriel Rosenfeld,et al.  Tracking Groups of People , 2000, Comput. Vis. Image Underst..

[11]  Til Aach,et al.  Illumination-invariant change detection , 2000, 4th IEEE Southwest Symposium on Image Analysis and Interpretation.

[12]  Michael Harville,et al.  Foreground segmentation using adaptive mixture models in color and depth , 2001, Proceedings IEEE Workshop on Detection and Recognition of Events in Video.

[13]  Heinrich Niemann,et al.  The systematic design and analysis cycle of a vision system: a case study in video surveillance , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[14]  Naoya Ohta,et al.  A statistical approach to background subtraction for surveillance systems , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[15]  Takeo Kanade,et al.  Statistical Calibration of the CCD Imaging Process , 2001, ICCV.

[16]  Andreas Siebert.  Retrieval of gamma corrected images , 2001, Pattern Recognit. Lett..

[17]  Vassilios Morellas,et al.  Two Examples of Indoor and Outdoor Surveillance Systems: Motivation, Design, and Testing , 2002 .

[18]  Mubarak Shah,et al.  Tracking and Object Classification for Automated Surveillance , 2002, ECCV.

[19]  Jun-Wei Hsieh,et al.  Shadow elimination for effective moving object detection by Gaussian shadow modeling , 2003, Image Vis. Comput..

[20]  Yücel Altunbasak,et al.  A fast parametric motion estimation algorithm with illumination and lens distortion correction , 2003, IEEE Trans. Image Process..

[21]  Hong Wang,et al.  Background updating in illumination-variant scenes , 2003, Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems.

[22]  Klamer Schutte,et al.  Probabilistic classification between foreground objects and background , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[23]  Tom Fawcett,et al.  Robust Classification for Imprecise Environments , 2000, Machine Learning.

[24]  Horst Bischof,et al.  Illumination insensitive recognition using eigenspaces , 2004, Comput. Vis. Image Underst..

[25]  Visvanathan Ramesh,et al.  Sudden illumination change detection using order consistency , 2004, Image Vis. Comput..

[26]  P.J. Withagen,et al.  CCD characterization for a range of color cameras , 2005, 2005 IEEE Instrumentationand Measurement Technology Conference Proceedings.

[27]  Academisch Proefschrift,et al.  Object detection and segmentation for visual surveillance , 2006 .

[28]  Ben Kröse,et al.  Probabilistic audio visual sensor fusion for speaker detection , 2006 .

[29]  Gregor Pavlin,et al.  Fault localization in bayesian networks , 2006 .

[30]  Frans A. Oliehoek,et al.  Dec-POMDPs and extensive form games: equivalence of models and algorithms , 2006 .

[31]  Klamer Schutte,et al.  CCD Color Camera Characterization for Image Measurements , 2007, IEEE Transactions on Instrumentation and Measurement.

[32]  K. Schutte,et al.  Shadow detection using a physical basis , 2008, 2008 IEEE Instrumentation and Measurement Technology Conference.

[33]  C. Priebe.  Adaptive Mixtures , 2010 .