8th Indian Conference on Computer Vision, Graphics and Image Processing,
2012
Motion detection using background modeling is a widely used technique in object tracking. To meet the demands of real-time multi-target tracking applications in large and/or high resolution imagery fast parallel algorithms for motion detection are desirable. One common method for back- ground modeling is to use an adaptive 3D median filter that is updated appropriately based on the video sequence. We describe a parallel 3D spatiotemporal median filter al- gorithm implemented in CUDA for many core Graphics Pro- cessing Unit (GPU) architectures using the integral histogram as a building block to support adaptive window sizes. Both 2D and 3D median filters are also widely used in many other computer vision tasks like denoising, segmentation, and recognition. Although fast sequential median algorithms exist, improving performance using parallelization is attrac- tive to reduce the time needed for motion detection in order to support more complex processing in multi-target tracking systems, large high resolution aerial video imagery and 3D volumetric processing. Results show the frame rate of the GPU implementation was 60 times faster than the CPU ver- sion for a 1K × 1K image reaching 49 fr/sec and 21 times faster for 512 × 512 frame sizes reaching 194 fr/sec. We characterize performance of the parallel 3D median filter for different image sizes and varying number of histogram bins and show selected results for motion detection.