Fast Reliable Multi-Scale Motion Region Detection in Video Processing

Motion region detection is an important vision topic usually tackled by a background subtraction principle, which has some practical restrictions. We hence propose a multi-scale motion region detection technique that can fast and reliably segment foreground motion regions from two successive video frames. The key idea is to leverage multi-scale structural aggregation to effectively accentuate real motion changes while suppressing trivial noisy changes. Consequently, this technique can be effectively applied to motion region-of-interest (ROI) based video coding. Our experiments show that the proposed algorithm can reliably extract motion regions and is less sensitive to thresholds than single-scale methods. Compared with a H.264/AVC encoder, the proposed semantic video encoder achieves a bitrate saving ratio of up to 34% at the similar video quality, besides an overall speedup factor of 2.6 to 3.6. The motion-ROI detection can process a 352 × 288 size video at 20 fps on an Intel Pentium 4 processor.

[1]  Michael Gleicher,et al.  Region Enhanced Scale-Invariant Saliency Detection , 2006, 2006 IEEE International Conference on Multimedia and Expo.

[2]  Badrinath Roysam,et al.  Image change detection algorithms: a systematic survey , 2005, IEEE Transactions on Image Processing.

[3]  Touradj Ebrahimi,et al.  Semantic video analysis for adaptive content delivery and automatic description , 2005, IEEE Transactions on Circuits and Systems for Video Technology.

[4]  John B. Shoven,et al.  I , Edinburgh Medical and Surgical Journal.

[5]  Yong Wang,et al.  Bi-level video: video communication at very low bit rates , 2001, MULTIMEDIA '01.

[6]  Gary R. Bradski,et al.  Motion segmentation and pose recognition with motion history gradients , 2002, Machine Vision and Applications.

[7]  Arie Shoshani,et al.  Optimizing connected component labeling algorithms , 2005, SPIE Medical Imaging.

[8]  Luigi di Stefano,et al.  A novel approach to change detection based on a coarse-to-fine strategy , 2005, IEEE International Conference on Image Processing 2005.