18 December 2014 Hole filling using joint bilateral filtering for moving object segmentation
Author Affiliations +
Abstract
Due to various reasons (e.g., poor quality of image, sudden changes in light conditions, occlusions, or objects with similar colors), holes may appear in the moving object region when performing moving object segmentation. How to remove these holes is a crucial problem in high-quality segmentation. A moving object segmentation approach combining symmetrical differencing and joint bilateral filtering is proposed. One important aspect of our approach is that joint bilateral filtering is used to eliminate/reduce the holes in the moving object region, which makes the extracted moving object more accurate and complete, in many cases in contrast to the reference temporal difference approaches. The approach first performs block-based symmetrical differencing to obtain coarse moving object regions. Then, a joint bilateral filter that uses the current gray image as a guide image is adopted to smooth the difference image. Next, edge detection is performed on the smoothed difference image and the current gray image, respectively, to get the edges of moving objects. Finally, the undesired background is distinguished from the moving object and is cut off by a postprocessing module. In addition, the fast joint bilateral filters that can be used as substitutes for the classical joint bilateral filter are discussed. Experimental results show that this approach can effectively fill the holes in the moving object region and provide an improvement in accuracy of moving object segmentation in many cases.
© 2014 SPIE and IS&T
Ran Liu, Bole Li, Zhengwei Huang, Donghua Cao, Yingchun Tan, Zekun Deng, Miao Xu, Ruishuang Jia, Weimin Tan, "Hole filling using joint bilateral filtering for moving object segmentation," Journal of Electronic Imaging 23(6), 063021 (18 December 2014). https://doi.org/10.1117/1.JEI.23.6.063021 . Submission:
JOURNAL ARTICLE
17 PAGES


SHARE
RELATED CONTENT

Extraction of moving objects for content-based video coding
Proceedings of SPIE (December 28 1998)
Object tracking for video annotation
Proceedings of SPIE (November 02 2004)
Real time approach to recognizing the human face in poor...
Proceedings of SPIE (September 21 2001)
Livewire based single still image segmentation
Proceedings of SPIE (December 08 2011)

Back to Top