Advanced search

Estimating motion reliability to improve moving object detection in the H.264/AVC domain

Sarah De Bruyne (UGent) , Chris Poppe (UGent) , Steven Verstockt (UGent) , Peter Lambert (UGent) and Rik Van de Walle (UGent)
Author
Organization
Abstract
This paper presents a new algorithm for moving object detection in the H.264/AVC compressed domain which relies on motion vector information. In contrast to other motion vector-based algorithms, special attention is paid to noisy motion vectors as they highly decrease the performance of these algorithms. We propose to estimate the reliability of motion vectors by comparing them with projected motion vectors from surrounding frames. As such, noisy motion vectors are localized. By combining this information with the magnitude of motion vectors, foreground objects are distinguished. Experimental results demonstrate that our algorithm achieves significantly better segmentation quality compared to other motion vector-based approaches.
Keywords
motion reliability, object detection, H.264/AVC, COMPRESSED-DOMAIN, SEGMENTATION

Citation

Please use this url to cite or link to this publication:

Chicago
De Bruyne, Sarah, Chris Poppe, Steven Verstockt, Peter Lambert, and Rik Van de Walle. 2009. “Estimating Motion Reliability to Improve Moving Object Detection in the H.264/AVC Domain.” In Proceedings. Ieee International Conference on Multimedia and Expo, 330–333. New York, NY, USA: IEEE.
APA
De Bruyne, Sarah, Poppe, C., Verstockt, S., Lambert, P., & Van de Walle, R. (2009). Estimating motion reliability to improve moving object detection in the H.264/AVC domain. PROCEEDINGS. IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (pp. 330–333). Presented at the 2009 IEEE International Conference on Multimedia and Expo (ICME), New York, NY, USA: IEEE.
Vancouver
1.
De Bruyne S, Poppe C, Verstockt S, Lambert P, Van de Walle R. Estimating motion reliability to improve moving object detection in the H.264/AVC domain. PROCEEDINGS. IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO. New York, NY, USA: IEEE; 2009. p. 330–3.
MLA
De Bruyne, Sarah, Chris Poppe, Steven Verstockt, et al. “Estimating Motion Reliability to Improve Moving Object Detection in the H.264/AVC Domain.” Proceedings. Ieee International Conference on Multimedia and Expo. New York, NY, USA: IEEE, 2009. 330–333. Print.
@inproceedings{740029,
  abstract     = {This paper presents a new algorithm for moving object detection in the H.264/AVC compressed domain which relies on motion vector information. In contrast to other motion vector-based algorithms, special attention is paid to noisy motion vectors as they highly decrease the performance of these algorithms. We propose to estimate the reliability of motion vectors by comparing them with projected motion vectors from surrounding frames. As such, noisy motion vectors are localized. By combining this information with the magnitude of motion vectors, foreground objects are distinguished. Experimental results demonstrate that our algorithm achieves significantly better segmentation quality compared to other motion vector-based approaches.},
  author       = {De Bruyne, Sarah and Poppe, Chris and Verstockt, Steven and Lambert, Peter and Van de Walle, Rik},
  booktitle    = {PROCEEDINGS. IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO},
  isbn         = {9781424442904},
  issn         = {1945-788X},
  language     = {eng},
  location     = {New York, NY, USA},
  pages        = {330--333},
  publisher    = {IEEE},
  title        = {Estimating motion reliability to improve moving object detection in the H.264/AVC domain},
  url          = {http://dx.doi.org/10.1109/ICME.2009.5202501},
  year         = {2009},
}

Altmetric
View in Altmetric
Web of Science
Times cited: