Details
| Original language | English |
|---|---|
| Title of host publication | 2013 Picture Coding Symposium |
| Subtitle of host publication | PCS 2013 - Proceedings |
| Publisher | IEEE Computer Society |
| Pages | 129-132 |
| Number of pages | 4 |
| ISBN (print) | 9781479902941 |
| Publication status | Published - 2013 |
| Event | 2013 Picture Coding Symposium, PCS 2013 - San Jose, CA, United States Duration: 8 Dec 2013 → 11 Dec 2013 |
Publication series
| Name | 2013 Picture Coding Symposium, PCS 2013 - Proceedings |
|---|
Abstract
Current Moving Object Detectors in airborne Region of Interest (ROI) coding systems for police surveillance applications used on-board of UAVs are often based on Global Motion Estimation (GME) techniques. Since in these scenarios the camera is moving, simple background removal approaches cannot be applied without a Global Motion Compensation (GMC). Common GMC algorithms assume the ground to be planar, allowing the pixels of the previous frame to be motion compensated into the current frame by applying a projective transformation. The difference image between the compensated frame and the current frame emphasis regions containing possible motion. Such moving object detectors are great in terms of run-time efficiency but are known to lack in terms of accuracy - especially for unstructured regions of moving objects - as well as the robustness against noise. Superpixel segmentation was recently proposed to overcome the issue of the imprecise region cuts given by the difference image. It provides a greatly improved true positive detection rate, but unintentionally also increases the area of false positives. This paper proposes the use of a mesh-based GME and GMC to detect the moving object regions wherein a cluster filter eliminates errors in the optical flow by assuming a smooth vector field as the global motion model. In doing so we improve the coding efficiency of the fully automatic ROI coding system by more than 24% for moving object areas conserving the detection benefits of the integration of superpixel segmentation.
Keywords
- Aerial surveillance, Global motion compensation, Low bit rate video coding, Mesh, Moving object detection, Optical flow, ROI Coding, Superpixel
ASJC Scopus subject areas
- Computer Science(all)
- Computer Vision and Pattern Recognition
- Computer Science(all)
- Software
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2013 Picture Coding Symposium: PCS 2013 - Proceedings. IEEE Computer Society, 2013. p. 129-132 6737700 (2013 Picture Coding Symposium, PCS 2013 - Proceedings).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Optical Flow Cluster Filtering for ROI Coding
AU - Meuel, Holger
AU - Munderloh, Marco
AU - Reso, Matthias
AU - Ostermann, Jorn
PY - 2013
Y1 - 2013
N2 - Current Moving Object Detectors in airborne Region of Interest (ROI) coding systems for police surveillance applications used on-board of UAVs are often based on Global Motion Estimation (GME) techniques. Since in these scenarios the camera is moving, simple background removal approaches cannot be applied without a Global Motion Compensation (GMC). Common GMC algorithms assume the ground to be planar, allowing the pixels of the previous frame to be motion compensated into the current frame by applying a projective transformation. The difference image between the compensated frame and the current frame emphasis regions containing possible motion. Such moving object detectors are great in terms of run-time efficiency but are known to lack in terms of accuracy - especially for unstructured regions of moving objects - as well as the robustness against noise. Superpixel segmentation was recently proposed to overcome the issue of the imprecise region cuts given by the difference image. It provides a greatly improved true positive detection rate, but unintentionally also increases the area of false positives. This paper proposes the use of a mesh-based GME and GMC to detect the moving object regions wherein a cluster filter eliminates errors in the optical flow by assuming a smooth vector field as the global motion model. In doing so we improve the coding efficiency of the fully automatic ROI coding system by more than 24% for moving object areas conserving the detection benefits of the integration of superpixel segmentation.
AB - Current Moving Object Detectors in airborne Region of Interest (ROI) coding systems for police surveillance applications used on-board of UAVs are often based on Global Motion Estimation (GME) techniques. Since in these scenarios the camera is moving, simple background removal approaches cannot be applied without a Global Motion Compensation (GMC). Common GMC algorithms assume the ground to be planar, allowing the pixels of the previous frame to be motion compensated into the current frame by applying a projective transformation. The difference image between the compensated frame and the current frame emphasis regions containing possible motion. Such moving object detectors are great in terms of run-time efficiency but are known to lack in terms of accuracy - especially for unstructured regions of moving objects - as well as the robustness against noise. Superpixel segmentation was recently proposed to overcome the issue of the imprecise region cuts given by the difference image. It provides a greatly improved true positive detection rate, but unintentionally also increases the area of false positives. This paper proposes the use of a mesh-based GME and GMC to detect the moving object regions wherein a cluster filter eliminates errors in the optical flow by assuming a smooth vector field as the global motion model. In doing so we improve the coding efficiency of the fully automatic ROI coding system by more than 24% for moving object areas conserving the detection benefits of the integration of superpixel segmentation.
KW - Aerial surveillance
KW - Global motion compensation
KW - Low bit rate video coding
KW - Mesh
KW - Moving object detection
KW - Optical flow
KW - ROI Coding
KW - Superpixel
UR - http://www.scopus.com/inward/record.url?scp=84897678874&partnerID=8YFLogxK
U2 - 10.1109/PCS.2013.6737700
DO - 10.1109/PCS.2013.6737700
M3 - Conference contribution
AN - SCOPUS:84897678874
SN - 9781479902941
T3 - 2013 Picture Coding Symposium, PCS 2013 - Proceedings
SP - 129
EP - 132
BT - 2013 Picture Coding Symposium
PB - IEEE Computer Society
T2 - 2013 Picture Coding Symposium, PCS 2013
Y2 - 8 December 2013 through 11 December 2013
ER -