Details
| Original language | English |
|---|---|
| Title of host publication | 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance |
| Subtitle of host publication | AVSS 2013 |
| Publisher | IEEE Computer Society |
| Pages | 395-400 |
| Number of pages | 6 |
| ISBN (print) | 9781479907038 |
| Publication status | Published - Oct 2013 |
| Event | 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2013 - Krakow, Poland Duration: 27 Aug 2013 → 30 Aug 2013 |
Publication series
| Name | 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2013 |
|---|
Abstract
A major constraint for mobile surveillance systems (e.g. UAV-mounted) is the limited available bandwidth. Thus, ROI-based video coding, where only important image parts are transmitted with high data rate, seems to be a suitable solution for these applications. The challenging part in these systems is to reliably detect the regions of interest (ROI) and to select the corresponding macroblocks to be encoded in high quality. Recently, difference image-based moving object detectors have been used for this purpose. But as these pixel-based approaches fail for homogeneous parts of moving objects, which leads to artifacts in the decoded video stream, this paper proposes the use of a superpixel-based macroblock selection. It is shown that the proposed approach significantly reduces artifacts by raising the moving objects detection rate from 7 % to over 96 % while increasing the data rate by only 20% to 1.5-4 Mbit/s (full HD resolution, 30 Hz) still meeting the given constraints. Moreover, other simple approaches (dilation) as well as state-of-the-art GraphCut-based approaches are outperformed.
ASJC Scopus subject areas
- Computer Science(all)
- Computer Networks and Communications
- Computer Science(all)
- Signal Processing
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance: AVSS 2013. IEEE Computer Society, 2013. p. 395-400 6636672 (2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2013).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Superpixel-based Segmentation of Moving Objects for Low Bitrate ROI Coding Systems
AU - Meuel, Holger
AU - Reso, Matthias
AU - Jachalsky, Jörn
AU - Ostermann, Jörn
PY - 2013/10
Y1 - 2013/10
N2 - A major constraint for mobile surveillance systems (e.g. UAV-mounted) is the limited available bandwidth. Thus, ROI-based video coding, where only important image parts are transmitted with high data rate, seems to be a suitable solution for these applications. The challenging part in these systems is to reliably detect the regions of interest (ROI) and to select the corresponding macroblocks to be encoded in high quality. Recently, difference image-based moving object detectors have been used for this purpose. But as these pixel-based approaches fail for homogeneous parts of moving objects, which leads to artifacts in the decoded video stream, this paper proposes the use of a superpixel-based macroblock selection. It is shown that the proposed approach significantly reduces artifacts by raising the moving objects detection rate from 7 % to over 96 % while increasing the data rate by only 20% to 1.5-4 Mbit/s (full HD resolution, 30 Hz) still meeting the given constraints. Moreover, other simple approaches (dilation) as well as state-of-the-art GraphCut-based approaches are outperformed.
AB - A major constraint for mobile surveillance systems (e.g. UAV-mounted) is the limited available bandwidth. Thus, ROI-based video coding, where only important image parts are transmitted with high data rate, seems to be a suitable solution for these applications. The challenging part in these systems is to reliably detect the regions of interest (ROI) and to select the corresponding macroblocks to be encoded in high quality. Recently, difference image-based moving object detectors have been used for this purpose. But as these pixel-based approaches fail for homogeneous parts of moving objects, which leads to artifacts in the decoded video stream, this paper proposes the use of a superpixel-based macroblock selection. It is shown that the proposed approach significantly reduces artifacts by raising the moving objects detection rate from 7 % to over 96 % while increasing the data rate by only 20% to 1.5-4 Mbit/s (full HD resolution, 30 Hz) still meeting the given constraints. Moreover, other simple approaches (dilation) as well as state-of-the-art GraphCut-based approaches are outperformed.
UR - http://www.scopus.com/inward/record.url?scp=84890874536&partnerID=8YFLogxK
U2 - 10.1109/AVSS.2013.6636672
DO - 10.1109/AVSS.2013.6636672
M3 - Conference contribution
AN - SCOPUS:84890874536
SN - 9781479907038
T3 - 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2013
SP - 395
EP - 400
BT - 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance
PB - IEEE Computer Society
T2 - 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2013
Y2 - 27 August 2013 through 30 August 2013
ER -