TCSVT Special Issue Video Analysis on Resource-Limited Systems

IEEE Transactions Circuits and Systems for Video Technology

Special Issue on
Video Analysis on Resource-Limited Systems

Guest Editors
Rama Chellappa, University of Maryland, USA
Andrea Cavallaro, Queen Mary, University of London, UK
Ying Wu, Northwestern University, USA
Caifeng Shan, Philips Research, The Netherlands
Yun (Raymond) Fu, University at Buffalo (SUNY), USA
Kari Pulli, Nokia Research Center (NRC) Palo Alto, USA

Submission deadline: Dec. 15, 2010
Notification of acceptance: Jun. 15, 2011
Final manuscript due: Jun. 30, 2011
Tentative publication date: Oct. 2011

In many real-world video analytics systems, the available resource is limited. This could mean low-quality data (e.g., limited imaging resolution/sensor size/frame rate), such as video footage from surveillance cameras and videos captured by consumers via mobile or wearable cameras. Another dimension comes from limited amount of processing power, for example, on mobile camera phones. There is a huge demand for video analysis and computer vision techniques on resource-limited systems. However, although there are some existing studies, video analysis on low-quality video data or with limited computing power is still an under-explored field. The existing video analysis research mainly focuses on high-performance systems, that is, high-quality video data or powerful computing platforms. There aremany challenges when addressing video analysis on resource-limited systems. For example, how to effectively extract representative visual features from low-quality data? How to fuse mult
iple low-resolution frames for reliable recognition? How to accelerate vision algorithms for use on mobile platforms? How to mitigate degrading factors caused by the low quality data? We have to adapt the existing approaches developed for high-performance systems or find new techniques suitable for resource-limited systems.

This special issue seeks to present and highlight the latest developmentson video analysis and computer vision on resource-limited systems. Submissions that address real-world applications are especially encouraged.

Topics of interest include, but are not limited to,
– Feature extraction from low-quality data
– Super-resolution
– Video stabilization
– Object detection in low-quality data
– Visual tracking on resource-limited systems
– Image recognition on mobile devices
– Face image analysis on resource-limited systems
– (Soft-)biometrics (face, body, gait, … ) in low-quality data – Gesture recognition in low-quality data
– Human activity analysis in low-quality data
– Video analysis on resource-limited platforms (UAVs, toy robots, capsuleendoscopy, …) – Energy optimization for video coding on resource-limited devices – Multiple-view analysis of low-quality data
– Low-cost smart camera networks with embedded computing
– Video analysis on low-cost non-classical cameras (e.g., omni-directional cameras)
– Real-world applications on resource-limited systems (smart environments, safety and surveillance, entertainment …) – Evaluation of video analysis algorithms on resource-limited systems