Construction of a Video Dataset for Face Tracking Benchmarking Using a Ground Truth Generation Tool
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
In the current generation of smart mobile devices, object tracking is one of the most important research topics for computer vision. Because human face tracking can be widely used for many applications, collecting a dataset of face videos is necessary for evaluating the performance of a tracker and for comparing different approaches. Unfortunately, the well-known benchmark datasets of face videos are not sufficiently diverse. As a result, it is difficult to compare the accuracy between different tracking algorithms in various conditions, namely illumination, background complexity, and subject movement. In this paper, we propose a new dataset that includes 91 face video clips that were recorded in different conditions. We also provide a semi-automatic ground-truth generation tool that can easily be used to evaluate the performance of face tracking systems. This tool helps to maintain the consistency of the definitions for the ground-truth in each frame. The resulting video data set is used to evaluate well-known approaches and test their efficiency.
Abstract
In the current generation of smart mobile devices, object tracking is one of the most important research topics for computer vision. Because human face tracking can be widely used for many applications, collecting a dataset of face videos is necessary for evaluating the performance of a tracker and for comparing different approaches. Unfortunately, the well-known benchmark datasets of face videos are not sufficiently diverse. As a result, it is difficult to compare the accuracy between different tracking algorithms in various conditions, namely illumination, background complexity, and subject movement. In this paper, we propose a new dataset that includes 91 face video clips that were recorded in different conditions. We also provide a semi-automatic ground-truth generation tool that can easily be used to evaluate the performance of face tracking systems. This tool helps to maintain the consistency of the definitions for the ground-truth in each frame. The resulting video data set is used to evaluate well-known approaches and test their efficiency.
참고문헌 (22)
- R. Gross, "Handbook of Facial Recognition" (2005), Springer
- D. Comaniciu, "Robust detection and tracking of human faces with an active camera", The Third IEEE International Workshop on Visual Surveillance, pp.11~18 (2000)
- M. Kim, "Face tracking and recognition with visual constraints in real-world videos", Conference on Computer Vision and Pattern Recognition, (1), pp.1~8 (2008)
- E. Maggio, "Particle PHD filtering for multi-target visual tracking", ICASSP, 1, pp.1101~1104 (2007)
- F. Dornaika, "Real time 3D face and facial feature tracking", Journal of real-time image processing, 2, pp.35~44 (2007)
- M. D. Cordea, "Three-Dimensional Head Tracking and Facial Expression Recovery Using an Anthropometric Muscle-Based Active Appearance Model", Transactions on Instrumentation and Measurement, pp.1578~1588 (2008)
- G. R. Bradski, "Computer Vision Face Tracking for Use in a Perceptual User Interface", Intel Technology Journal, 2(2), pp.13~27 (1998)
- K. Nummiaro, "An adaptive color-based particle filter", Image Vision Computing, 21(1), pp.99~110 (2003)
- B. Martinkauppi, "Face video database", Proc. First European Conference on Color in Graphics, Imaging and Vision, pp.380~383 (2002)
- T. List, "Performance evaluating the evaluator", ICCCN, pp.129~136 (2005)
- Y. Li, "Evaluating the performance of systems for tracking football players and ball", Proceedings of the IEEE International Conference on Advanced Video and Signal Based Surveillance, pp.632~637 (2005)
- A. T. Nghiem, "ETISEO, performance evaluation for video surveillance systems", Proceedings of the IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS ’07), pp.476~481 (2007)
- K. Smith, "Evaluating multi-object tracking", Proceedings of the IEEE Workshop on Empirical Evaluation Methods in Computer Vision (EEMCV ’05), 3, pp.36~ (2005)
- K. Bernadin, "Evaluating Multiple Object Tracking Performance The CLEAR MOT Metrics", EURASIP Journal on Image and Video Processing, pp.1~11 (2008)
- J. Xiao, "Real-Time Combined 2D+3D Active Appearance Models", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.535~542 (2004)
- R. Stolkin, "An adaptive background model for camshift tracking with a moving camera", Proc. International Conference on Advances in Pattern Recognition, pp.147~151 (2007)
- P. Viola, "Robust Real-Time Face Detection", International Journal of Computer Vision, 57(2), pp.137~154 (2004)
- C. Bao, "Real time robust L1tracker using accelerated proximal gradient approach", CVPR, pp.1830~1837 (2012)
- Z. Xiao, "Object tracking with L2-RLS", ICPR, pp.1351~1354 (2012)