caa a22 4500 605446954 CHVBK 20210128100129.0 cr unu---uuuuu 210128e20151101xx s 000 0 eng 10.1007/s11042-014-2145-5 doi (NATIONALLICENCE)springer-10.1007/s11042-014-2145-5 Video object segmentation by integrating trajectories from points and regions [Elektronische Daten] [Geng Zhang, Zejian Yuan, Yuehu Liu, Liang Ma, Nanning Zheng] We describe a novel video object segmentation system based on a conditional random field model with high-order term which is capable of capturing longer-range spatial and temporal grouping information. Our system is able to segment different moving objects effectively from complex background due to integrating the complementary properties of trajectories from points and regions. Although point and region trajectories have already been used in video object segmentation, their complementary properties have not been well investigated. In this paper, we propose an ingenious scheme to transfer the labels of sparse point trajectories to region trajectories. Especially, for region trajectories with few texture, this scheme can automatically predict their label probabilities by using a Gaussian mixture model of appearance and motion given the labels of point trajectories. Meanwhile, we design a reliability measurement for region trajectories based on shape consistency, which helps us to design robust high-order potentials for spatially overlapping region trajectories. Our region trajectories are extracted from hierarchical image over-segmentation, and hence they can capture meaningful regions over time. Additionally, our approach is a streaming process, in which object labels are propagated over a video. We validate the effectiveness of our approach on public challenging datasets, and show that our approach outperforms other competing methods Springer Science+Business Media New York, 2014 Video object segmentation nationallicence Point tajectory nationallicence Region trajectory nationallicence Complementary property nationallicence High-order model nationallicence Zhang Geng Institute of Artificial Intelligence and Robotics, #28 West Xianning Road, Xi'an, Shaanxi, People's Republic of China aut Yuan Zejian Institute of Artificial Intelligence and Robotics, #28 West Xianning Road, Xi'an, Shaanxi, People's Republic of China aut Liu Yuehu Institute of Artificial Intelligence and Robotics, #28 West Xianning Road, Xi'an, Shaanxi, People's Republic of China aut Ma Liang Institute of Artificial Intelligence and Robotics, #28 West Xianning Road, Xi'an, Shaanxi, People's Republic of China aut Zheng Nanning Institute of Artificial Intelligence and Robotics, #28 West Xianning Road, Xi'an, Shaanxi, People's Republic of China aut Multimedia Tools and Applications Springer US; http://www.springer-ny.com 74/21(2015-11-01), 9665-9696 1380-7501 74:21<9665 2015 74 11042 https://doi.org/10.1007/s11042-014-2145-5 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s11042-014-2145-5 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Zhang Geng Institute of Artificial Intelligence and Robotics, #28 West Xianning Road, Xi'an, Shaanxi, People's Republic of China aut NATIONALLICENCE 700 1- Yuan Zejian Institute of Artificial Intelligence and Robotics, #28 West Xianning Road, Xi'an, Shaanxi, People's Republic of China aut NATIONALLICENCE 700 1- Liu Yuehu Institute of Artificial Intelligence and Robotics, #28 West Xianning Road, Xi'an, Shaanxi, People's Republic of China aut NATIONALLICENCE 700 1- Ma Liang Institute of Artificial Intelligence and Robotics, #28 West Xianning Road, Xi'an, Shaanxi, People's Republic of China aut NATIONALLICENCE 700 1- Zheng Nanning Institute of Artificial Intelligence and Robotics, #28 West Xianning Road, Xi'an, Shaanxi, People's Republic of China aut NATIONALLICENCE 773 0- Multimedia Tools and Applications Springer US; http://www.springer-ny.com 74/21(2015-11-01), 9665-9696 1380-7501 74:21<9665 2015 74 11042