Spatiotemporal segmentation for compact video representation |
| |
| Affiliation: | 1. Department of Information Systems Engineering, Osaka University, Osaka 565, Japan;2. Department of Computer Sciences, Fudan University, Shanghai 200433, China;3. Department of Electronic Engineering, Southern Methodist University, Dallas TX 75275, USA;1. Eastern Virginia Medical School, 825 Fairfax Avenue, Norfolk, VA, 23507, United States;2. Department of Dermatology, Massachusetts General Hospital, 50 Staniford Street, Suite 200, Boston, MA, 02114, United States;3. Professor of Dermatology, University of Arizona, Medical Dermatology Specialists, 1331 N 7th Suite 250, Phoenix, AZ, 85006, United States;1. Institute of Mechanics, Materials and Civil Engineering - Materials & Process Engineering (iMMC-IMAP), UCLouvain, Place Sainte Barbe 2, 1348 Louvain-la-Neuve, Belgium;2. Research & Innovation Centre for Process Engineering (ReCIPE), Place Sainte Barbe, 2 bte L5.02.02, B-1348 Louvain-la-Neuve, Belgium;1. Department of Medical Oncology, San Raffaele Scientific Institute, Milan, Italy;2. IRCCS Arcispedale S Maria Nuova Azienda Ospedaliera di Reggio Emilia, Reggio Emilia, Italy;3. European Institute of Oncology, Milan, Italy;4. Department of Medical Oncology, IRCCS Azienda Ospedaliera Universitaria San Martino—IST, Genoa, Italy;5. SSD Medical Oncology Addari, Policlinico Sant''Orsola Malpighi, Bologna, Italy;6. Department of Oncology, Azienda Sanitaria Universitaria Integrata, Udine, Italy;7. Oncology, Azienda Ospedaliero Universitaria di Ferrara—Arcispedale Sant''Anna, Ferrara, Italy;8. Fondazione Michelangelo, Milan, Italy;1. State Key Laboratory of Biochemical Engineering, Institute of Process Engineering, Chinese Academy of Sciences, 100190 Beijing, China;2. Institute of Fundamental Medicine and Biology, Kazan Federal University, Kazan 420008, Republic of Tatarstan, Russian Federation;3. School of Chemical Engineering, University of Chinese Academy of Sciences, 100049 Beijing, China;4. Center for Mesoscience, Institute of Process Engineering, Chinese Academy of Sciences, 100190 Beijing, China;1. Children’s Research Institute and the Department of Pediatrics, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA;2. Department of Neurology, Changzheng Hospital, Second Military Medical University, Shanghai 200003, China;3. Department of Internal Medicine, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA;4. Department of Neurology and Neurotherapeutics, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA;5. Tongji Hospital Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei 4300030, China;6. Department of Pathology, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA;7. Department of Radiology, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA;8. Department of Bioengineering, University of Texas, Arlington, TX 76010, USA;9. Department of Anatomy, Histology and Embryology, School of Basic Medical Sciences, Fudan University, Shanghai 200032, China;10. Department of Neuroscience, Graduate School of Biomedical Sciences, Tufts University School of Medicine, Tufts University, Boston, MA 02111, USA;11. Department of Microbiology, Immunology, and Cancer Biology, University of Virginia, Charlottesville, VA 22908, USA;12. Chinese Institute for Brain Research, Beijing 102206, China;13. School of Basic Medical Sciences, Capital Medical University, Beijing 100069, China;14. Harold C. Simmons Comprehensive Cancer Center, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA;15. Department of Neuroscience, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA |
| |
| Abstract: | In this paper, a novel hierarchical object-oriented video segmentation and representation algorithm is proposed. The local variance contrast and the frame difference contrast are jointly exploited for structural spatiotemporal video segmentation because these two visual features can indicate the spatial homogeneity of the grey levels and the temporal coherence of the motion fields efficiently, where the two-dimensional (2D) spatiotemporal entropic technique is further selected for generating the 2D thresholding vectors adaptively according to the variations of the video components. After the region growing and edge simplification procedures, the accurate boundaries among the different video components are further exploited by an intra-block edge extraction procedure. Moreover, the relationships of the video components among frames are exploited by a temporal tracking procedure. This proposed object-oriented spatiotemporal video segmentation algorithm may be useful for MPEG-4 system generating the video object plane (VOP) automatically. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
