Guanfeng Wang
Roger Zimmermann
ABSTRACT
Camera motion information is one aspect that helps to infer higher-level semantic descriptions in many video applications, e.g., in video retrieval. However, an efficient methodology for annotating camera motion information is still an elusive goal. Here we propose and present a novel and efficient approach for the task of partitioning a video document into sub-shots and characterizing their camera motion. By leveraging location (GPS) and digital compass data, which are available from most current smartphone handsets, we exploit the geographical sensor information to detect transitions between two sub-shots based on the variations of both the camera location and the shooting direction. The advantage of our method lies in its considerable accuracy. Additionally, the computational efficiency of our scheme enables it to be deployed on mobile devices and to process videos while recording. We utilize this capability to show how the HEX motion estimation algorithm in the H.264/AVC encoder can be simplified with the aid of our camera motion information. Our experimental results show that we can reduce the computation of the HEX algorithm by up to 50% while achieving comparable video quality.
- E. Ardizzone, M. La Cascia, A. Avanzato, and A. Bruna. Video Indexing Using MPEG Motion Compensation Vectors. In IEEE Intl. Conference on Multimedia Computing and Systems, volume 2, pages 725--729, July 1999. Google Scholar
Digital Library
- S. Arslan Ay, R. Zimmermann, and S. Kim. Viewable Scene Modeling for Geospatial Video Search. In 16th ACM Intl. Conference on Multimedia, pages 309--318, 2008. Google ScholarDigital Library
- S. Battiato, G. Gallo, G. Puglisi, and S. Scellato. SIFT Features Tracking for Video Stabilization. In 14th Intl. Conference on Image Analysis and Processing, pages 825--830, Sept. 2007. Google ScholarDigital Library
- P. Bouthemy, M. Gelgon, and F. Ganansia. A Unified Approach to Shot Change Detection and Camera Motion Characterization. IEEE Trans. on Circuits and Systems for Video Technology, 9(7):1030--1044, Oct. 1999. Google ScholarDigital Library
- X. Chen, Z. Zhao, A. Rahmati, Y. Wang, and L. Zhong. SaVE: Sensor-assisted Motion Estimation for Efficient H.264/AVC Video Encoding. In 17th ACM Intl. Conference on Multimedia, pages 381--390, 2009. Google ScholarDigital Library
- J. Denzler, V. Schless, D. Paulus, and H. Niemann. Statistical Approach to Classification of Flow Patterns for Motion Detection. In Intl. Conference on Image Processing, pages 517--520, 1996.Google ScholarCross Ref
- L. Duan, J. Jin, Q. Tian, and C. Xu. Nonparametric motion characterization for robust classification of camera motion patterns. IEEE Trans. on Multimedia, 8(2):323--340, 2006. Google ScholarDigital Library
- R. Ewerth, M. Schwalb, P. Tessmann, and B. Freisleben. Estimation of Arbitrary Camera Motion in MPEG Videos. In 17th Intl. Conference on Pattern Recognition, volume 1, pages 512--515, Aug. 2004. Google ScholarDigital Library
- C. Graham, N. Bartlett, J. Brown, Y. Hsia, C. Mueller, and L. Riggs. Vision and Visual Perception. 1965.Google Scholar
- J. Heuer and A. Kaup. Global Motion Estimation in Image Sequences Using Robust Motion Vector Field Segmentation. In 7th ACM Intl. conference on Multimedia, pages 261--264, 1999. Google ScholarDigital Library
- G. Hong, A. Rahmati, Y. Wang, and L. Zhong. SenseCoding: Accelerometer-assisted Motion Estimation for Efficient Video Encoding. In 16th ACM Intl. Conference on Multimedia, pages 749--752, 2008. Google ScholarDigital Library
- R. Jin, Y. Qi, and A. Hauptmann. A Probabilistic Model for Camera Zoom Detection. In 16th Intl. Conference on Pattern Recognition, volume 3, pages 859--862, 2002. Google ScholarDigital Library
- K. Jinzenji, S. Ishibashi, and H. Kotera. Algorithm for Automatically Producing Layered Sprites by Detecting Camera Movement. In Intl. Conference on Image Processing, volume 1, pages 767--770, Oct. 1997. Google ScholarDigital Library
- J. Kim, H. Chang, J. Kim, and H. Kim. Efficient Camera Motion Characterization for MPEG Video Indexing. In IEEE Intl. Conference on Multimedia and Expo, pages 1171--1174, 2000.Google Scholar
- T. Lertrusdachakul, T. Aoki, and H. Yasuda. Camera Motion Estimation by Image Feature Analysis. Pattern Recognition and Image Analysis, pages 618--625, 2005. Google ScholarDigital Library
- J. Park, S. Inoue, and Y. Iwadate. Estimating Camera Parameters from Motion Vectors of Digital Video. In IEEE Second Workshop on Multimedia Signal Processing, pages 105--110, Dec. 1998.Google Scholar
- F. Tiburzi and J. Bescos. Camera Motion Analysis in On-line MPEG Sequences. In 8th Intl. Workshop on Image Analysis for Multimedia Interactive Services, page 42, June 2007. Google ScholarDigital Library
- M. Ulrich and S. Martin. Sensor assited video compression. European Patent Application EP1921867.Google Scholar
- R. Wang and T. Huang. Fast Camera Motion Analysis in MPEG Domain. In Intl. Conference on Image Processing, volume 3, pages 691--694, 1999.Google Scholar
Index Terms
- Sensor-assisted camera motion analysis and motion estimation improvement for H.264/AVC video encoding
Recommendations
Video Encoding without Integer-Pel Motion Estimation
DCC '11: Proceedings of the 2011 Data Compression ConferenceTraditionally, motion estimation (ME) consists of three main steps, including spatial-temporal prediction, integer-pel ME and fractional-pel ME. Integer-pel ME, which searches the integer-pel reference position with a low encoding cost, was considered ...
On using hierarchical motion history for motion estimation in H.264/AVC
The embedded multireference frames selection with variable block-size motion compensation model drastically increases the computational complexity of the H.264/AVC video coding standard. This paper proposes an adaptive hierarchical motion estimation (ME)...
Joint block motion estimation in H.264/AVC
PCS'09: Proceedings of the 27th conference on Picture Coding SymposiumTraditionally, block-based motion estimation (ME) searches for the best motion vector (MV) for one block at a time based upon a pre-defined ME cost. The ME cost is often a function of the best MV and its predictor (MVP). In H.264/AVC, MVP of a block is ...
Comments