In the era of information explosion, especially the data rich but information poor epoch, how can we effectively secure useful information with limited time becomes a fundamental issue. Considering we are browsing a tedius video content, many skip and/or fast forward operations have to be done to filter out the worthlessness. Usually, the chosen video playback speed is adapted to the sort of video clip and user preference as well. In this thesis, the aim is to play surveillance videos in an efficient, convenient and smooth way.
We abstract some necessary information while encoding the video content and form a set of fast forward parameters, which shows where the playback speed has to be tuned. With the referencing of these essential parameters, video program can be controlled and played in the high and suitable speed automatically.
To decide the rate for different time intervals, we employ saliency detection concept to simulate the conceivable human perception. In the implementation, attention values are mesaured by statisticals of both saliency and motion features, thus the fast forward parameters are mapped based on the curve of attention values accordingly. Finally, we proposed an innovative mechanism to evaluate whether the user’ perception information is preserved while fast forwarding the videos. According to the experimental results, the proposed automatic fast forward method is effective, convenient, smooth, and fulfilled with users’ demand.

在這個網路發達的年代，各式各樣的資訊充斥在我們的日常生活中，如何在有限的時間內獲取最大的資訊成為一個我們所關注的課題。在平日我們觀看冗長的影片時，針對不同的影片類型，我們常常會使用跳段或是加快播放速度的方式快速瀏覽過整個影片內容，並且在快轉影片時，依照使用者的時間考量或是影片的內容來改變快轉的速度。這篇論文將主題放在如何能有效率地播放監視系統影片，在影片壓縮的過程中擷取必要的資訊，產生一組影片播放速度的建議參數，標示出影片需要慢速播放或是快速前進的地方，因此影片在播放時就可參照這組參數來達到自動改變快轉速率的目的。
為了要決定不同時間點的快轉速率，我們利用特徵圖資訊模擬人類視覺注目度，標示出不同時間點時影片的對視覺產生的資訊量而產生出一條注意力曲線，接著將注目度對應到快轉速率的改變值。最後我們提出一個新方法來量測影片快轉後重要的資訊是否有被保留。經由實驗我們可以得知，自動快轉的方式可以在符合使用者需求並且不遺漏影片重要資訊的要求下大量節省觀看時間。

[1] K. A. Peker and A. Divakaran, "An extended framework for adaptive playback-based video summarization," Internet Multimedia Management Systems, 2003.
[2] Y. Li, S.-H. Lee, C.-H. Yeh, and J. Kuo, "Techniques for movie content analysis and skimming: tutorial and overview on video abstraction techniques," IEEE Signal Processing Magazine, vol. 23, pp. 79-89, 2006.
[3] C.-W. Ngo, Y.-F. Ma, and H.-J. Zhang, "Video summarization and scene detection by graph modeling," IEEE Transactions on Circuits and Systems for Video Technology, vol. 15, pp. 296-305, 2005.
[4] Y.-F. Ma and H.-J. Zhang, "Video snapshot: a bird view of video sequence," Proceedings of International Multimedia Modelling, pp. 94-101, 2005.
[5] Y.-F. Ma, L. Lu, H.-J. Zhang, and M. Li, "A user attention model for video summarization," Proceedings of the tenth ACM international conference on Multimedia, pp. 533-542, 2002.
[6] L. Herranz and J. M. Martinez, "A Framework for Scalable Summarization of Video," IEEE Transactions on Circuits and Systems for Video Technology, vol. 20, pp. 1265-1270, 2010.
[7] T. Wang, T. Mei, X.-S. Hua, X.-L. Liu, and H.-Q. Zhou, "Video Collage: A Novel Presentation of Video Sequence," IEEE International Conference on Multimedia and Expo, pp. 1479-1482, 2007.
[8] H. Luo and J. Fan, "Concept-oriented video skimming and adaptation via semantic classification," Proceedings of international workshop on Multimedia information retrieval, 2004.
[9] K. A. Peker, A. Divakaran, and S. Huifang, "Constant pace skimming and temporal sub-sampling of video using motion activity," International Conference on Image Processing, pp. 414-417, 2001.
[10] L. Shi, M. R. Lyu, and I. King, "Video summarization by spatial-temporal graph optimization," Proceedings of International Symposium on Circuits and Systems, pp. 197-200, 2004.
[11] Y.-F. Ma and H.-J. Zhang, "A model of motion attention for video skimming," International Conference on Image Processing, pp. 129-132, 2002.
[12] B. Hoferlin, M. Hoferlin, D. Weiskopf, and G. Heidemann, "Information-based adaptive fast-forward for visual surveillance," Multimedia Tools and Applications, 2010.
[13] N. Petrovic, N. Jojic, and T. S. Huang, "Adaptive Video Fast Forward," Multimedia Tools and Applications, vol. 26, pp. 327-344, 2005.
[14] L. Itti, C. Koch, and E. Niebur, "A model of saliency-based visual attention for rapid scene analysis," IEEE Transaction on Pattern Analysis and Machine Intelligence, 1998.
[15] J. Harel, C. Koch, and P. Perona, "Graph-based visual saliency," Advances in Neural Information Processing Systems, pp. 545-552, 2007.
[16] K. A. Peker and A. Divakaran, "Adaptive fast playback-based video skimming using a compressed-domain visual complexity measure," IEEE International Conference on Multimedia and Expo, pp. 2055-2058, 2004.
[17] K.-Y. Cheng, S.-J. Luo, B.-Y. Chen, and H.-H. Chu, "SmartPlayer: user-centric video fast-forwarding," International conference on Human factors in computing systems, 2009.
[18] F. Li, A. Gupta, E. Sanocki, L.-W. He, and Y. Rui, "Browsing digital video," Proceedings of the SIGCHI conference on Human factors in computing systems, The Hague, The Netherlands, pp. 169-176, 2000.
[19] Z. Chen, W. Lin, and K. N. Ngan, "Perceptual video coding: Challenges and approaches," IEEE International Conference on Multimedia and Expo (ICME), pp. 784-789, 2010.
[20] C. Guo and L. Zhang, "A novel multiresolution spatiotemporal saliency detection model and its applications in image and video compression," IEEE Transactions on Image Processing, vol. 19, pp. 185-198, 2010.
[21] L. Itti, C. Koch, and E. Niebur, "A model of saliency-based visual attention for rapid scene analysis," IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1254-1259, 1998.
[22] Y. Xia, R. Hu, Z. Huang, and Y. Su, "A novel method for generation of motion saliency," IEEE International Conference on Image Processing, pp. 4685-4688, 2010.
[23] X. Song and G. Fan, "Selecting salient frames for spatiotemporal video modeling and segmentation," IEEE Transactions on Image Processing, vol. 16, pp. 3035-3046, 2007.
[24] W. Kim, C. Jung, and C. Kim, "Spatiotemporal saliency detection and its applications in static and dynamic scenes," IEEE Transactions on Circuits and Systems for Video Technology, vol. 21, pp. 446-456, 2011.
[25] L. Itti, N. Dhavale, and F. Pighin, "Realistic avatar eye and head animation using a neurobiological model of visual attention," pp. 64-78, 2004.
[26] S. Pongnumkul, J. Wang, G. Ramos, and M. Cohen, "Content-aware dynamic timeline for video browsing," Proceedings of the Symposium on User interface software and technology, 2010.
[27] PETS2001 Datasets. Available: http://www.cvg.cs.rdg.ac.uk/PETS2001/pets2001-dataset.html
[28] L. M. Brown, A. W. Senior, Y.-l. Tian, J. Connell, A. Hampapur, C.-f. Shu, H. Merkl, and M. Lu, "Performance evaluation of surveillance systems under varying conditions," IEEE Int'l Workshop on Performance Evaluation of Tracking and Surveillance, 2005.