Foreground Object Detection from a Moving Video Camera 林家宇、曾逸鴻
E-mail: 9707242@mail.dyu.edu.tw
ABSTRACT
For computer vision field, the intelligent video monitoring systems is always an important subject. Many high-tech surveillance technologies, software and hardware installations provide against danger. However, not all solutions applied to many different circumstances. Compared to traditional build-in camera, mobile camera not only avoids many dead angle situations, but also save huge cost on facilities. Furthermore, mobile camera reaches a higher and better quality surveillance result. The research on this paper will mainly focus on video monitoring system development using mobile camera for moving objects detecting and tracking.
Background changes while camera is in moving motion. Therefore, the traditional background subtraction would not be the best solution for detecting the foreground objects. Essentially, the emphasis on this paper will be the research on using optical flow analytics to improved and avoid traditional weakness and combined with the optical flow character in order to track moving object.
Keywords : mobile camera ; optical flow ; moving object detection ; background subtraction Table of Contents
中文摘要 ．．．．．．．．．．．．．．．．．．．．．． iii 英文摘要 ．．．．．．．．．．．．．．．．．．．．
．． iv 誌謝辭 ．．．．．．．．．．．．．．．．．．．．．． v 內容目錄 ．．．．．．．．．．．．．．．．．．
．．．． vi 表目錄 ．．．．．．．．．．．．．．．．．．．．．． viii 圖目錄 ．．．．．．．．．．．．．．．．
．．．．．． ix 第一章 緒論．．．．．．．．．．．．．．．．．．．． 1 第一節 研究背景與動機．．．．
．．．．．．．．． 1 第二節 研究目的．．．．．．．．．．．．．．．． 2 第三節 研究限制．．．．．．
．．．．．．．．．． 3 第四節 論文架構．．．．．．．．．．．．．．．． 4 第二章 文獻探討．．．．．．．
．．．．．．．．．．． 5 第一節 移動物體偵測．．．．．．．．．．．．．． 5 第二節 光流偵測技術及加 速方法．．．．．．．．． 9 第三節 移動物體追蹤．．．．．．．．．．．．．． 13 第四節 利用光流進行移動物體 偵測．．．．．．．． 14 第三章 移動物體偵測．．．．．．．．．．．．．．．． 16 第一節 光流計算．．．．
．．．．．．．．．．．． 16 第二節 光流計算之加速．．．．．．．．．．．．． 18 第三節 前景物體偵測．．
．．．．．．．．．．．． 32 第四節 動態調整畫面擷取頻率．．．．．．．．．． 37 第四章 移動物體追蹤．．
．．．．．．．．．．．．．． 40 第一節 物體特徵抽取及調整．．．．．．．．．．． 40 第二節 移動物體比對
．．．．．．．．．．．．．．． 43 第五章 實驗結果與討論．．．．．．．．．．．．．．． 46 第六章 結論．
．．．．．．．．．．．．．．．．．．． 50 參考文獻 ．．．．．．．．．．．．．．．．．．．．．． 52 REFERENCES
Aggarwal, J. K. & Zhou, Q. (2006). Object tracking in an outdoor environment using fusion of features and cameras. Computer Vision and Image Understanding, 24 (11), 1244-1255. Ahmad, A. M., Ahmad, B. M. & Lee, S. Y. (2004). Fast and robust object detection framework in compressed domain. IEEE International Symposium on Multimedia Software Engineering, 210-217. Barron, J. L., Fleet, D. J. & Beauchemin, S. S. (1994).
Performance of optical flow techniques. International Journal of Computer Vision 12 (1), 43-77. Beauchemin, S. S. & Barron, J. L. (1995). The computation of optical flow. ACM Computing Surveys, 27 (3), 433-467. Chen, K. Y., Cheng, M. Y. & Tsai, M. C. (2002). Design and
implementation of a real-time pan-tilt visual tracking system. IEEE International Conference on Control Applications, 736-741. Cheng, F. H. &
Chen, Y. L. (2006). Real time multiple objects tracking and identification based on discrete wavelet transform. Pattern Recognition, 39 (6), 1126-1139. Collins, R. T., Liu, Y. & Leordeanu, M. (2005). Online selection of discriminative tracking features. IEEE Transactions on Pattern Analysis and Machine Intelligentce, 27 (10), 1631-1643. Denman, S., Chandran, V. & Sridharan, S. (2007). An adaptive optical flow technique for person tracking systems. Pattern Recognition Letters, 28, 1232-1239. Elgammal, A., Harwood, D. & Davis, L. (2000). Non-parametric model for background subtraction. European Conference on Computer Vision, 751-767. Heeger, D. J. (1988). Optical flow using spatiotemporal filters.
International Journal of Computer Vision, 279-302. Horn, B. K. & Schunck, B. G. (1981). Determining optical flow. Artificial Intelligence, 17, 185-203. Kang, H. & Kim, D. (2005). Real-time multiple people tracking using competitive condensation. Pattern Recognition, 38 (7), 1045-1058.
Lerdsudwichai, C., Abdel-Mottaleb, M. & Ansari, A. N. (2005). Tracking multiple people with recovery from partial and total occlusion. Pattern Recognition, 38 (7), 1059-1070. Ohta, N. (2001). A statistical approach to background subtraction for surveillance systems. IEEE International
Conference on Computer Vision, 2, 481-486. Seki, M., Fujiwara, H. & Sumi, K. (2000). A robust background subtraction method for changing background. IEEE Workshop on Applications of Computer Vision, 207-213. Senior, A., Hampapur, A., Tian, Y. L., Brown, L., Pankanti, S. &
Bolle, R. (2006). Appearance models for occlusion handling. Computer Vision and Image Understanding, 24 (11), 1233-1243. Sun, C. (2002). Fast optical flow using 3D shortest path techniques. Image and Vision Computing, 20, 981-991. Tagliasacchi, M. (2007). A genetic algorithm for optical flow estimation. Image and Vision Computing, 25, 141-147. Tissainayagama, P. & Suterb, D. (2005). Object tracking in image sequences using point features. Pattern Recognition, 38 (1), 105-113. Tseng, Y. H. & Lin, Y. Y. (2007). Multiple objects tracking in a night environment with weak lamplight. Proceedings of the 20th Conference on Computer Vision, Graphics and Image Processing, 786-793, Miaoli. Zelek, J. S. (2004). Towards Bayesian real-time optical flow. Image and Vision Computing, 22, 1051-1069.
