臺灣博碩士論文加值系統

影像辨識在電腦視覺中是一個熱門的議題，對於如何在影像中辨識出人們感興趣的物體，一直都是大家追求的目標，而行人檢出更是影像辨識中一個熱門的主題。在監視系統方面，常有運用成功的案例，例如:保全監視、防盜系統、交通安全…等。
環境的複雜程度及行人的各種姿態，都是行人檢出會面臨到的問題，由於這些問題常會使得行人的外型輪廓無法完整擷取出來，進而無法得到較佳之檢出效果。而本研究將針對行人檢出的問題，發展一套利用Adaboost檢出行人之候選區塊，並結合行人小波特徵與樣板比對的檢出方式，以提高檢出的正確性。經實驗結果顯示，將可以獲得不錯的檢出率及檢出精確率。

Pattern recognition is a popular issue in area of computer vision . How to recognize objects of interest is always our goal to achieve, and pedestrian detection is even a very hot subject in pattern recognition. In the aspect of surveillance system, there are often successful projects, such as safety surveillance, burglarproof system, traffic safety, etc.
The complexity of the environment and every posture of pedestrian are all the problems we will face when detecting pedestrians. Due to these problems we meet, we often can’t completely extract the shape and the contour of pedestrians, and we can’t get ideal detection results. According to the pedestrian detection problems, this study will develop Adaboost to detect candidate regions of pedestrians in combination with pedestrian wavelet features and template matching as to rise accuracy. In our experiments, the result shows good detection ratio and detection accuracy ratio.

英文摘要 I
中文摘要 II
誌 謝 III
目 錄 IV
圖表索引 VI
第一章 緒論 1
1.1 研究背景與動機 1
1.2 論文架構 2
第二章 文獻回顧 3
2.1 變化檢出 3
2.1.1時間差異法 3
2.1.2背景相減法 4
2.2 樣板比對 5
第三章 行人檢出 9
3.1 積分影像 9
3.2 矩形特徵 11
3.3 Adaboost演算法 12
3.4 串聯式分類器 14
3.5 行人樣板 17
3.5.1多重解析處理 17
3.5.2子頻帶分析 18
3.5.3 Haar離散小波轉換 19
3.5.4小波行人樣板 23
第四章 實驗結果 26
4.1 行人檢出之流程圖 27
4.2 Adaboost之訓練樣本及參數設定 27
4.3 Adaboost實驗的初步結果與討論 29
4.4 建立小波行人樣板 36
4.4.1小波行人樣本 36
4.4.2小波行人樣本分類討論 38
4.4.3小波行人樣本之選取 39
4.4.4待測影像輪廓擷取 41
4.4.5利用小波行人樣板之行人檢出 44
4.5 結合Adaboost及小波行人樣板之行人檢出 44
第五章 結論與未來展望 58
5.1 結論 58
5.2 未來展望 58
參考文獻 60

[1]S. Huwer and H. Niemann, "Adaptive change detection for real-time surveillance applications," Proceedings of the Third IEEE International Workshop on Visual Surveillance, pp. 37-46, 2000.
[2]F. E. Alsaqre and B. Yuan, "Multiple moving objects tracking for video surveillance systems," 2004 7th International Conference on Signal Processing, vol.2, pp. 1301-1305, 2004.
[3]D. M. Gavrila and V. Philomin, "Real-time object detection for “smart” vehicles," Proceedings of the Seventh IEEE International Conference on Computer Vision, vol.1, pp. 87-93, 1999.
[4]B. Leibe, E. Seemann, and B. Schiele, "Pedestrian detection in crowded scenes," IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1 , pp. 878-885, 2005.
[5]C. P. Papageorgiou, M. Oren, and T. Poggio, "A general framework for object detection," Sixth International Conference on Computer Vision, pp. 555-562, 1998.
[6]H. Elzein, S. Lakshmanan, and P. Watta, "A motion and shape-based pedestrian detection algorithm," Proceedings of the IEEE Intelligent Vehicles Symposium, pp. 500-504, 2003.
[7]吳伯毅，整合小波轉換與Förstner特徵運算元的行人檢出，台灣科技大學電機工程系碩士論文，2006。
[8]W. Förstner, “Quality assessment of object location and point transfer using digital image correlation,” International Archives of Photogrammetry and Remote Sensing, vol. 25-Ⅲ, pp. 197-219, 1984.
[9]A. Broggi, M. Bertozzi, A. Fascioli, and M. Sechi, "Shape-based pedestrian detection,", Proceedings of the IEEE in Intelligent Vehicles Symposium, pp. 215-220, 2000.
[10]P. Viola, M. J. Jones, and D. Snow, "Detecting pedestrians using patterns of motion and appearance," Proceedings of the Ninth IEEE International Conference on Computer Vision, vol.2, pp. 734-741, 2003.
[11]P. Viola and M. Jones, "Rapid object detection using a boosted cascade of simple features," Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol.1, pp. I-511-I-518, 2001.
[12]G. Monteiro, P. Peixoto and U. Nunes, "Vision-based pedestrian detection using Haar-like features," Proceedings of the 6th Robotics Portuguese Festival, 2006.
[13]P. Viola and M. Jones, "Robust real-time face detection," Proceedings of the Eighth IEEE International Conference on Computer Vision, pp. 747-747, 2001.
[14]E.H. Adelson, C.H. Anderson, J.R. Bergen, P.J. Burt, J.M. Ogden, “Pyramid methods in image processing,” RCA Engineer, vol.29, no.6, pp. 33-41, 1984.
[15]M. Oren, C. Papageorgiou, P. Sinha, E. Osuna, and T. Poggio, "Pedestrian detection using wavelet templates," Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 193-199, 1997.
[16]N. Otsu, "A threshold selection method from gray-level histograms," IEEE Transactions on Systems, Man and Cybernetics, vol. 9, pp. 62-66, 1979.
[17]劉世超，行人檢出的研究，台灣科技大學電機工程系碩士論文， 2005。