結論

本系統的重點在於行人偵測，用三種不同的行人偵測法，處理各種行人群可 能會遇到的組合狀態，使用不同的影像特徵擷取正確的行人位置，不管是側向走 行人、正向走行人還是斜向走行人都有考慮到。利用本系統可以解決行人群遮蔽 的問題，只要不是行人影像完全被遮住就有機會成功的偵測出。

因為本實驗場景中會有汽機車經過，必須考慮到汽機車對行人偵測的影響，

最理想的狀態就是汽機車偵測成功，汽機車偵測結果區域就不用做行人偵測的處 理，就能夠成功的減少因為汽機車造成的行人誤偵測。

行人追蹤和汽機車追蹤也是重點，因為需要有計數行人的動作，正確的行人 追蹤結果才能把正確的人數計算出來。汽機車和行人之間也是會有重疊的行為，

配合兩種追蹤結果，可以減少因為汽機車遮蔽行人造成的偵測困難。

在不同時間點都有測試過，白天的情況只要不是超過七個人以上的人群擠在 一起經過 ROI 範圍，都能夠有效的成功偵測。白天的情況只要有足夠的光線照 射在路面上，不管是早上、中午、下午還是傍晚的情況，都能夠進行行人偵測，

而且偵測的效能與單獨使用背景相減法與移動輪廓法比較，本文的偵測效能比較 好，正確性也比較高。

場景不是完全平坦的狀態，ROI 下半部是水平的地面，ROI 上半部是往下傾 斜的地面，行人行走在這種路面一定會出現和平坦路面不同的差異性，行人在不 平坦路面走動，通常會造成影像中行走速度改變，和高處行人遮蔽低處行人程度 高等現象，因為本系統在設定上有一定的容忍度，儘管在不平坦的路面上做行人 偵測，還是能夠成功的做出行人計數。

6.3 未來展望

本系統主要是對白天場景做行人偵測，雖然夜間場景因為有路燈的支持，不

會使畫面完全看不到情況。但是畫面亮度不均勻也使得夜間的偵測效能較差。因 此，夜間的行人偵測需要加強影像的清晰與辨識度，才能把行人偵測率和正確率 提升。

長時間的運用，因為在不同時間的陽光，會造成物體有不同的陰影結果，汽 機車偵測要考慮不同陰影的影響，加上多餘的陰影濾除，可以有效提升汽機車偵 測的正確性。

在白天的場景本系統有九成左右的行人偵測率，剩下的一成的失誤率還要利 用不同的方法加強。汽機車偵測的部分因為本系統只用一個特徵來處理，可以加 強汽機車偵測的部分，還要考慮到汽機車的種類，像是機車、小客車、貨車、大 客車或貨櫃車等等車種。

考慮到行人可能有不同行為，像是跑步、撐雨傘、蹲下、拿東西或者背著背 包等等不同情況，不同的情況會遇到不同的麻煩，對不同行為分別的處理可以使 行人偵測率提高。

一個優良的系統應該能夠適應不同場景，所以改善的地方在測試不同的行人 場景，在不用修改太多系統參數之下，可以針對不同場景做出高偵測率的行人偵 測。因此本論文可測試其他場景，驗證其強健性。

參考文獻

[1] N. Ikeda, A. Saitoh, T. Isokawa, N. Kamiura and N. Metsui, ”A Neural Network Approach for Counting Pedestrians from Video Sequence Images,” SICE Annual Conference, pp. 2485-2488, Aug. 2008.

[2] O. Masoud and N. P. Papanikolopoulos, ”A Novel Method for Tracking and Counting Pedestrians in Real-Time Using a Single Camera,” IEEE Trans. on Vehicular Technology, vol. 50, no. 5, pp. 1267-1278, Sep. 2001.

[3] I. Haritaoglu, D. Harwood and L. S. Davis, ” W4: Real-Time Surveillance of People and Their Activities,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 809-830, Aug. 2000.

[4] C. R. Wren, A. Azarbayejani, T. Darrell and A. P. Pentland, “Pfinder: Real-Time Tracking of the Human Body,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 780-785, July 1997.

[5] R. Cutler and L. S. Davis, ”Robust Real-Time Periodic Motion Detection, Analysis, and Applications,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 781-796, Aug. 2000.

[6] P. Viola, M. J. Jones and D. Snow, “Detecting Pedestrians Using Patterns of Motion and Appearance,” IEEE International Conference on Computer Vision, vol.

2, pp.734-741, Oct. 2003.

[7] L. Zhao and C. Thorpe, “Stereo- and Neural Network-Based Pedestrian Detection,”

IEEE Trans. on Intelligent Transportation Systems, vol. 1, no. 3, pp. 148-154, Sep.

2000.

[8] I. P. Alonso, D. F. Llorca, M. A. Sotelo, L. M. Bergasa, J. Nuevo, M. Ocana and M.

A. G. Garrido, “Combination of Feature Extraction Methods for SVM Pedestrian Detection,” IEEE Trans. on Intelligent transportation Systems, vol. 8, no. 2, pp.

292-307, Jun. 2007.

[9] S. Kang, H. Byun and S. W. Lee, “Real-time Pedestrian Detection Using Support Vector Machines”, Lecture Notes in Computer Science, vol. 2388, pp. 268-277, 2002.

[10] J. Janta, P. Kumsawat, K. Attakitmongcol and A. Srikaew, ”Pedestrian Detection using Color Symmetry Phases,” Proceedings of ECTI-CON, 5th International Conference on Electrical Engineering/Electronics, Computer, vol. 1, pp. 437-440, May 2008.

[11] Z. Li, W. Bo and R. Nevatia, ”Pedestrian Detection in Infrared Image Based on Local Shape Features,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, June 2007.

[12] 彭振軒, “使用樣板比對做進出口行人數量統計,” 國立中央大學資訊工程研 究所碩士論文, 2006.

[13] 羅安鈞, “俯視型行人計數系統,” 國立台灣師範大學資訊工程研究所碩士論 文, 2008.

[14] L. Guo, R. B. Wang, L. S. Jin, L. H. Li and L. Yang, “Algorithm Study for Pedestrian Detection Based on Monocular Vision,” IEEE International Conference on Vehicular Electronics and Safety, pp. 83-87, Dec. 2006.

[15] V. Sharma and J. W. Davis, ” Simultaneous Detection and Segmentation of Pedestrians using Top-down and Bottom-up Processing,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, Jun. 2007.

[16] Y. W. Xu, X. B. Cao and H. Qiao, “A Low-Cost Pedestrian Detection System with a Single Optical Camera,” 6th World Congress on Intelligent Control and Automation, pp. 8759-8763, 2006.

[17] S. L. Phung and A. Bouzerdoum, “Detecting People in Images: an Edge Density Approach,” IEEE International Conference on Acoustics, Speech and Signal Processing, vol. 1, pp. 1229-1232, April 2007.

[18] M. Bertozzi, A. Broggi, R. Chapuis, F. Chausse, A. Fascioli and A. Tibaldi,

“Shape-Based Pedestrian Detection and Localization,” IEEE Trans. on Intelligent Transportation Systems, vol. 1, pp. 328-333, 2003.

[19] M. Chen and S. Kee, “Head Tracking with Shape Modeling and Detection,” 2nd Canadian Conference on Computer and Robot Vision, pp. 483-488, May 2005.

[20] L. Lee, G. Dalley and K. Tieu, “Learning Pedestrian Models for Silhouette Refinement,” 9th IEEE International Conference on Computer Vision, vol. 1, pp.

663-670, Oct. 2003.

[21] C. Curio, J. Edelbrunner, T. Kalinke, C. Tzomakas and W. von Seelen, ”Walking Pedestrian Recognition,” IEEE Trans. on Intelligent Transportation Systems, vol.

1, no. 3, pp.155-163, Sept. 2000.

[22] 白家榮, “十字路口行人的偵測及追蹤,” 國立台灣師範大學資訊教育研究所 碩士論文, 2002.

[23] P. Sabzmeydani and G. Mori, ” Detecting Pedestrians by Learning Shapelet Features,” IEEE Conference on Computer Vision and Pattern Recognition, pp.

1-8, June 2007.

[24] R. Yang, Z. Qinfen, I. Weiss, L. S. Davis, W. Abd-Almageed and Z. Liang,

“Pedestrian Classification from Moving Platforms Using Cyclic Motion Pattern,”

IEEE International Conference on Image Processing, vol. 2, pp. 854-857, Sep.

2005.

[25] V. Philomin, R. Duraiswami and L. Davis, “Pedestrian Tracking from a Moving Vehicle,” Proceedings of the IEEE Intelligent Vehicles Symposium, pp. 350-355, Oct. 2000.

[26] F. Xu, X. Liu and K. Fujimura, “Pedestrian Detection and Tracking with Night Vision,” IEEE Transactions on Intelligent Transportation Systems, vol. 6, no. 1, pp. 63-71, Mar. 2005.