• 沒有找到結果。

移動車輛之遮蔽偵測與陰影去除 陳政廷、曾逸鴻

N/A
N/A
Protected

Academic year: 2022

Share "移動車輛之遮蔽偵測與陰影去除 陳政廷、曾逸鴻"

Copied!
2
0
0

加載中.... (立即查看全文)

全文

(1)

移動車輛之遮蔽偵測與陰影去除 陳政廷、曾逸鴻

E-mail: 360556@mail.dyu.edu.tw

摘 要

由於國民生活品質快速成長,使得車輛數目大幅度增加,更突顯交通管理方面的需求。以電腦視覺技術為基礎的智慧型交 通監控系統裡,往往因為光源照射所產生的陰影,以及車子重疊所產生的遮蔽,讓交通數據統計的準確率下降。本研究以 連續影像之分析技術,模擬人類視覺判斷,消除陰影、並分離遮蔽,提升智慧型交通監控系統之準確率。本研究在車輛偵 測時,利用背景相減的方法,擷取前景車輛物體。在消除陰影部分,利用陰影比背景較暗且三原色變暗幅度接近的特性,

對陰影像素做初步的去除。此外,車輛在日照底下移動時,根據日照角度的不同,使得車輛與陰影像素的移動特性有所差 異;因此,本研究根據前景像素的移動特性,再次進行細部陰影像素的判定與去除。在分離遮蔽部分,利用光流法對移動 車輛像素進行特性分析,分別採取移動方向與速度組成特徵向量,並對其利用改良性K-means作分群,根據分群數量判斷 是否發生遮蔽,利用分群相交處做遮蔽分割處,加以分離,最後得到完整的移動車輛。實驗結果在陰影消除和分離遮蔽部 分,正確率分別可達93%和91%,表示本研究所提出的方法是可行的,將使智慧型交通監控系統更加的穩定。

關鍵詞 : 陰影去除、視訊監控系統、遮蔽偵測

目錄

中文摘要......................... ii 英文摘要...................

...... iii 致謝辭.......................... iv 內容目錄...........

.............. v 表目錄.......................... vii 圖目錄....

...................... viii 第一章 緒論........................

1 第一節 研究背景與動機................... 1 第二節 研究目的...............

....... 4 第三節 系統流程...................... 4 第四節 研究範圍與限制....

............... 6 第五節 論文架構...................... 6 第二章 文獻探 討...................... 7 第一節 移動物體偵測....................

7 第二節 光照陰影判定與去除................. 9 第三節 移動物體遮蔽判定與分離........

....... 12 第三章 移動車輛陰影判定與去除............... 14 第一節 移動車輛偵測....

................ 14 第二節 單張畫面陰影判定.................. 20 第三節 連 續畫面之車輛陰影判定與去除............ 23 第四章 移動車輛遮蔽判定與分離............

... 29 第一節 移動車輛物體之光流分析............... 29 第二節 連續畫面之車輛遮蔽分離...

............ 32 第五章 實驗結果與分析................... 36 第一節 實驗結果.

..................... 36 第二節 錯誤分析...................... 41 第六章 結論........................ 43 參考文獻..................

....... 44 參考文獻

一、中文部分 交通部統計處。機動車輛登記數。2012年1月15日,取自:

http://www.motc.gov.tw/mocwebGIP/wSite/public/Attachment/f1326673691586.xlsf 曾逸鴻,林曉菁(2009),多光源環境下之陰影模型建 立與前景物 體陰影去除,全國計算機會議,vol. 8, pp. 520-529。 曾逸鴻,黃吉緯(2009),整合多搜尋方法之影像資料庫 檢索系統,科學 與工程技術期刊,5(3),1-12。 二、英文部分 Bugeau, A., & Perez, P. (2009). Detection and segmentation of moving objects in complex scenes.

Computer Vision and Image Understanding, 113(4), 459-476. 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. Fang, L. Z., Qiong, W. Y., Sheng, Y. Z.

(2008). A method to segment moving vehicle cast shadow based on wavelet transform. Pattern Recognition Letters, 29, 2182-2188 Gao, X., Yang, Y., Tao, D., & Li, X. (2009). Discriminative optical flow tensor for video semantic analysis. Computer Vision and Image Understanding, 113(3), 372-383. Gentile, C., Camps, O., and Sznaier, M. (2004). Segmentation for robust tracking in the presence of severe occlusion. IEEE Trans. Image Process, 13(2), 166-178. Huang, C. L. and Liao, W. C. (2004). A vision-based vehicle identification system. in Proc. ICPR , 4, 364-367. Jacques, J.

S., Jung, C. R., Musse, S. R. (2005). Background Subtraction and Shadow Detection in Grayscale Video Sequences. CROMOS

(2)

Labouratory,PIPCA ,Proceedings of the XVIII Brazilian symposium on Computer Graphics and Image Processing SIBGRAPI'05,IEEE Computer society. Jung, C. R. (2009). Efficient background subtraction and shadow removal for monochromatic video sequences. IEEE Transactions on Multimedia, 11(3), 571-577. Kamijo, S., Matsushita, Y., Ikeuchi, K., and Sakauchi, M. (2000). Traffic monitoring and accident detection at intersections. IEEE Trans. Intell. Transp. Syst., 1(2), 108-118. Kanhere, N. K., Pundlik, S. J., and Birchfield, S. T. (2005). Vehicle segmentation and tracking from a low-angle off-axis camera. Proc. IEEE Conf. CVPR, 5(2), 1152-1157. Kim, E., & Park, S. (2006). Automatic video

segmentation using genetic algorithms. Pattern Recognition Letters, 27(11), 1252-1265. Kinoshita, K., Enokidani, M., Izumida, M., & Murakami, K. (2006). Tracking of a moving object using one-dimensional optical flow with a rotating observer. IEEE International Conference on Control, Automation, Robotics and Vision, 6(9), 1-6. Lai, J. Z. C., Huang, T.-J., & Liaw, Y.-C. (2009). A fast k-means clustering algorithm using cluster center displacement. Pattern Recognition, 42(11), 2551-2556. Levine, M., & Bhattacharyya, J. (2005). Removing shadows. Pattern Recognition Letters, 26(3), 251-265. Lianqiang, N., & Nan, J. (2008). A Moving Objects Detection Algorithm Based on Improved Background Subtraction.

Paper presented at the Intelligent Systems Design and Applications, 2008. ISDA '08. Eighth International Conference on, 3, 604-607. Lu, Y., Xin, H., Kong, J., Li, B. & Wang, Y. (2006). Shadow removal based on shadow direction and shadow attributes. Computational Intelligence for Modelling, Control and Automation, 37-37. Nicolas, H., & Pinel, J. M. (2006). Joint moving cast shadows segmentation and light source detection in video sequences. Signal Processing: Image Communication, 21(1), 22-43. Pyung-Soo, H., Ki-Yeol, E., Jae-Young, J., & Moon-hyun, K. (2009). A Statistical Approach to Robust Background Subtraction for Urban Traffic Video. Paper presented at the Computer Science and Engineering, 2009. WCSE '09. Second International Workshop on, 2, 177-181. Salvador, E., Cavallaro, A., & Ebrahimi, T. (2004). Cast shadow segmentation using invariant color features. Computer Vision and Image Understanding, 95(2), 238-259. Su, M. C. and C. H. Chou (2001). A modified version of the k-means algorithm with a distance based on cluster symmetry. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(6), 674-680. Tseng, Y. H. and H. Z. Xiao (2005). Background model construction and maintenance in a video surveillance system. Proceedings of the 18th Conference on Computer Vision, Graphics and Image Processing, 303-309. Veeraraghavan, H., Masoud. O., and Papanikolopoulos, N. P.

(2003). Computer vision algorithms for intersection monitoring. IEEE Trans. Intell. Transp. Syst., 4(2) ,78-89. Zhang, J., & Gong, S. (2009). People detection in low-resolution video with non-stationary background. Image and Vision Computing, 27(4), 437-443.

參考文獻

相關文件

 Light travels between source and detector as a probability wave.

 Light travels between source and detector as a probability wave..

Effect (a) Detector moving; source stationary...

(1) 99.8% detection rate, 50 minutes to finish analysis of a minute of traffic. (2) 85% detection rate, 20 seconds to finish analysis of a minute

(1) 99.8% detection rate, 50 minutes to finish analysis of a minute of traffic?. (2) 85% detection rate, 20 seconds to finish analysis of a minute

– evolve the algorithm into an end-to-end system for ball detection and tracking of broadcast tennis video g. – analyze the tactics of players and winning-patterns, and hence

In order to promote urban renewal, urban design, and urban landscape movement, Hsinchu city government held “2000 Chu-chieh youth urban designer camp” for two sessions in year

D.Wilcox, “A hidden Markov model framework for video segmentation using audio and image features,” in Proceedings of the 1998 IEEE Internation Conference on Acoustics, Speech,