在動態場景中，往往無法準確地建立前景與背景的模型，而造成物體偵測工作的失敗。本研究欲探討如何在一移動車輛中，也能對週遭車流量進行計數工作。我們利用Gestalt心理學中視覺組織之法則，包含：鄰近法則、相似法則、封閉法則、共同速度、過往經驗及亮度感知等，提出以視覺組織為基礎之聚類與分類特徵，配合基於Hough Transform之同質多物體偵測方法，藉以達成在動態背景下偵測車輛並完成計數工作。本研究提出以視覺組織為基礎之聚類特徵，首先將原始圖像分別利用：基於稀疏光流法求得共同速度特徵、基於反向投影法求RGB三原色之直方特徵，而成為四種特徵影像之組合。我們並說明如何利用輪廓及亮度特徵，進行車輛偵測工作。組合以上六種特徵影像，並在不同尺度下利用滑動視窗於不同位置，不同範圍，對此六影像特徵個別進行車輛出現機率估測。此機率值隨後將可被利用於Barinova等人所提出之基於Hough Transform之同質多物體偵測方法，計算出整體Hough Space的最大後設機率。統計Hough Space中得票數大於給定門檻值之個數，即為該場景中車輛計數之結果。本研究以真實影像來驗證所提出之方法。

Perceptual organization is the process of establishing the meaningful relational visual structures which are grouped together by our proposed methods. In this work, we automatically count the number of moving vehicles in dynamic scene. The image sequences used in our experiments were taken from a camera mounted on a moving vehicle. We make use of the characteristics of the visual organization laws which were developed based on Gestalt psychology, such as: Law of Proximity, Law of Similarity, Law of Closure, Law of Common Fate, Law of Past Experience, and the brightness perception, to generate our target features. The probabilistic framework based on Hough transform is designed to iteratively estimate the maximum a posteriori (MAP) of Hough space. Taking advantage of this process, one can detect the occluded vehicles and then estimates the statistics of vehicles. Experimental results using real images demonstrate the feasibility of the proposed method.

1.D. Chen, “Intelligent transportation system of vehicles extraction and counting of research,” Proc. 2012 International Symposium on Instrumentation & Measurement, Sensor Network and Automation, Aug. 2012, pp. 423-424.
2.C. Stauffer and W. E. L. Grimson, “Adaptive background mixture models for real-time tracking,” Proc. IEEE Conference on Computer Vision and Pattern Recognition, Vol. 2, 1999, pp. 252.
3.L. Unzueta, M. Nieto, A. Cortes, J. Barandiaran, O. Otaegui, and P. Sanchez, “Adaptive Multicue Background Subtraction for Robust Vehicle Counting and Classification,” IEEE Transactions on Intelligent Transportation Systems, 2012, vol. 13, no. 2, pp. 527-540.
4.L.-W. Tsai, J.-W. Hsieh, and K.-C. Fan, “Vehicle Detection Using Normalized Color and Edge Map,” IEEE Transactions on Image Processing, 2007, vol. 16, no. 3, pp. 850-864.
5.A. Broggi, P. Cerri, and P. C. Antonello, “Multi-resolution vehicle detection using artificial vision,” Proc. IEEE Intelligent Vehicles Symposium, June 2004, pp. 310-314.
6.J. Liu, Y. Zhao, Y. Yuan, W. Luo, and K. Liu, “Vehicle capturing and counting using a new edge extraction approach,” Proc. IEEE Conference on Intelligent Transportation Systems, Oct. 2011, pp. 62-66.
7.E. Bas, M. Tekalp, and F. S. Salman, “Automatic Vehicle Counting from Video for Traffic Flow Analysis,” Proc. IEEE Intelligent Vehicles Symposium, June 2007, pp. 392-397.
8.A. B. de Oliveira and J. Scharcanski, “Vehicle Counting and Trajectory Detection Based on Particle Filtering,” Proc. SIBGRAPI Conference on Graphics, Patterns and Images, Aug. 2010, pp. 376-383.
9.S. Sudeep, “An introduction to perceptual organization,” Proc. International Conference on Integration of Knowledge Intensive Multi-Agent Systems, Sept. 2003, pp. 330-335.
10.R. O. Duda and P. E. Hart, “Use of the Hough transformation to detect lines and curves in pictures,” Commun. ACM, vol. 15, no. 1, 1972, pp. 11-15.
11.O. Barinova, V. Lempitsky, and P. Kholi, “On Detection of Multiple Object Instances Using Hough Transforms,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 9, 2012, pp. 1773-1784.
12.B. D. Lucas and T. Kanade, “An Iterative Image Registration Technique with an Application to Stereo Vision,” Proc. DARPA Image Understanding Workshop, April, 1981, pp. 121-130.
13.B. Alexe, T. Deselaers, and V. Ferrari, “What is an object?,” Proc. IEEE Conference on Computer Vision and Pattern Recognition, June 2010, pp. 73-80.
14.B. Alexe, T. Deselaers, and V. Ferrari, “Measuring the Objectness of Image Windows,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 11, 2012, pp. 2189-2202.
15.B. Johansson, J. Wiklund, P.-E. Forssen, and G. Granlund, “Combining shadow detection and simulation for estimation of vehicle size and position,” Pattern Recogn. Lett., vol. 30, no. 8, 2009, pp. 751-759.
16.S. K. Naik and C. A. Murthy, “Hue-preserving color image enhancement without gamut problem,” IEEE Transactions on Image Processing, vol. 12, no. 12, 2003, pp. 1591-1598.
17.N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” Proc. IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, June 2005, pp. 886-893.
18.S. X. Yu, “Angular embedding: From jarring intensity differences to perceived luminance,” Proc. IEEE Conference on Computer Vision and Pattern Recognition, June 2009, pp. 2302-2309.
19.P. Viola and M. Jones, “Robust real-time face detection,” Proc. IEEE International Conference on Computer Vision, 2001, pp. 747-747.
20.H. Grabner, J. Matas, L. Van Gool, and P. Cattin, “Tracking the invisible: Learning where the object might be,” Proc. IEEE Conference on Computer Vision and Pattern Recognition, June 2010, pp. 1285-1292.
21.L. Zappella, X. Llado and J. Salvi, “New Trends in Motion Segmentation,” Pattern Recognition, InTech, 2009.