汽車數量的高度增長帶來進階駕駛輔助系統（ ADAS ）的需求，為了讓駕駛在旅途中做出正確的判斷與決定，確保駕駛員獲得周圍環境和可能障礙物(特別是車輛)的所有資訊是很重要的。為了實現這一目標，越來越多的研究投入在研發準確的車輛檢測系統。在本篇論文中，我們提出了一個融合雷達和影像的車輛檢測系統，這個系統同時具有雷達的高距離準確率以及影像的直觀於人眼這兩項優勢，可以獲得精準的位置和輪廓資訊。藉著投設雷達的數據結果於視覺圖像上，降低了系統在搜尋障礙物的影像處理中的複雜性和運算時間。我們使用一個影像紋理分類演算法：Sorted Quadrant Median Vector（ SQMV ）來獲取垂直和水平的邊緣圖[1] ，並利用這些邊緣圖開發一個演算法來判斷圖像中是否存在車輛。實驗結果表明，我們的系統在使用MIT CBCL車輛數據庫[2]來做模擬時能夠達到98 %的檢出率以及2.53%的false positive rate.。此外，我們也將SQMV邊緣檢測演算法利用TSMC 90nm技術合成電路。該系統可以達到333 MHz的頻率，換言之，輸入一張128*128的影像並計算出水平垂直邊緣圖只需要50μs。

The growing of vehicle number brings about the needs of driver assistance system. For drivers
to make the right decisions during the journey, it is important to make sure that drivers
obtain all the information of surrounding environment and possible obstacles, especially
vehicles. To achieve this goal, a growing number of papers dedicate in nding accurately
vehicle detection. In this thesis, we propose a fusion vehicle detection system by combining
the advantages of both radar and camera sensors. By applying radar data onto the vision
image, an increasing accuracy of both position and contour is achieved. This system reduces
the complexity and computing time in image processing for obstacle search. Here, a texture
classied algorithm: Sorted Quadrant Median Vector (SQMV) is used to obtain the vertical
and horizontal edge maps [1]. Based on these edge maps, we developed an algorithm to
determine the existence of a vehicle in an image. The experiment results using MIT CBCL
car database [2] demonstrate that this system can reach 98% detection rate with false positive
rate 2.53%. In the last part of the thesis, a hardware model of SQMV edge detection is also
implemented. The system can reach a frequency of 333 MHz, which means it takes only
50s to calculate the edge maps for a 128*128 image.

[1] C.-H. Lin, J.-S. Tsai, and C.-T. Chiu, \Switching bilateral lter with a texture/noise detector for universal noise removal," Image Processing, IEEE Transactions on, vol. 19, no. 9, pp. 2307{2320, 2010.
[2] (2013, Oct.). [Online]. Available: http://cbcl.mit.edu/software-datasets/CarData.html
[3] (2013, Oct.). [Online]. Available: http://on-demand.gputechconf.com/gtc/2013/
presentations/S3413-Advanced-Driver-Assistance-Systems-ADAS.pdf
[4] (2013, Oct.). [Online]. Available: http://www.eetimes.com/document.asp?doc id=
1271493
[5] Z. Yankun, C. Hong, and N. Weyrich, \A single camera based rear obstacle detection
system," in Intelligent Vehicles Symposium (IV), 2011 IEEE. IEEE, 2011, pp. 485{490.
[6] T. Wang, J. Xin, and N. Zheng, \A method integrating human visual attention and
consciousness of radar and vision fusion for autonomous vehicle navigation," in Space
Mission Challenges for Information Technology (SMC-IT), 2011 IEEE Fourth Interna-
tional Conference on. IEEE, 2011, pp. 192{197.
[7] C.-T. Chiu and C.-J.Wu, \Texture classication based low order local binary pattern for
face recognition," in Image Processing (ICIP), 2011 18th IEEE International Conference
on. IEEE, 2011, pp. 3017{3020.
[8] Z. Sun, G. Bebis, and R. Miller, \On-road vehicle detection: A review," Pattern Analysis
and Machine Intelligence, IEEE Transactions on, vol. 28, no. 5, pp. 694{711, 2006.
47
[9] Y. Fang, I. Masaki, and B. Horn, \Distance/motion-based segmentation under heavy
background noise," in Intelligent Vehicle Symposium, 2002. IEEE, vol. 2. IEEE, 2002,
pp. 483{488.
[10] M. Bertozzi and A. Broggi, \Gold: A parallel real-time stereo vision system for generic
obstacle and lane detection," Image Processing, IEEE Transactions on, vol. 7, no. 1,
pp. 62{81, 1998.
[11] Y.-T. Yang, \Study of Ecient Multiple Object Detection and Hardware Implementa-
tion," Master's thesis, National Tsing Hua University, Taiwan, 2013.
[12] Y. Fang, I. Masaki, and B. Horn, \Depth-based target segmentation for intelligent
vehicles: Fusion of radar and binocular stereo," Intelligent Transportation Systems,
IEEE Transactions on, vol. 3, no. 3, pp. 196{202, 2002.
[13] S. Wu, S. Decker, P. Chang, T. Camus, and J. Eledath, \Collision sensing by stereo
vision and radar sensor fusion," Intelligent Transportation Systems, IEEE Transactions
on, vol. 10, no. 4, pp. 606{614, 2009.
[14] M. Haberjahn and R. Reulke, \Object discrimination and tracking in the surroundings
of a vehicle by a combined laser scanner stereo system," in Computer Vision{ACCV
2010 Workshops. Springer, 2011, pp. 225{234.
[15] M. Mahlisch, R. Hering, W. Ritter, and K. Dietmayer, \Heterogeneous fusion of video,
lidar and esp data for automotive acc vehicle tracking," in Multisensor Fusion and
Integration for Intelligent Systems, 2006 IEEE International Conference on. IEEE,
2006, pp. 139{144.
[16] J. Wang, Z. Liu, S. Yi, and K. Li, \Target vehicle selection based on multi features
fusion method," in Intelligent Vehicles Symposium (IV), 2010 IEEE. IEEE, 2010, pp.
13{19.
[17] M. Aly, \Real time detection of lane markers in urban streets," in Intelligent Vehicles Symposium, 2008 IEEE. IEEE, 2008, pp. 7{12.

[18] (2013, Sep.). [Online]. Available: http://www.csgnetwork.com/stopdistcalc.html
[19] C. Papageorgiou and T. Poggio, \A trainable object detection system: Car detection in
static images," Tech. Rep. 1673, October 1999, (CBCL Memo 180).
[20] M. Oren, C. Papageorgiou, P. Sinha, E. Osuna, and T. Poggio, \Pedestrian detection
using wavelet templates," 1997, pp. 193{99.
[21] C. Papageorgiou, M. Oren, and T. Poggio, \A general framework for object detection,"
in Proceedings of 6th International Conference on Computer Vision, 1998.
[22] C. Papageorgiou, \A trainable system for object detection in images and video se-quences," Technical Report 1685, 2000.
[23] C. Papageorgiou and T. Poggio, \A trainable system for object detection," 2000, in press.
[24] (2013, Sep.). [Online]. Available: http://cogcomp.cs.illinois.edu/Data/Car/4