Vehicles are equipped with smarter and smarter driver assistance systems to improve driving safety year by year. One direction of safety improvement is related to the detection and recognition of driving environment, such as lane detection, traffic sign recognition, pedestrian and vehicle detection, etc. On-board pedestrian detection is a very challenging task because driving environment is very dynamic, where humans appear in wide varieties of clothing, illumination, size, speed and distance from the vehicle. Many methods for pedestrian detection have been proposed where the core element is classification. Most of these methods are based on the sliding window search methodology to localize humans in an image. It is very important to select appropriate regions in images where the human might appear. The easiest and also the most popular way is to check the whole image at all possible scales. Such methods usually produces large number of false positives and are consuming computing resources because large number of inappropriate regions were checked. In this thesis we develop a method which can reduce the search space in pedestrian detection by using simple properties of projective geometry, in both cases when camera parameters are available and when camera parameters are unavailable. We showed the efficiency of our method on public dataset with known camera parameters and self captured dataset without registered camera parameters. The self-captured dataset includes four on-board driving video sequences acquired during the day and night with labeled pedestrian locations as ground truth and it will be made available on-line.

Vehicles are equipped with smarter and smarter driver assistance systems to improve driving safety year by year. One direction of safety improvement is related to the detection and recognition of driving environment, such as lane detection, traffic sign recognition, pedestrian and vehicle detection, etc. On-board pedestrian detection is a very challenging task because driving environment is very dynamic, where humans appear in wide varieties of clothing, illumination, size, speed and distance from the vehicle. Many methods for pedestrian detection have been proposed where the core element is classification. Most of these methods are based on the sliding window search methodology to localize humans in an image. It is very important to select appropriate regions in images where the human might appear. The easiest and also the most popular way is to check the whole image at all possible scales. Such methods usually produces large number of false positives and are consuming computing resources because large number of inappropriate regions were checked. In this thesis we develop a method which can reduce the search space in pedestrian detection by using simple properties of projective geometry, in both cases when camera parameters are available and when camera parameters are unavailable. We showed the efficiency of our method on public dataset with known camera parameters and self captured dataset without registered camera parameters. The self-captured dataset includes four on-board driving video sequences acquired during the day and night with labeled pedestrian locations as ground truth and it will be made available on-line.

[1] “World Bank: Road Safety,” http://www.worldbank.org/transport/roads/
safety.htm, [Online; accessed 18-April-2012].
[2] N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” in IEEE Conf. CVPR, 2005, pp. 886–893.
[3] M. Enzweiler and D.M. Gavrila, “Monocular pedestrian detection: Survey and experiments,”
Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol.31, no. 12, pp. 2179 –2195, dec. 2009.
[4] “Daimler 6D vision,” http://www.6d-vision.com/, [Online; accessed 30-April-2012].
[5] “Daimler Gavrila research,” http://www.gavrila.net/, [Online; accessed 30-April-2012].
[6] “Mitsubishi Electric Research Laboratories,” http://www.merl.com/, [Online; accessed 30-April-2012].
[7] “Volkswagen Electronics Research Laboratory,” http://www.vwerl.com/, [Online; accessed 30-April-2012].
[8] Yun Luo, J. Remillard, and D. Hoetzer, “Pedestrian detection in near-infrared night vision system,” in Intelligent Vehicles Symposium (IV), 2010 IEEE, 2010, pp. 51 –58.
[9] O. Tsimhoni, “Pedestrian detection with night vision systems enhanced by automatic
warnings,” Transportation Research Institute (UMTRI), 2005.
[10] Yu-Chun Lin, Yi-Ming Chan, Luo-Chieh Chuang, Li-Chen Fu, Shih-Shinh Huang, Pei-Yung Hsiao, and Min-Fang Luo, “Near-infrared based nighttime pedestrian detection by combining multiple features,” in Intelligent Transportation Systems (ITSC), 2011 14th International IEEE Conference on, oct. 2011, pp. 1549 –1554.
[11] Jianfei Dong, Junfeng Ge, and Yupin Luo, “Nighttime pedestrian detection with near infrared using cascaded classifiers,” in Image Processing, 2007. ICIP 2007. IEEE
International Conference on, 16 2007-oct. 19 2007, vol. 6, pp. VI –185 –VI –188.
[12] A. Broggi, R.L. Fedriga, and A. Tagliati, “Pedestrian detection on a moving vehicle:
an investigation about near infra-red images,” in Intelligent Vehicles Symposium, 2006 IEEE, 0-0 2006, pp. 431 –436.
[13] Thi Thi Zin, P. Tin, and H. Hama, “Bundling multislit-hog features of near infrared images for pedestrian detection,” in Innovative Computing, Information and Control
(ICICIC), 2009 Fourth International Conference on, dec. 2009, pp. 302 –305.
[14] R. O’Malley, M. Glavin, and E. Jones, “A review of automotive infrared pedestrian
detection techniques,” IET Conference Publications, vol. 2008, no. CP539, pp. 168–173, 2008.
[15] Jianfei Dong, Junfeng Ge, and Yupin Luo, “Nighttime pedestrian detection with near
infrared using cascaded classifiers,” in Image Processing, 2007. ICIP 2007. IEEE International Conference on, 16 2007-oct. 19 2007, vol. 6, pp. VI –185 –VI –188.
[16] M. Soga, S. Hiratsuka, H. Fukamachi, and Y. Ninomiya, “Pedestrian detection for a near infrared imaging system,” in Intelligent Transportation Systems, 2008. ITSC
2008. 11th International IEEE Conference on, oct. 2008, pp. 1167 –1172.
[17] Junfeng Ge, Yupin Luo, and Gyomei Tei, “Real-time pedestrian detection and tracking
at nighttime for driver-assistance systems,” Intelligent Transportation Systems, IEEE Transactions on, vol. 10, no. 2, pp. 283 –298, june 2009.
[18] Ronan OMalley, Edward Jones, and Martin Glavin, “Detection of pedestrians in far infrared automotive night vision using region-growing and clothing distortion compensation,” Infrared Physics & Technology, vol. 53, no. 6, pp. 439 – 449, 2010.
[19] S.J. Krotosky and M.M. Trivedi, “A comparison of color and infrared stereo approaches
to pedestrian detection,” in Intelligent Vehicles Symposium, 2007 IEEE, June 2007, pp. 81 –86.
[20] D. Gero andnimo, A.M. Lo andpez, A.D. Sappa, and T. Graf, “Survey of pedestrian detection for advanced driver assistance systems,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 32, no. 7, pp. 1239 –1258, july 2010.
[21] P. Dollar, C. Wojek, B. Schiele, and P. Perona, “Pedestrian detection: An evaluation
of the state of the art,” Pattern Analysis and Machine Intelligence, IEEE Transactions
on, vol. 34, no. 4, pp. 743 –761, april 2012.
[22] Xiaoyu Wang, Tony X. Han, and Shuicheng Yan, “An hog-lbp human detector with partial occlusion handling,” in Computer Vision, 2009 IEEE 12th International Conference on, 29 2009-oct. 2 2009, pp. 32 –39.
[23] Victor Prisacariu and Ian Reid, “fasthog - a real-time gpu implementation of hog,”
Tech. Rep. 2310/09, Department of Engineering Science, Oxford University, 2009.
[24] Chih-Chung Chang and Chih-Jen Lin, “LIBSVM: A library for support vector machines,” ACM Transactions on Intelligent Systems and Technology, vol. 2, pp.
27:1–27:27, 2011, Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm.
[25] Robert Schapire, “Theoretical views of boosting,” in Computational Learning Theory, Paul Fischer and Hans Simon, Eds., vol. 1572 of Lecture Notes in Computer Science, pp. 639–639. Springer Berlin / Heidelberg, 1999, 10.1007/3-540-49097-3-1.
[26] D. Hoiem, A.A. Efros, and M. Hebert, “Putting objects in perspective,” in Computer
Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on, 2006,
vol. 2, pp. 2137 – 2144.
[27] Sung Chun Lee and R. Nevatia, “Robust camera calibration tool for video surveillance
camera in urban environment,” in Computer Vision and Pattern Recognition
Workshops (CVPRW), 2011 IEEE Computer Society Conference on, june 2011, pp.62 –67.
[28] Guanghui Wang, Hung-Tat Tsui, Zhanyi Hu, and Fuchao Wu, “Camera calibration
and 3d reconstruction from a single view based on scene constraints,” Image and Vision Computing, vol. 23, no. 3, pp. 311 – 323, 2005.
[29] B.W. He and Y.F. Li, “A novel method for camera calibration using vanishing points,” in Mechatronics and Machine Vision in Practice, 2007. M2VIP 2007. 14th Interna-
tional Conference on, dec. 2007, pp. 44 –47.
[30] Guanghui Wang, Hung-Tat Tsui, and Q. M. Jonathan Wu, “What can we learn
about the scene structure from three orthogonal vanishing points in images,” Pattern Recogn. Lett., vol. 30, no. 3, pp. 192–202, Feb. 2009.
[31] R. Cipolla, T. Drummond, and D. Robertson, “Camera calibration from vanishing
points in images of architectural scenes,” 1999.
[32] Xuehui Chen, Ruiqing Jia, Hui Ren, and Yinbin Zhang, “A new vanishing point detection algorithm based on hough transform,” in Computational Science and Op-
timization (CSO), 2010 Third International Joint Conference on, may 2010, vol. 2,pp. 440 –443.
[33] Guanghui Wang, Hung-Tat Tsui, Zhanyi Hu, and Fuchao Wu, “Camera calibration and 3d reconstruction from a single view based on scene constraints,” Image and Vision Computing, vol. 23, no. 3, pp. 311 – 323, 2005.
[34] Jingyu Yang Cailing Wang, Chunxia Zhao, “Monocular odometry in country roads based on phase-derived optical flow and 4-dof ego-motion model,” Industrial Robot:
An International Journal, vol. 38, 2011.
[35] Bin Luo, Fuxing Yang, and Lei Yan, “Key technologies and research development of cmos image sensors,” in Geoscience and Remote Sensing (IITA-GRS), 2010 Second
IITA International Conference on, aug. 2010, vol. 1, pp. 322 –325.
[36]“Lighting Technology,”
http://eyesolarlux.com/AO_lighting_tech.htm,
[Online; accessed 30-April-2012].
[37] Jean-Michel Morel Antoni Buades, Bartomeu Coll, “Non-local Means Denoising,” Image Processing On Line, 2011.
[38] “OpenCV Library,” http://opencv.willowgarage.com/wiki/, [Online; accessed 30-April-2012].
[39] “Wikipedia article: Human,” http://en.wikipedia.org/wiki/Human, [Online; accessed 19-March-2012].
[40] P. Viola, M.J. Jones, and D. Snow, “Detecting pedestrians using patterns of motion
and appearance,” in Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on, oct. 2003, pp. 734 –741 vol.2.
[41] P. Viola and M. Jones, “Robust real-time face detection,” ICCV01, vol. 2, pp. 747,2001.