在本篇論文中，我們提出了一種利用梯度方向直方圖(HOG)的特徵，結合AdaBoost學習式的分類演算法，針對行人的頭部和肩膀進行偵測的方法。梯度方向直方圖(Histogram of oriented Gradient簡稱HOG)是目前廣為研究者用的特徵，能優異地擷取行人的邊緣和輪廓資訊。使用梯度方向直方圖(HOG)是一種密集的特徵擷取方式，透過對互相重疊區域的區塊(block)擷取邊緣資訊，對行人外型的差異、行人姿態動作多變性和影像光線干擾等辨識上的障礙，都有突破性的效果。除此之外，為了改善HOG的效能，解決行人互相遮擋影響偵測正確率的問題，我們選擇使用行人的上半身─頭部和肩膀作為主要偵測行人的依據。AdaBoost是以特徵選取為基礎的一種快速的分類器，它可以從一大群的特徵中，選取出較有辨別性的特徵，每一個特徵也就是一個弱分類器(weak classifier)，將這數個弱分類器依據其各自擁有的權重，最後結合成為一個強分類器(strong classifier)。透過這個強分類器，可以判斷出是行人或者非行人的影像。從實驗的結果，可以發現，弱分類器的個數越多，偵測的準確率會較高，此外，我們分別使用了三個訓練集圖庫：MIT dataset 、INRIA dataset以及Hybrid dataset，以訓練樣本數量最多的Hybrid dataset的準確率較高。

[1] N. Dalal, B. Triggs, “Histograms of oriented gradients for human detection,” IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 886-893, July 2005.
[2] Xiaoyu Wang, Tony X. Han, Shuicheng Yan, ”An HOG-LBP human detector with Partial occlusion handling,” IEEE Conf. Computer Vision, pp.32-39, 2009.
[3] Timo Ahonen, Abdenour Hadid, and Matti Pietikainen, “Face description with local binary patterns: Application to face recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, pp.2037-2041, 2006.
[4] Y. Freund and R. E. Schapire, “A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting,” Journal of Computer and System Sciences, vol. 55, pp. 119-139, 1997.
[5] R. Schaire and Y. Singer, “Improving boosting algorithms using confidence-rated prediction,” Machine Learning, pp. 297-336, 1999.
[6] Y. Freund and R. E. Schapire, “Experiments with a New Boosting Algorithm,” Machine Learning, pp.148-156, 1996.
[7] C. Zeng and H. Ma,“ Robust Head-shoulder Detection by PCA-Based Multilevel HOG-LNP Detector for people Counting,” IEEE Conf. Pattern Recognition, 2010.
[8] Michael J. Jones and Paul Viola,” Face Recognition Using Boosted Local Features,” 2003.
[9] Bo Wu and Ram Nevatia,“ Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination of Edgelet based Part Detectors,” IEEE Conf. Computer Vision, pp. 90-97, 2006.
[10] Payam Sabxmeydani and Greg Mori,” Detecting Pedestrians by Learning Shapelet Features,” IEEE Conf. Computer Vision and Pattern Recognition, pp. 1-8,2007.
[11] Hsiuao-Ying Chen, Chung-Lin Huang and Chih-Ming Fu,” Hybrid-boost learning for multi-pose face detection and facial expression recognition,” IEEE Conf. Multimedia and Expo, pp.671-674, 2007.
[12] Wei Gao, Haizhou Ai and Shihong Lao, “Adaptive Contour Features in Oriented Granular Space for Human Detection and Segmentation,” IEEE Conf. Computer Vision and Pattern Recognition, pp. 1786-1793, 2009.
[13] Bo Wu and Ram Nevatia,” Simultaneous Object Detection and Segmentation by Boosting Local Shape Feature based Classifier,” IEEE Conf. Computer Vision and Pattern Recognition, pp.1-8, 2007.
[14] Bo Wu and Ram Nevatia,” Cluster Boosted Tree Classifier for Multi-View, Multi-Pose Objection Detection,” IEEE Conf. Computer Vision, pp.1-8, 2007.
[15] Bo Wu and Ram Nevatia,” Optimizing Discrimination-Efficiency Tradeoff in Integraling Heterogenous Local Features for Object Detection,” IEEE Conf. Computer Vision and Pattern Recognition, pp.1-8, 2008.
[16] Bo Wu and Ram Nevatia,” Detection of Multiple Partially Occluded Humans in a Single Image by Bayesian Combination of edgelet Part Detectors,” IEEE Conf. Computer Vision, pp.90-97, 2005.
[17] Paul Viola, Michael J. Jones and Daniel Snow,” Detecting Pedestrians Using Patterns of Motion and Appearance,” IEEE Conf. Computer Vision, pp.734-741, 2003.
[18] 台灣大學林智仁教授, LIBSVM, http://www.csie.ntu.edu.tw/~cjlin/libsvm/index.html
[19] MIT Pedestrian Data, http://cbcl.mit.edu/software-datasets/PedestrianData.html
[20] INRIA Person Dataset, http://pascal.inrialpes.fr/data/human/