摘要
物件追蹤在近年來是一個相當熱門話題，特別在電腦視頻領域上，以物件追蹤為基礎用在自動監控系統上更是活躍，其中HOG演算法是目前公認最有效的演算法。
實際應用上HOG佔據太多運算，又以Gamma correction最為耗時。本研究本論文設計MHOG(Modified Histogram of Oriented Gradient)，提出用Sobel Edge演算法的概念來延伸來進行取代，修改HOG耗費資源部分，提出一個試用及時系統演算法，稱之為基於改良式HOG之物件追蹤演算法MHOG(Modified Histogram of Oriented Gradient)和HOG相比的優點包括:

1.更能減少運算資源。
2.提升追蹤穩定度
在實驗結果上，展示出原始HOG與本研究所改良之差異性。依序是六個測試影像水鳥、汽車(靜止)、計算機、汽車(移動中)、黑猩猩
 

Abstract
Object tracking has recently been a widely researched topic, specifically in studies investigating computer-automated surveillance systems in the field of computer vision. Among currently available algorithms , the histogram of oriented gradients (HOG) has been recognized as the most effective design.
However, in practice, applying the HOG requires excessive computational resources, particularly for the gamma correction method, which is the most time-consuming method. Therefore, by expanding the concept of Sobel edge detection, the present study proposed a feasible real-time computing system named the modified histogram of oriented gradients (MHOG) to minimize the resource requirements of the conventional HOG. Comparing the MHOG and HOG revealed that the proposed algorithm has lower computational resource requirements and enhances the stability of tracking.
In this thesis, the differences between the conventional HOG and MHOD are demonstrated in six experimental images, namely images of a water bird, a stationary automobile, a calculator, a moving automobile, and a chimpanzee.

參考文獻
[1]A.M.Elgammal,D.Harwood,and L.S.Davis,”non-parametic model for background subtraction,”in proc. Of the 6th Europan conference on computer Vision,pp.751-767,2000.
[2]B. Horn and B. schunck, “Determining optical flow,”Artificial Intelligence,vol.17,pp.185-203,1981.
[3]D.Comaniciu,and P.Meer, “Mean Shift:A Robust Approach toward Fearure Space Analysis,”IEEE trans.On Pattern Analysis and Machine Intelligence,vol.24,no.5,pp.603-619,May 2002.
[4]K.Nummiaro,E.koller-Meier,and LV Gool,”An Adaptive Color-Based Particle Filter,”Image and Vision Computing,vol.21,pp.990110,2003[
[5] M.Breitenstein, F.Reichlin, B.Leibe, E.Koller-Meier, L.V.Gool,”Robust tracking-by-detection using a detector confidence particle filter,”In Proc.OfICCV,2009.
[6]B.Babenko,M.-H. Yang,S.Belongie,”Visual Tisual Tracking with Online Multiple Instance Learning”,In Proc.Of CVPR,2009
[7]H.Grabner and H.Bischof.”On-line boosting and vision.”In Proc.CVPR,volume 1,pp.260-267,2006.
[8]T.G.Dietterich,R.H.Lathrop,and L.T.perez.Solving the multiple instance problem with axis parallel rectangles.artificial Intelligence,pp.31-71,1997.
[9] G.Yang, and T.S.Huang,”Human facedetection in complex background,”Pattern Recognition,27(1),53-63,1994.
[10] Hsu,R.L.,A.M.Mohamed and A.K.Jain,”Face detection in color omage,”IEEE Transactions on Pattern Analysis and Machine Intelligence,24(5),pp.696-704,2002.
[11] Jain ,K.,Y.Zhong and M.P.Jolly,”Deformable template models:A review,”Signal Processing.71(2),pp.109-129,1998.
[12] K.K.Sung, and T.Poggio,”Example-based Learning for view-based human face detection,”IEEE Transactions on Pattern Analysis and Machine Intelligence,20(1),pp.39-51,1998.
[13]R.Gonzalez and R.woods,”Digital Image Proccessing,”Addison Wesley,1992,pp.414-428.
[14]R.Boyle and R.Thomas,”Computer Vision: A First Course,”Blockwell Scientific Publications,1988,pp.48-50.
[15]Viola and Jones,”Rapid object detection using a boosted cascade of simplefeatures”,Computer Vision and Pattern Recognition,2001
[16] R.Lienhart, and J.Maydt, ,”An extended set of Haar-like features for rapid object detection”,In Proc.OFICIP,pp.I:900-903,2002
[17] C.H.Messom, and A.L.C.Barczak,”Fast and Efficient Rotated Haar-like Features Using Rotated Integral Images”,In Proc.Of Australian Conference on Robotics and Automation,pp.1-6,2006
[18]S.Brahnam,L.C.Jain,L.Nanni,and A.Lumini,Eds.,Local Binary Patterns:New Variants and Applications.London,U.K.:Springer,2014.
[19]T.Ojala,M.Pietikainen,and T.Maenpaa,”Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,”IEEE Trans.Pattern Anal.Mach.Intell.,vol.24,no.7,pp.971-987,jul.2002.
[20] L Liu, S Lao, Fieguth P, S S Guo, X Wang and M Pietikainen,”Median robust extended local binary pattern for texture classification,”IEEE Transactions on Image Processing,25(3):pp.1368-1381,2016.
[21] G.David, Lowe,”Object recongnition from local scale-invariant features”.Proceedings of the international Conference on Computer Vision.pp,1150-1157,1999.

[22]Lowe, G.David,”Distinctive Image Feature from Scale-Invariant Keypoints”.International Journal of Computer Vision.60(2):pp.91-110,2004.
[23]Herbert Bay,Andress Ess,Tinne Tuytelaars,Luc Vn Gool,”SURF:Speeded Up
Robust Features”,Computer Vision and Image Understanding,Vol.110,No.3.pp.346-359,2008.
[24] H Bay, A Ess and T Tuytelaars,”Speeded-up robust features(SURF),”Computer vision and image understanding,”110(3):pp.346-359,2008
[25] P M Panchal, S R Panchal and S K. Shah,”A comparison of SIFT and SURF,”International Journal of Innovative Research in Computer and Communiction Engineering,1(2320):pp.97-98,2013.
[26]X.Wang,X.Han,and S.Yan.”A HOG-LBP human detector with partial occlusion handling,”In Proc.of ICCV,2009.
[27] N Dalal and B TRiggs.,”Histograms of oriented gradients for human detection,”In proc.IEEE Computer Society Conference on Computer Vision and Pattern Recognition,1:pp.886-893,2005.
[28] Q Zhu, M C Yeh and K T Cheng,”Fast human detection using a cascade of histograms of oriented gradients,”In Proc.IEEE Computer Society Conference on Computer Vision and Pattern Recognition,pp.1491-1498,2006.
[29]Y.pang,Y.Yuan and X,Li,”Efficient HOG human detrction,”Signal Prcessing,91:pp.773-781,2011.