Object Tracking using HOG and SVM

Object Tracking using HOG and SVM

  IJETT-book-cover  International Journal of Engineering Trends and Technology (IJETT)          
  
© 2017 by IJETT Journal
Volume-48 Number-6
Year of Publication : 2017
Authors : Siji Joseph, Arun Pradeep
DOI :  10.14445/22315381/IJETT-V48P257

Citation 

Siji Joseph, Arun Pradeep "Object Tracking using HOG and SVM", International Journal of Engineering Trends and Technology (IJETT), V48(6),321-325 June 2017. ISSN:2231-5381. www.ijettjournal.org. published by seventh sense research group

Abstract
Object detection and tracking is a vital task among computer vision researchers. The main objective of object detection and tracking is to establish correspondence of objects and object parts between consecutive frames of video. It became difficult since the object faces some problems usually shape deformation, occlusion, scale change, drift etc. There are various algorithm used for tracking. In this project, tracking is performed by using HOG and SVM classifier. The Histogram of Oriented Gradients (HOG) is a feature/image descriptor used in image Processing and other visual areas for the purpose of object detection. The HOG is capable (Histogram of Oriented Gradients) to distinguish the target and the background with HOG visualization and the technique counts occurrences of gradient orientation in localized portions of an image. Support Vector Machine (SVM) is the classifier used for classification. SVM with a single kernel is used in this project. The radial basis function kernel (RBF kernel) SVM are used for training and tracking. The HOG and SVM combination makes our system more efficient. And also we use RGB histogram and SIFT to describe the image.

 References

[1] Fan Yang, Huchuan Lu, and Ming-Hsuan Yang, Robust Superpixel Tracking, IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 23, NO. 4, page 1639- 1651, 2014.
[2] Navneet Dalal and Bill Triggs,Leslie Lamport, Histograms of Oriented Gradients for Human Detection, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR, vol.1, pp. 886-893, 2005.
[3] Miss. A. Sanofer Nisha and Mrs. K. Thulasimani, Part-Based Pedestrian Detection And Tracking Using HOG-SVM Classification, International Journal of Computer Science and Mobile Applications, Vol.2 Issue. 1, pg. 142-155, 2014.
[4] Robert T. Collins and Yanxi Liu, On-Line Selection of Discriminative Tracking Features,in Proc. IEEE Int. Conf. Comput.Vis, pp. 346352 2nd edition,2003.
[5] Kwon and K. M. Lee, Visual Tracking Decompositionm, in Proc. IEEE Conf. Comput. Vis. Pattern Recognition,pp. 12691276 , 2010.
[6] Avidan S, Support Vector Tracking,In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 184191, 2001.
[7] Reecha P. Yadav, Vinu chackravarthy and Sunita P. Ugale, Implementation of Robust HOG-SVM based Pedestrian Classification,International Journal of Computer Applications (0975 8887) ,Volume 114 No. 19,pp 10-16, 2015.
[8] Er. Navjot Kaur and Er. Yadwinder Kaur , Object classification Techniques using Machine Learning Mode, International Journal of Computer Trends and Technology (IJCTT) Volume 18 Number 4, 2014.
[9] Deepthi V.K.P and Mr. Mohammed Anvar P.K Visual Tracking Using HOG and SVM, International Journal of Advanced Engineering Research and Technology (IJAERT),Volume 4 Issue 5,2016.
[10] Durgesh K. Srivastava and Lekha Bhambhu, Data Classification Using Support Vector Machin, Journal of Theoretical and Applied Information Technology,pp 1-7.

Keywords
Object tracking, HOG, SVM, RBF kernel, SIFT, RGB histogram.