Human detection and tracking is one of the tasks in computer vision which needs a lot of understanding and appreciable effort. It has a lot of use in visual surveillance, human machine interaction, robotics and many more. A lot of algorithms have been proposed by various researchers but the problem of detection and tracking has not yet been solved efficiently. There are a lot of problems for which there exists no generic solution using a single algorithm. Hence a combination of contrastive algorithms yields a comparatively good result. This paper mainly focuses on developing an algorithm using various image processing techniques without increasing the complexity and achieving comparatively better accuracy. In this paper a new method has been proposed using combination of algorithms. The algorithms used here are Histogram of Oriented Gradients (HOG), Covariance based method and Kalman Filter. The combined algorithms yield a reasonably good result.

1. Na Shoul, Hong Peng, Hui Wang, Li-Min Meng and K. -L. Du, "An ROls Based Pedestrian Detection System for Single Images", IEEE 5th International Congress on Image and Signal Processing, 2012.
2. N. Dalal and B. Triggs, "Histograms of Oriented Gradients for Human Detection", IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 886 - 893, 2005.
3. M. Ishikawa et aI, "Selection of Histograms of Oriented Gradients Features for Pedestrian Detection", ICONIP 2007, Part II, LNCS 4985, pp. 598-607,springer-Verlag Berlin Heidelberg, 2008.
4. P. Dollar, C. Wojek, B. Schiele, P. Perona, "Pedestrian detection: an evaluation of the state of the art," IEEE Trans. Pattern Anal. Machine Intell. , vol. 34, pp. 743-761, April ,2012.
5. Daimeng Wei, Yong Zhao, Ruzhong Cheng and Guoliang Li, "An Enhanced Histogram of Oriented Gradient for Pedestrian Detection", Fourth International Conference on Intelligent Control and Information Processing (ICICIP), Beijing, China, June 2013.
6. O. Tuzel, F. Porikli, and P. Meer, "Region covariance: A fast descriptor for detection and classification", In Proc. 9th European Conf. on Computer Vision, Graz, Austria, volume 2, pages 589-600, 2006.
7. Yaping Liu, Jian Yao, Renping Xie, and Sa Zhu, "Pedestrian Detection from Still Images Based on Multi-Feature Covariances", Proceeding of the IEEE International Conference on Information and Automation, Yinchuan, China, August ,2013.
8. Prajna Parimita Dash, Santhosh Aitha and Dipti Patra," Ohta Based Covariance Technique for Tracking Object in Video Scene", IEEE Students' Conference on Electrical, Electronics and Computer Science (SCEECS), Bhopal, India, Pages 1-4, March,2012.
9. Cargill P. C, Rius C. U, Domingo Mery and Alvaro Soto, "Performance Evaluation of the Covariance Descriptor for Target Detection", International Conference of the Chilean Computer Science Soceity (SCCC), Santiago, Chile, , pages 133 – 141, Nov 10-12, 2009.
10. Xin Li, Kejun Wang, Wei Wang, Yang Li, "A Multiple Object Tracking Method Using Kalman Filter", Proceedings of 2010 IEEE International Conference on Information and Automation, Harbin, China, June 20-23, 2010.
11. Jong-Min Jeong, Tae-Sung Yoon, and Jin-Bae Park, "Kalman Filter Based Multiple Objects Detection-Tracking Algorithm Robust to Occlusion", SICE Annual Conference, Hokkaido University, Sapporo, Japan, September 9-12, 2014.
12. Changyan Li and Lijun Guo, Yichen Hu, "A New Method Combining HOG and Kalman Filter for Video-based Human Detection and Tracking", 3rd IEEE conference on International Congress on Image and Signal Processing-2010
13. . Dayanand Kumar N. C, K. V Suresh, "HOG-PCA Descriptor with Optical Flow based Human Detection and Tracking", International Conf. on Communication and Signal Processing, April 3-5, 2014.
14. Bhuvanarjun. K. M, T. C. Mahalingesh, "Pedestrian Detection in a video sequence using HOG and Covariance method", International Conference on Recent Innovations in Science, Engineering and Management,(IJEEE), New Delhi, vol. 7, issue 1,2015.

Object Detection Object Tracking Video Processing Visual Surveillance.