Abstract
Identification and Tracking of a person in a video are useful in applications such as video surveillance. Two levels of tracking are carried out. They are Classification and monitoring of individuals. The human body's color histogram is used as the basis for monitoring individuals. Our project can detect a human face in a video and store the detected facial features of the Local Binary Pattern Histogram (LBPH). In a video, once a person is detected, it automatically track that individual and assigns a label to that individual. We use the stored LBPH features to track him in any other videos. In this paper, we proposed and compared the efficiency of two algorithms. One constantly updates the background to make it suitable for illumination changes and other uses depth information with RGB. This is the first step in many complex algorithms in computer vision, such as identification of human activity and behavior recognition. The main challenges in human/object detection and tracking are changing illumination and background. Our work is based on image processing and also it learns the activities and stores them using machine learning with the help of OpenCV, an open source computer vision library
References
Human detection and object tracking based on Histograms of Oriented Gradients Zhang S., Wang X. (2013) Proceedings - International Con-ference on Natural Computation, , art. no. 6818189 , pp. 1349-1353.
Navneet Dalal and Bill Triggs. Histogram of oriented gradients for human detection, 2005.
G. Gamage, I. Sudasingha, I. Perera and D. Meedeniya, ”Reinstating Dlib Correlation Human Trackers Under Occlusions in Human Detection based Tracking,” 2018 18th International Conference on Advances in ICT for Emerging Regions (ICTer), Colombo, Sri Lanka, 2018, pp. 92-98.
Ahonen, T., Hadid, A., and Pietikainen, M. Face Recognition with Local Binary Patterns. Computer Vision - ECCV 2004 (2004), 469481.
FZ Eishita, A Rahman, SA Azad, A Rahman, Occlusion handling in ob-ject detection. Multidisciplinary computational intelligence techniques: applications in business, engineering, and medicine. IGI Global. (2013). doi: 10.4018/978-1- 4666-1830-5.ch005
B Wu, R Nevatia, Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors, in IEEE International Conference on Computer Vision (ICCV 2005) (IEEE, Piscataway, 2005), pp. 90–97
N Dalal, B Triggs, Histograms of oriented gradients for human detection, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2005) (IEEE, Piscataway, 2005), pp. 886–893