Efficient Object Tracking Based on Local Invariant Features
Yanjun Li, Jinfeng Yang, Renbiao Wu et al. · International Symposium on Communications and Information Technologies · 2006
Object tracking has many applications in computer vision. Traditionally, to track objects successfully, motion prediction often plays an important role in tracking process. However, the cumulative error from motion prediction often leads to object losing, especially in occlusion. In this paper, an efficient method of object tracking without motion prediction is presented. Firstly, an adaptive Gaussian method is used to object detection. Then local features of the detected objects are extracted using the scale invariant feature transform (SIFT). Finally, object tracking are implemented by matching local invariant features which are learned online. The experimental results illustrate that the proposed method is capable of tracking objects under partial or severe occlusions
Cited by 11 works. doi:10.1109/iscit.2006.340024
Authors
References
- Distinctive Image Features from Scale-Invariant Keypoints
- Pfinder: real-time tracking of the human body
- A performance evaluation of local descriptors
- Adaptive background mixture models for real-time tracking
- Scale & Affine Invariant Interest Point Detectors
- W/sup 4/: Who? When? Where? What? A real time system for detecting and tracking people
- An efficient method for contour tracking using active shape models
- Tracking Groups of People
- Effective Gaussian mixture learning for video background subtraction
- Motion-based background subtraction using adaptive kernel density estimation