Pedestrian Tracking from a Moving Host Using Corner Points
We present a new camera based algorithm to track pedestrians from a moving host using corner points. The algorithm can handle partial shape variations and the set of point movement vectors allows to estimate not only translation but also scaling. The algorithm works as follows: Corner points are extracted within a bounding box, where the pedestrian is detected in the current frame and in a search region in the next frame. We compare the local neighbourhood of points to find point correspondences using an improved method. The point correspondences are used to estimate the object movement using a translation scale model. A fast iterative outlier removal strategy is employed to remove single false point matches. A correction step is presented to correct the position estimate. The step uses the accumulated movement of each point over time to detect outliers that can not be found using inter-frame motion vectors. First tests indicate a good performance of the presented tracking algorithm, which is improved by the presented correction step.
KeywordsCorner Point Interest Point Search Region Correction Step Point Trajectory
Unable to display preview. Download preview PDF.
- [AB01]Motamedi, S., Behrad, A., Shahrokni, A.: A robust vision-based moving target detection and tracking system (2001)Google Scholar
- [Abd01]Abdeljaqued, Y.: Feature Point Extraction and Tracking for Video Summarization and Manipulation. PhD thesis, Universitaet Hannover (November 2001)Google Scholar
- [CSR94]Brandt, S., Smith, C., Papanikolopoulos, N., Richards, C.: Visual tracking strategies for intelligent vehicle-highway systems. In: International Symposium on Photonics for Industrial Applications, Intelligent Vehicle Highway Systems, Boston (1994)Google Scholar
- [Der04]Derpanis, K.: The Harris Corner Detector. Technical report, Department of Computer Science and Engineering, York University, Toronto, Ontario, Canada (October, 27th 2004)Google Scholar
- [HS88]Harris, C., Stephens, M.: A combined corner and edge detector. In: Fourth Alvey Vision Conference, pp. 147-151, Manchester (1988)Google Scholar
- [KSB05]Odobez, J.-M., Smith, K., Gatica-Perez, D., Ba, S.: Evaluating multi-object tracking. In: Workshop on Empirical Evaluation Methods in Computer Vision (EEMCV) (June 2005)Google Scholar
- [LF05]Lepetit, V., Fua, P.: Monocular model-based 3d tracking of rigid objects: A survey. Foundations and Trends in Computer Graphics and Vision 1 (2005)Google Scholar
- [Low04]Lowe, D.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision (2004)Google Scholar
- [MS04]Mikolajczyk, K., Schmid, C.: Scale and affine invariant interest point detectors. International Journal of Computer Vision 60 (2004)Google Scholar
- [PGV05]Piater, J., Gabriel, P., Hayet, J., Verly, J.: Object tracking using color interest points. In: Advanced Video and Signal Based Surveillance, pp. 159-164 (September 2005)Google Scholar
- [Smi95]Smith, S.: Asset 2: Real-time motion segmentation and tracking. Technical report, Oxford Centre For Functional Magnetic Resonance Imaging of the Brain Department of Clinical Neurology, Oxford University, Oxford, UK (1995)Google Scholar
- [ST94]Shi, J., Tomasi, C.: Good features to track. In: 1994 IEEE CVPR, pp. 593–600 (1994)Google Scholar