1 publications with the keyword "data association"

Multi-object tracking implemented on airborne wide area motion imagery (WAMI) is still challenging problem in computer vision applications. Extremely camera motion, low frame rate, rapid appearance changes, and occlusion by different objects are the most challenges. Data association, link detected object in the current frame with the existing tracked objects, is the most challenging part for multi-object tracking algorithms. The ambiguity of data association increases in WAMI datasets because objects in the scenes suffer form the lack of rich feature descriptions beside the closeness to each other, and inaccurate object movement displacement. In this paper, detection-based multi-object tracking system that uses a two-step data association scheme to ensure high tracking accuracy and continuity. The first step ensures having reliable short-term tracklets using only spatial information. The second step links tracklets globally and reduces matching hypotheses using discriminative features and tracklets history. Our proposed tracker tested on wide area imagery ABQ dataset [1]. MOTChallage [2] evaluation metrics have been used to evaluate the performance compared to some multi-object-tracking baselines for IWTS42018 [3] and VisDrone2018 [4] challenges. Our tracker shows promising results compared to those trackers.

@inproceedings{Noor2018:AIPR_MOT_WAMI,
  author = "N. Al-Shakarji and F. Bunyak and G. Seetharaman and K. Palaniappan",
  title = "Robust multi-object tracking for wide area motion imagery",
  year = 2018,
  journal = "IEEE Applied Imagery Pattern Recognition Workshop (AIPR)",
  pages = "1-5",
  keywords = "tracking, wide area motion imagery, multi-object tracking, tracking-by-detection, data association",
  doi = "10.1109/AIPR.2018.8707377",
  url = "https://ieeexplore.ieee.org/abstract/document/8707377"
}

N. Al-Shakarji, F. Bunyak, G. Seetharaman, and K. Palaniappan. Robust multi-object tracking for wide area motion imagery. IEEE Applied Imagery Pattern Recognition Workshop (AIPR), pages 1-5, 2018.