Deterministic object tracking using Gaussian ringlet and directional edge features

• Published in: Optics and laser technology 2017-10, Vol.95, p.133-146
• Main Authors: Krieger, Evan W., Sidike, Paheding, Aspiras, Theus, Asari, Vijayan K.
• Format: Article
• Language: English
• Subjects: Algorithms; Computation; Datasets; Drift; Feature extraction; Filtration; Gaussian ringlet; Imagery; Kirsch mask; Object tracking; Optical tracking; Real time; Test procedures
• ISSN: 0030-3992; 1879-2545
• DOI: 10.1016/j.optlastec.2017.04.011

•Challenges in WAMI tracking include distortions, scale change, and low res. target.•Proposed a novel tracking method: Directional Ringlet Intensity Feature Transform.•Developed Gaussian ringlet approximation to improve processing speed of DRIFT.•Results show DRIFT is robust to object deformation, rotation, and scale change.•Outperforms state of the art feature-based tracking methods. Challenges currently existing for intensity-based histogram feature tracking methods in wide area motion imagery (WAMI) data include object structural information distortions, background variations, and object scale change. These issues are caused by different pavement or ground types and from changing the sensor or altitude. All of these challenges need to be overcome in order to have a robust object tracker, while attaining a computation time appropriate for real-time processing. To achieve this, we present a novel method, Directional Ringlet Intensity Feature Transform (DRIFT), which employs Kirsch kernel filtering for edge features and a ringlet feature mapping for rotational invariance. The method also includes an automatic scale change component to obtain accurate object boundaries and improvements for lowering computation times. We evaluated the DRIFT algorithm on two challenging WAMI datasets, namely Columbus Large Image Format (CLIF) and Large Area Image Recorder (LAIR), to evaluate its robustness and efficiency. Additional evaluations on general tracking video sequences are performed using the Visual Tracker Benchmark and Visual Object Tracking 2014 databases to demonstrate the algorithms ability with additional challenges in long complex sequences including scale change. Experimental results show that the proposed approach yields competitive results compared to state-of-the-art object tracking methods on the testing datasets.