Final colloquium Mallika Tripatha

Multiple Object Tracking in Underwater Environment

Supervisors: Prof.dr.ir. Bart De Schutter, Athina Ilioudi

Abstract: While various tracking algorithms have demonstrated effectiveness in terrestrial and aerial contexts, their performance in underwater settings remains unexplored. Object tracking in underwater videos presents unique challenges due to variable lighting, water turbidity, and unpredictable camera movement, all of which are likely to hinder the performance of traditional detection and tracking methods. Addressing this gap is crucial for applications such as marine biology research, underwater surveillance, and autonomous underwater vehicles. 

This research first evaluates existing tracking algorithms, Simple, Online, and Realtime Tracking (SORT), ByteTrack, and Bag-of-Tricks SORT (BoT-SORT), each incorporating motion estimation and linear data assignment methods on a novel underwater video dataset with a moving camera. The study then improves on the SORT algorithm by adopting velocity estimation techniques, a formula-based and an optical flow-based, giving rise to two new algorithms, SORT-V and SORT-OF. Furthermore, the thesis proposes a novel tracker that utilises an Interacting Multiple Models (IMM) filter to estimate the location of a target object. The evaluation focuses on finding a balance between specific metrics, such as tracking accuracy, identity switches, and the number of tracked and lost trajectories. The results indicate that using velocity estimation techniques improves the tracking performance by 11%, and tracks more objects by nearly halving the number of lost objects. Incorporating another motion model, a constant acceleration model, gives the best result, with the highest tracking accuracy and the least number of identity switches all in real-time computational speed.