Qualitative Analysis of Single Object and Multi Object Tracking Models

Tracking the object(s) of interest in the real world is one of the most salient research areas that has gained widespread attention due to its applications. Although different approaches based on traditional machine learning and modern deep learning have been proposed to tackle the single and multi-object tracking problems, these tasks are still challenging to perform. In our work, we conduct a comparative analysis of eleven object trackers to determine the most robust single object tracker (SOT) and multi-object tracker (MOT). The main contributions of our work are (1) employing nine pre-trained tracking algorithms to carry out the analysis for SOT that include: SiamMask, GOTURN, BOOSTING, MIL, KCF, TLD, MedianFlow, MOSSE, CSRT; (2) investigating MOT by integrating object detection models with object trackers using YOLOv4 combined with DeepSort, and CenterNet coupled with SORT; (3) creating our own testing videos dataset to perform experiments; (4) performing the qualitative analysis based on the visual representation of results by considering nine significant factors that are appearance and illumination variations, speed, accuracy, scale, partial and full-occlusion, report failure, and fast motion. Experimental results demonstrate that SiamMask tracker overcomes most of the environmental challenges for SOT while YOLOv+DeepSort tracker obtains good performance for MOT. However, these trackers are not robust enough to handle full occlusion in real-world scenarios and there is always a trade-off between tracking accuracy and speed.