Evaluation of deep learning based multiple object trackers

Date

2020-9

Author

Moured, Omar

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

33
views

26
downloads

Cite This

Multiple object tracking (MOT) is a significant problem in the computer vision community due to its applications, including but not limited to, surveillance and emerging autonomous vehicles. The difficulties of this problem lie in several challenges, such as frequent occlusion, interaction, intra-class variations, in-and-out objects, etc. Recently, deep learning MOT methods confront these challenges effectively. State-of-the-art deep learning (DL) trackers pipeline consists of two stages, i.e., appearance handling, which includes object detection and feature extraction, and grouping step, which performs affinity computation and data association. One of the main concerns of this thesis is to investigate how DL was employed in each one of these stages. In addition to that, we have experimented with different performance-enhancing methods, the currently top online tracker on the MOTChallenge dataset. Based on the investigation and experiments, we will identify and discuss the significant shortcomings of the current frameworks, providing possible ways to improve it.

Subject Keywords

Multiple Object Tracking, Deep Learning, Online Tracker

URI

https://hdl.handle.net/11511/69277

Collections

Graduate School of Natural and Applied Sciences, Thesis