End-to-end two-frame online multiple object tracking with convolutional neural networks | |
| Author | Chaipat Suwannaphum |
| Subject(s) | networks (Computer science) Detectors Computer vision Automatic tracking |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Computer Science |
| Publisher | Asian Institute of Technology |
| Abstract | In this thesis, I propose a framework based on a convolutional neural network to perform multiple object tracking. In particular, I extend the architecture of the convolutional neural network used in YOLOv3, an object detection algorithm, to perform short (two frame) tracking. The proposed network takes two image frames as input, detects objects in one frame, and outputs the locations of the objects in the other frame. Short tracks are combined in a post processing step to generate long tracks. The network tracks mul tiple objects simultaneously using only a single forward pass of two image frames. This makes the tracking framework more efficient compared to methods based on neural net works that follow a traditional tracking-by-detection strategy, which requires repeated comparison of two sets of detections to score similarities when performing data association. Experimental results on real world data, a quantitaive evaluation, and comparison with other methods are also included. |
| Year | 2020 |
| Type | Thesis |
| School | School of Engineering and Technology (SET) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Computer Science (CS) |
| Chairperson(s) | Dailey, Matthew N.; |
| Examination Committee(s) | Mongkol Ekpanyapong;Chutiporn Anutariya; |
| Scholarship Donor(s) | His Majesty the King’s Scholarships (Thailand); |
| Degree | Thesis (M. Eng.) - Asian Institute of Technology, 2020 |