A Graph Convolutional Neural Network Based Approach for Object Tracking Using Augmented Detections With Optical Flow
This thesis presents a novel method for online Multi-Object Tracking (MOT) using Graph Convolutional Neural Network (GCNN) based feature extraction and end-to-end feature matching for object association. The Graph based approach incorporates both appearance and geometry of objects at past frames as...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Others |
| Published: |
Virginia Tech
2021
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10919/103372 |