https://github.com/MedChaabane/DEFT

Joint detection and tracking model named DEFT, or ``Detection Embeddings for Tracking." Our approach relies on an appearance-based object matching network jointly-learned with an underlying object detection network. An LSTM is also added to capture motion constraints.
https://github.com/MedChaabane/DEFT

joint-detection-and-tracking multi-object-tracking tracking-by-detection

Last synced: about 1 month ago
JSON representation

Joint detection and tracking model named DEFT, or ``Detection Embeddings for Tracking." Our approach relies on an appearance-based object matching network jointly-learned with an underlying object detection network. An LSTM is also added to capture motion constraints.

• Host: GitHub
• URL: https://github.com/MedChaabane/DEFT
• Owner: MedChaabane
• License: mit
• Created: 2021-01-30T17:40:01.000Z (about 4 years ago)
• Default Branch: main
• Last Pushed: 2021-06-16T22:44:49.000Z (almost 4 years ago)
• Last Synced: 2024-10-28T07:40:00.565Z (6 months ago)
• Topics: joint-detection-and-tracking, multi-object-tracking, tracking-by-detection
• Language: Python
• Homepage:
• Size: 32.3 MB
• Stars: 269
• Watchers: 12
• Forks: 43
• Open Issues: 20
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-multiple-object-tracking - [code