Spongebobbbbbbbb/FDTA
The official repository of the paper "From Detection to Association: Learning Discriminative Object Embeddings for Multi-Object Tracking"
This project helps video analysts, sports broadcasters, or security personnel accurately track multiple moving objects across video frames. It takes video footage along with depth information for each frame and outputs precise trajectories of individual objects, even in crowded or complex scenes. This tool is for professionals who need to automatically identify and follow specific entities like dancers, athletes, or vehicles throughout an entire video sequence.
Use this if you need to reliably identify and follow multiple distinct objects in video footage, especially when dealing with similar-looking items or cluttered environments.
Not ideal if you only need to detect objects in single frames, or if your videos lack corresponding depth map information.
Stars
56
Forks
2
Language
Python
License
MIT
Category
Last pushed
Mar 21, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Spongebobbbbbbbb/FDTA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lucidrains/vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with...
roflcoopter/viseron
Self-hosted, local only NVR and AI Computer Vision software. With features such as object...
blakeblackshear/frigate
NVR with realtime local object detection for IP cameras
levan92/deep_sort_realtime
A really more real-time adaptation of deep sort
notAI-tech/NudeNet
Lightweight nudity detection