TRI-ML/PF-Track
Implementation of PF-Track
PF-Track helps autonomous vehicle engineers and researchers accurately track multiple moving objects (like cars and pedestrians) across various camera views in complex real-world scenarios. It takes raw camera footage from multiple sources as input and outputs precise 3D object trajectories, even when objects are temporarily hidden or switch between camera views. This is ideal for those developing and testing self-driving systems.
251 stars. No commits in the last 6 months.
Use this if you need highly reliable 3D multi-object tracking for autonomous driving applications, especially where minimizing identity switches for objects across different camera feeds is critical.
Not ideal if your primary goal is simple 2D object detection or if you are not working with multi-camera 3D environments for autonomous systems.
Stars
251
Forks
32
Language
Python
License
—
Category
Last pushed
Jul 28, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/TRI-ML/PF-Track"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cvg/LightGlue
LightGlue: Local Feature Matching at Light Speed (ICCV 2023)
shariqfarooq123/AdaBins
Official implementation of Adabins: Depth Estimation using adaptive bins
amusi/CVPR2026-Papers-with-Code
CVPR 2026 论文和开源项目合集
isl-org/ZoeDepth
Metric depth estimation from a single image
daviddmc/NeSVoR
NeSVoR is a package for GPU-accelerated slice-to-volume reconstruction.