3d-vehicle-tracking
Official PyTorch implementation for joint monocular 3D vehicle detection and tracking from ICCV 2019.
What is 3d-vehicle-tracking?
3D Vehicle Tracking is a PyTorch implementation of a research framework for joint monocular 3D vehicle detection and tracking. It solves the problem of estimating and following vehicles in 3D space from a single camera feed, which is critical for autonomous driving systems where cost and sensor limitations are considerations. The approach integrates 3D pose estimation with temporal tracking to produce stable results.
Researchers and engineers in computer vision and autonomous driving who are working on 3D perception, monocular depth estimation, and multi-object tracking. It's particularly relevant for those exploring joint detection-and-tracking models.
Developers choose this implementation because it provides the official code for a seminal ICCV paper, offering a proven, joint framework that improves 3D estimation stability through temporal tracking. It's a valuable baseline for monocular 3D perception research.
Overview
Official implementation of Joint Monocular 3D Vehicle Detection and Tracking (ICCV 2019)
Use Cases
Best For
- Research on monocular 3D object detection for autonomous vehicles
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
