From-scratch C++17 LiDAR + camera perception — sector RANSAC, LiDAR-inertial SLAM, MOT, probabilistic traversability, CBF safety. 13 engineering deep-dives.
-
Updated
May 9, 2026 - C++
From-scratch C++17 LiDAR + camera perception — sector RANSAC, LiDAR-inertial SLAM, MOT, probabilistic traversability, CBF safety. 13 engineering deep-dives.
This repository implements RCNNshift in PyTorch for efficient moving object tracking. RCNNshift enhances the traditional Meanshift tracking algorithm by incorporating an RCNN or 3DRCNN to generate ignition maps, enhancing image channel features for improved tracking.
Add a description, image, and links to the moving-object-tracking topic page so that developers can more easily learn about it.
To associate your repository with the moving-object-tracking topic, visit your repo's landing page and select "manage topics."