dynamic-object-removal

Numpy-only dynamic object removal for LiDAR point clouds — 3D box crop + temporal filtering. No GPU, no deep learning.

LiDAR pose graph optimization with dynamic object removal.

Multimodal perception pipeline using CARLA simulation data for synchronized multicamera RGB, LiDAR, and IMU sensor fusion. Implemented LiDAR-Inertial Odometry and a 15-state ESKF. Generated RGB-colored static-world 3D reconstructions with dynamic object removal, reducing ghost trails.

Offline, containerized M-detector prototype for LiDAR dynamic/static point cloud segmentation.