Deep Learning for Motion Segmentation in 3D Point Cloud Scenes

Bachelor Thesis, Master Thesis

Motion detection and segmentation is an important task for urban scene understanding. It is used by automated vehicles to build dynamic occupancy grids to plan their navigation. While deep learning-based approaches achieve good results in motion detection and segmentation with RGB images, designing neural networks that process 3D point clouds for the same task is quite challenging.

Goal

Design, implement and evaluate a deep learning model for motion segmentation in 3D point cloud.

Requirements

  • A good knowledge in deep learning
  • Hands-on experience in implementing deep learning models is desirable (python+ tensorflow or pytorch)
  • Hands-on experience in 3D point cloud processing is beneficial but not necessary.