3D Object Detection and Segmentation from Point Clouds

Abstract

With the success of convolutional neural networks in computer vision tasks such as object detection and semantic segmentation on 2D data and images, there has been ongoing research on how to apply such deep learning models on 3D data. For applications such as robotics and autonomous driving, one can use depth sensing cameras to provide 3D data. However, these data are sparse and computationally hard to process. In this project, we want to process 3d data, namely, point clouds, segment them semantically and predict the bounding boxes around them.

Requirements

General understanding of 3D computer vision is needed. Understanding of deep learning concepts in computer vision Hands-on experience of Python and deep learning frameworks

Literature

Qi, Charles R., et al. "Pointnet: Deep learning on point sets for 3d classification and segmentation." CVPR. 2017.

Su, Hang, et al. "Splatnet: Sparse lattice networks for point cloud processing." CVPR. 2018.

Shi, Shaoshuai, Xiaogang Wang, and Hongsheng Li. "Pointrcnn: 3d object proposal generation and detection from point cloud." CVPR. 2019.

Zhou, Yin, and Oncel Tuzel. "Voxelnet: End-to-end learning for point cloud based 3d object detection." CVPR. 2018.

Application

If you are interested, please contact us via e-mail:

Mahdi Saleh

Federico Tombari