ProjectsProject Details

3D Object Detection For Intel RealSense LiDAR

Project ID: 5931-1-21
Year: 2021
Student/s: Anaelle Yasdi, Judit Ben Ami
Supervisor/s: Ori Bryt

This project's main goal is to exam and study the Intel Realsense Lidar Camera, and do to object detection and classification of in-door images taken by L515. The secondary objective of the project is to create a small database with those images and to label them.
The first step in the project was to find a deep learning network and the large 3D in-door dataset it was trained on. The second step was to create a small database with labeled images taken by L515 camera, and the third and final step was to input those images to the chosen network, do adjustments, and to achieve the project's goal: do objects detection and classification.
In practice, VoteNet NN (neural network) was chosen and SUNRGBD database. We created a database of 100 images taken by L515 camera and we were able to get good results in detection and classification. However, surprisingly it turns out that our database was not similar to SUNRGBD from VoteNet perspective and transfer learning did not have an effect.

Poster for 3D Object Detection For Intel RealSense LiDAR