3D Computer Vision in Dynamic Traffic Scenes - HRI-US
This project focuses on development of computer vision and machine learning algorithms related to processing and fusion of 2D video and 3D point cloud data, including segmentation, recognition, registration, and tracking. The project scope includes analysis, reconstruction, and interpretation of 3D dynamic scenes through fusion of video and LiDAR point cloud data.
- MS or PhD candidate in computer science, electrical engineering, or related field
- Strong familiarity and research experience in 3D computer vision and machine learning
- Hands-on experience in one or more of the following: LIDAR data processing, simultaneous localization and mapping (SLAM), perception, sensor fusion
- Highly proficient in software engineering using C++ and Python
- Experience with Point Cloud Library (PCL), Robot Operating System (ROS), and GPU programming preferred
- Experience in open-source Deep Learning frameworks such as TensorFlow or Caffe preferred