Multi-Sensor Perception of Intelligent Vehicles
pedestrian and obstacle detection using multi-sensor information
In this project, I implemented algorithms for the perception of intelligent vehicles using multi-sensors such as LiDAR, Radar, and camera. For performance, I did point cloud processing and clustering. The processed point cloud was used as a prior for efficient region proposal for the visual detector. For frame transformation, the iterative closest point (ICP) was used for the ego-motion compensation of the vehicle. Besides, I implemented a ROS package for intelligent vehicles.
The project was along with the course RO47005 Machine Perception (instructor: Prof. Dariu Gavrila) at the Delft University of Technology. The final grade for this project was 9.5/10 (top 2 in the class).