Dive into a comprehensive deep learning course on computer vision and perception for self-driving cars. Explore essential tasks performed by a self-driving car's perception unit, including road segmentation using Fully Convolutional Networks, 2D object detection with YOLO, object tracking via Deep SORT, and 3D object detection using SFA 3D. Learn about LIDAR data visualization, homogeneous transformations, and multi-task learning with the Multi Task Attention Network. Discover how to transform camera views to bird's eye perspective using UNetXST. Access numerous resources, datasets, and research papers to deepen your understanding of cutting-edge techniques in autonomous vehicle perception.
Overview
Syllabus
) Introduction.
) Fully Convolutional Network | Road Segmentation.
) YOLO | 2D Object Detection.
) Deep SORT | Object Tracking.
) KITTI 3D Data Visualization | Homogenous Transformations.
) Multi Task Attention Network (MTAN) | Multi Task Learning.
) SFA 3D | 3D Object Detection.
) UNetXST | Camera to Bird's Eye View.
Taught by
freeCodeCamp.org
