After completing the course, the student:
- understands the motivation and goal of computer vision, including the applications and the general challenges.
- knows the mechanisms of image formation in terms of both geometry and radiometry.
- understands and is able to construct 3D voxel data from images or videos based on silhouettes.
- understands the concepts of image features and their importance in computer vision.
- understands the concepts and challenges of object recognition in computer vision.
- understands how training and evaluating an object detector works.
- is able to calibrate a camera and estimate the location and orientation of a checkerboard from a calibrated camera.
- is able to implement an algorithm to construct 3D voxel models from multi-view images.
- is able to implement an algorithm to cluster voxels based on their position and based on color information.
- is able to implement a fully operational pipeline to (1) train an object detector and (2) apply it to unseen images.
|
|
|
As "seeing" the world with your eyes is important and beneficial, so is computer vision. The goal of computer vision is to make computers work like human visual perception, namely, to recognize and understand the world through visual information including images or videos. In this course, we focus on (1) the reconstruction of 3D models from multiple image streams and (2) building an object detection pipeline. You will be introduced to a number of essential computer vision concepts and techniques, and will apply your knowledge in practice using the assignments.
|
|