About Course
This Computer Vision course provides an introduction to computer vision including fundamentals of image formation, camera imaging geometry, feature detection and matching, multi-view geometry including stereo, motion estimation, and tracking, and classification.
We’ll develop basic methods for applications that include finding known models in images, depth recovery from the stereo, camera calibration, image stabilization, automated alignment (e.g. panoramas), tracking, and action recognition. We focus less on the machine learning aspect of CV as that is really a classification theory best learned in an ML course.
Course Content
Computer Vision
-
Introduction to Convolutional Neural Networks for Visual Recognition
00:00 -
Efficient Methods and Hardware for Deep Learning
00:00 -
Deep Reinforcement Learning
00:00 -
Generative Models
00:00 -
Visualizing and Understanding
00:00 -
Detection and Segmentation
00:00 -
CNN Architectures
00:00 -
Recurrent Neural Networks
00:00 -
Deep Learning Software
00:00 -
Training Neural Networks
00:00 -
Training Neural Networks
00:00 -
Convolutional Neural Networks
00:00 -
Introduction to Neural Networks
00:00 -
Loss Functions and Optimization
00:00 -
Image Classification
00:00 -
Adversarial Examples and Adversarial Training
00:00
Student Ratings & Reviews
No Review Yet