N, multi-layer perceptron, activation functions, loss functions, gradient descent, back-propagation). Multi-view geometry (cont’d)Ĭomputer Vision in the era of deep learning 24. Image formulation, camera calibration (cont’d) 21. Image formulation, camera calibration 20. Motion and tracking (cont’d)ģD vision 19. Object detection (e.g., face and pedestrian) with sliding window approach, object detection using part-based models. Image classification and image search using advanced feature coding (First and second order local feature aggregation, sparse coding) (cont’d) 14. Image classification and image search using advanced feature coding (First and second order local feature aggregĪtion, sparse coding). Nearest neighbor and logistic regression (for image search and image classification) 12. Image classification overview and Bag of Features 11. Segmentation: tree-based segmentation, spectral clustering, other superpixel methods (cont’d) 10. Segmentation: tree-based segmentation, spectral clustering, other superpixel methods. Local features and fitting (Local features, Harris corner detection, Scale invariant feature transform, Image stitching and RANSAC) (cont’d) 7. Local features and fitting (Local features, Harris corner detection, Scale invariant feature transform, Image stitching and RANSAC) 6. Course introduction, Computer vision overview 2. Sions Teaching Method 2 - Laboratory Work Description: On-campus synchronous sessionsĢD vision: 1. (c) Standard on-campus delivery Teaching Method 1 - Lecture Description: Mix of on-campus/on-line synchronous/asynchronous ses (b) Fully online delivery and assessment Teaching Method 1 - Lecture Description: On-line synchronous/asynchronous lectures Teaching Method 2 - Laboratory Work Description: On-line synchronous/asynchronous sessions (a) Hybrid delivery Teaching Method 1 - Lecture Description: Mix of on-campus/on-line synchronous/asynchronous sessions Teaching Method 2 - Laboratory Work Description: Mix of on-campus/on-line synchronous/asynchronous sessions Teaching Method 2 - Laboratory Work Description: Attendance Recorded: Not yet decidedĭue to Covid-19, in 2021/22, one or more of the following delivery methods will be implemented based on the current local conditions. Teaching Method 1 - Lecture Description: Attendance Recorded: Not yet decided Notes: 3 lectures per week for 10 weeks (LO5) Demonstrate and apply the practical skills necessary to build computer vision applications. (LO4) Apply the principles of deep neural networks to various vision problems such as classification, detection, and semantic segmentation. (LO3) Describe the foundation of image formation with the pinhole camera model and how they project the 3D world to 2D images. (LO2) Describe state-of-the-art techniques for image classification, image search, image segmentation, object detection, and object tracking. (LO1) Demonstrate an understanding of the theoretical and practical aspects of image representations. To develop the practical skills necessary to build computer vision applications. To present fundamental problems in both 2D and 3D vision, and to explain a variety of classical and emerging approaches to overcome them. To provide an introduction to the topic of Computer Vision. Programme(s) (including Year of Study) to which this module is available on an optional basis: Programme(s) (including Year of Study) to which this module is available on a required basis: Programme(s) (including Year of Study) to which this module is available on a mandatory basis: Modules for which this module is a pre-requisite: Pre-requisites before taking this module (other modules and/or general educational/academic requirements):ĬOMP122 Object-Oriented Programming COMP116 Analytic Techniques for Computer Science School of Electrical Engineering, Electronics and Computer M Gairing Member of staff with responsibility for the module Queries about the module should be directed to the member of staff with responsibility for the module. The information contained in this module specification was correct at the time of publication but may be subject to change, either during the session because of unforeseen circumstances, or following review of the module at the end of the session.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |