Module Code - Title:
CE5012
-
INTELLIGENT VISUAL COMPUTING & APPLICATIONS
Year Last Offered:
2025/6
Hours Per Week:
Grading Type:
N
Prerequisite Modules:
Rationale and Purpose of the Module:
This module will focus on the use of state-of-the art Deep Learning techniques in specific Machine/Computer vision applications. This model follows on from previous Machine Vision and Geometric Computer Vision modules where students have previously studied traditional machine/computer vision methods and have also been introduced to the standard deep learning vision applications (classification, object detection and semantic segmentation). This model enables students to obtain broader understanding of practical applications of deep learning techniques in vision, through a series of lectures, student engagement activities and completion of coding tasks.
Syllabus:
Section 1: State of the art computer vision:
Facial Detection & Deep Metric Learning approach to Facial Recognition.
Generative models for vision. (Image cleaning/reconstruction, synthetic data
generation.)
Capsule & Transformer networks.
Section 2: Application of Reinforcement Learning to Vision.
Use of Reinforcement learning in object detection & grasping.
Future directions of Deep Reinforcement Learning in Vision & Sensing.
Section 3: 3D Visual Processing.
Depth Estimation and Visual Odometry with Deep Learning.
Deep learning for 3D classification (Point clouds).
Visual Simultaneous Localisation and Mapping.
Learning Outcomes:
Cognitive (Knowledge, Understanding, Application, Analysis, Evaluation, Synthesis)
On successful completion of this module, students will be able to:
1. Demonstrate an understanding of state of the art techniques in key computer vision tasks, such as Facial detection & recognition.
2. Demonstrate an understanding of the principles of reinforcement learning and it's application to machine vision tasks.
3. Demonstrate an understanding of the use of deep learning in 3D vision processing and applications.
4. Be able to effectively code high level deep learning algorithms for vision applications using Tensorflow.
5. Determine if a Deep learning solution can be appropriately applied to a machine vision problem.
Affective (Attitudes and Values)
On successful completion of this module, students will be able to:
1. Contribute meaningfully to engineering team project development with Deep Learning based Vision Systems.
Psychomotor (Physical Skills)
On successful completion of this module, students will be able to: n/a
How the Module will be Taught and what will be the Learning Experiences of the Students:
The module will be delivered to part-time students in a completely online learning format, with online pre-recorded video lectures and live interactive Q+A tutorials. The students also complete a series of coding exercises in their own time with online moderator support.
Research Findings Incorporated in to the Syllabus (If Relevant):
Prime Texts:
R. Sutton and A. Barto (2018)
Reinforcement Learning: An Introduction (second edition)
, MIT Press
Russell, Stuart J., and Peter Norvig (2016)
Artificial intelligence: a modern approach
, Pearson Education Limited, 2016
Other Relevant Texts:
Programme(s) in which this Module is Offered:
Semester(s) Module is Offered:
Spring
Module Leader:
Tony.Scanlan@ul.ie