Module Catalogues, Xi'an Jiaotong-Liverpool University   
Module Code: RBE306TC
Module Title: Computer Vision Systems
Module Level: Level 3
Module Credits: 5.00
Academic Year: 2022/23
Semester: SEM2
Originating Department: School of Robotics
Pre-requisites: N/A
To introduce the basic concepts of computer vision, e.g., image, motion, tracking;

To teach the basic methods for applications, e.g., image classification, object detection;

To develop the intuitions and mathematics of the methods in class, and then help to learn about the difference between theory and practice in experiments.
Learning outcomes 
A. Be familiar with both the theoretical and practical aspects of computer vision;

B. Demonstrate knowledge of image formation, measurement, analysis, and motion estimation.

C. Implement common methods for robust image matching and recognition, and object detection.

D. Develop the practical skills necessary to build computer vision applications.
Method of teaching and learning 
This module will be delivered through a combination of formal lectures and supervised laboratory sessions. There are totally five coursework that will be assigned across the semester.
1: Introduction to Computer Vision

(1) What is computer vision

(2) Brief history of computer vision

2: Image formation and filtering

(1) Pixels, sampling, scale, and quality

(2) Light and Color

(3) Image Filtering

(4) Thinking in Frequency

3: Feature detection and matching

(1) Edge detection

(2) Interest points and cornets

(3) Local image features

(4) Feature matching

4: Foundations of machine learning and deep learning

(1) unsupervised learning and supervised learning;

(2) neural networks;

(3) convolutional neural networks;

(4) basic introduction of R-CNN, SSD, YOLO, and FCN

5: Pattern recognition in computer vision

(1) Recognition overview

(2) Bag of features

(3) Large-scale instance recognition and advanced feature encoding

(4) Detection with sliding windows

6: Cameras, multiple views and motion

(1) cameras and optics

(2) camera calibration

(3) stereo introduction

(4) Epipolar Geometry, RANSAC, and Structure from Motion

7: Cameras, multiple views and motion continued

(1) Stereo disparity

(2) Optical flow

(3) Real-time pose estimation

8: Revision- Summary of the module
Delivery Hours  
Lectures Seminars Tutorials Lab/Prcaticals Fieldwork / Placement Other(Private study) Total
Hours/Semester 26      24    100  150 


Sequence Method % of Final Mark
1 Lab Reports 20.00
2 Assignment 20.00
3 Final Exam 60.00

Module Catalogue generated from SITS CUT-OFF: 6/5/2020 5:20:54 PM