Robot Vision

Recommended Prerequisites

 Linear algebra and analytic geometry, Matrix Calculus, Computer Vision, Stochastic Estimation, Machine Learning

Teaching Methods

This course adopts as teaching methodologies the presentation of theoretical and conceptual concepts in master (theoretical) classes, where a detailed exposition of the concepts, principles and methodologies fundamental to robotic vision and visual inspection is presented, complemented with a strong laboratory component where students are able to validate the concepts learned on the master classes by conducting several Robotic Vision projects, complemented with the elaboration of a review study on a related topic.

Learning Outcomes

The objective of the course is to provide students with knowledge about vision systems with applications in industrial automation and robotics. This universe of applications integrates the fields of visual inspection, robotics, vision process monitoring and vision based control. The main aim is to give students an understanding of main concepts in visual processing by constructing several vision systems oriented to robotics and industrial processes.

It is intended that students acquire competencies in design, development and integration of systems/subsystems of vision based systems, encouraging critical reasoning skills, autonomous learning and team work and ability to apply theoretical concepts to practical problems

Work Placement(s)

No

Syllabus

1.Introduction to Robotic and Industrial Vision;

2. Image formation and acquisition;

3. Ilumination: Techniques, Equipments and solutions;

4. Image&Object Descriptors: HOG,HOF, SURF, SIFT, LBP, FRISK

5. Model-based object recognition: Segmentation and Boundary Extraction, Model Matching, Pose Estimation, Verification;

6. Visual Object Detection: Face Detection and Pedestrian Detection;

7. Visual Object Tracking: Traffic and Pedestrian tracking;

8. Shape Modeling and Recognizing: Point Distribution Models (PDM), PCA Representations, Eigenfaces, Active Shape Models;

9. Object Recognition in 2D and 3D.

Assessment Methods

Assessment
Synthesis work: 10.0%
Exam: 40.0%
Project: 50.0%

Bibliography

Bibliografia Recomendada

-           E.R. Davies (2012), Computer and Machine Vision, Fourth Edition: Theory, Algorithms, Practicalities, Elsevier Inc. 2012.

-           R. Szeliski (2011), Computer Vision-Algorithms and Applications, Springer, 2011.

 

Bibliografia complementar

-           Alexander Hornberg, ed. (2008), Handbook of Machine Vision, Wiley-VCH.