Computer Vision

Credits
6
Types
Compulsory
Requirements
This subject has not requirements , but it has got previous capacities
Department
ESAII
This course is an introduction to computer vision, including the principles of image processing, scene recognition, and object classification.

Teachers

Person in charge

  • Isiah Zaplana Agut (isiah.zaplana@upc.edu)

Weekly hours

Theory
2
Problems
0
Laboratory
2
Guided learning
0
Autonomous learning
6

Competences

Transversal Competences

Transversals

  • CT6 [Avaluable] - Autonomous Learning. Detect deficiencies in one's own knowledge and overcome them through critical reflection and the choice of the best action to extend this knowledge.

    • Basic

  • CB1 - That students have demonstrated to possess and understand knowledge in an area of ??study that starts from the base of general secondary education, and is usually found at a level that, although supported by advanced textbooks, also includes some aspects that imply Knowledge from the vanguard of their field of study.
  • CB2 - That the students know how to apply their knowledge to their work or vocation in a professional way and possess the skills that are usually demonstrated through the elaboration and defense of arguments and problem solving within their area of ??study.
  • CB5 - That the students have developed those learning skills necessary to undertake later studies with a high degree of autonomy

    • Technical Competences

    Especifics

  • CE01 - To be able to solve the mathematical problems that may arise in the field of artificial intelligence. Apply knowledge from: algebra, differential and integral calculus and numerical methods; statistics and optimization.
  • CE02 - To master the basic concepts of discrete mathematics, logic, algorithmic and computational complexity, and its application to the automatic processing of information through computer systems . To be able to apply all these for solving problems.
  • CE03 - To identify and apply the basic algorithmic procedures of computer technologies to design solutions to problems by analyzing the suitability and complexity of the proposed algorithms.
  • CE04 - To design and use efficiently the most appropriate data types and structures to solve a problem.
  • CE13 - To evaluate the computational complexity of a problem, identify algorithmic strategies that can lead to its resolution and recommend, develop and implement the one that guarantees the best performance in accordance with the established requirements.
  • CE14 - To master the foundations, paradigms and techniques of intelligent systems and to analyze, designing and build computer systems, services and applications that use these techniques in any field of application, including robotics.
  • CE15 - To acquire, formalize and represent human knowledge in a computable form for solving problems through a computer system in any field of application, particularly those related to aspects of computing, perception and performance in intelligent environments or environments.
  • CE18 - To acquire and develop computational learning techniques and to design and implement applications and systems that use them, including those dedicated to the automatic extraction of information and knowledge from large volumes of data.
  • CE19 - To use current computer systems, including high-performance systems, for the processing of large volumes of data from the knowledge of its structure, operation and particularities.
  • CE26 - To design and apply techniques for processing and analyzing images and computer vision techniques in the area of artificial intelligence and robotics

    • Generic Technical Competences

    Generic

  • CG2 - To use the fundamental knowledge and solid work methodologies acquired during the studies to adapt to the new technological scenarios of the future.
  • CG4 - Reasoning, analyzing reality and designing algorithms and formulations that model it. To identify problems and construct valid algorithmic or mathematical solutions, eventually new, integrating the necessary multidisciplinary knowledge, evaluating different alternatives with a critical spirit, justifying the decisions taken, interpreting and synthesizing the results in the context of the application domain and establishing methodological generalizations based on specific applications.
  • CG6 - To identify opportunities for innovative applications of artificial intelligence and robotics in constantly evolving technological environments.
  • CG8 - Perform an ethical exercise of the profession in all its facets, applying ethical criteria in the design of systems, algorithms, experiments, use of data, in accordance with the ethical systems recommended by national and international organizations, with special emphasis on security, robustness , privacy, transparency, traceability, prevention of bias (race, gender, religion, territory, etc.) and respect for human rights.
  • CG9 - To face new challenges with a broad vision of the possibilities of a professional career in the field of Artificial Intelligence. Develop the activity applying quality criteria and continuous improvement, and act rigorously in professional development. Adapt to organizational or technological changes. Work in situations of lack of information and / or with time and / or resource restrictions.

    • Objectives

    1. Define and quantify the characteristics of an image
      Related competences: CB1, CE04,
    2. Compare and select the most appropriate image processing tools based on the problem to be solved.
      Related competences: CE26, CB1, CE01, CE02, CE03, CE04, CE15, CE19,
    3. To segment and label image regions
      Related competences: CE26, CG2, CG4, CB5, CE01, CE03, CE04, CE13, CE15,
    4. Find the most significant descriptors to characterize regions or points of interest of an object
      Related competences: CE26, CG2, CG4, CG8, CG9, CT6, CB5, CE14, CE15, CE18,
    5. Detect and recognize the presence of certain items in an image (with and without deep learning)
      Related competences: CE26, CG2, CG4, CG6, CG8, CG9, CT6, CE14, CE15, CE18, CE19,
    6. Correctly carry out experiments to evaluate the proposed methods, their limitations and weak points, based on objective results.
      Related competences: CG2, CG4, CG8, CB2, CE01, CE02, CE03, CE14,

    Contents

    1. Fundamentals of digital imaging
      The digital image, properties and characteristics. Discretization and quantification. Color spaces. Distances.
    2. Linear, non-linear and morphological image processing
      Linear processing. Operations with the intensity of the pixels. Geometric transformations. Image filtering. Digital derivatives. Morphological processing.
    3. Image segmentation
      Binarization. Contour and edge detection. Color clustering. Morphological segmentation.
    4. Descriptors and features
      Topological, geometric and statistical descriptors. The feature space. Histogram-based features, Hough and Harris transform. SIFT, ORB, and Haar key points.
    5. Object recognition
      Recognition through the use of templates. Recognition based on classifiers. Local registration. Global registration.
    6. Deep learning computer vision
      Recognition, detection and identification of objects. Architectures: YOLO, Fast/Faster R-CNN, Mask R-CNN. Visual transformers.

    Activities

    Activity Evaluation act


    Fundamental of the digital image

    The digital image, properties and characteristics. Discretization and quantization. Color spaces Distances
    Objectives: 1
    Contents:
    Theory
    2h
    Problems
    0h
    Laboratory
    2h
    Guided learning
    0h
    Autonomous learning
    4h

    Linear, non-linear and morphological image processing (I)

    Linear processing. Operations with intensity. Geometric transformations. Image filtering. Digital derivatives. Morphological processing.
    Objectives: 2
    Contents:
    Theory
    4h
    Problems
    0h
    Laboratory
    4h
    Guided learning
    0h
    Autonomous learning
    10h

    Linear, non-linear and morphological image processing (II)

    Linear processing. Operations with intensity. Geometric transformations. Image filtering. Digital derivatives. Morphological processing.
    Objectives: 2
    Contents:
    Theory
    4h
    Problems
    0h
    Laboratory
    4h
    Guided learning
    0h
    Autonomous learning
    8h

    Image segmentation

    Binarization. Contour extraction. Clustering by color. Morphological segmentation.
    Objectives: 3
    Contents:
    Theory
    2h
    Problems
    0h
    Laboratory
    4h
    Guided learning
    0h
    Autonomous learning
    4h

    First partial exam


    Objectives: 1 2 3
    Week: 7 (Outside class hours)
    Theory
    0h
    Problems
    0h
    Laboratory
    0h
    Guided learning
    0h
    Autonomous learning
    0h

    Second partial exam


    Objectives: 4 5 6
    Week: 15 (Outside class hours)
    Theory
    0h
    Problems
    0h
    Laboratory
    0h
    Guided learning
    0h
    Autonomous learning
    0h

    Descriptors and features

    Topological, geometric and statistical descriptors. The feature space. Histogram-based features, Hough and Harris transform. SIFT, ORB, and Haar key points.
    Objectives: 4
    Contents:
    Theory
    6h
    Problems
    0h
    Laboratory
    6h
    Guided learning
    0h
    Autonomous learning
    10h

    Object recognition

    Recognition through the use of templates. Recognition using classifiers. Local registration. Global registration.
    Objectives: 5 6
    Contents:
    Theory
    2h
    Problems
    0h
    Laboratory
    4h
    Guided learning
    0h
    Autonomous learning
    10h

    Deep learning computer vision

    Recognition, detection and identification of objects. Architectures: YOLO, Fast/Faster R-CNN, Mask R-CNN. Visual transformers.
    Objectives: 5 6
    Contents:
    Theory
    6h
    Problems
    0h
    Laboratory
    6h
    Guided learning
    0h
    Autonomous learning
    20h

    Teaching methodology

    The theoretical classes will be complemented by putting into practice on PC the techniques presented.
    In the laboratory classes, real computer vision problems will be solved.
    Problems of higher complexity will be raised as homework

    Evaluation methodology

    There will be a first midterm exam (P1), worth 35% of the final grade, and a final exam (EF), worth 65%.

    The final grade will be calculated using the following formula:

    NF = 0.35 · NP1 + 0.65 · NEF

    where NP1 is the grade obtained in the first midterm exam and NEF is the grade obtained in the final exam.

    Exceptionally, the final exam may be replaced by a second midterm exam (P2) and the assessment of the final practical assignments (PF). In this case, the first midterm exam will account for 35%, the second midterm exam for 35%, and the final practical assignments for 30% of the final grade.

    This alternative assessment method will only apply if the student satisfactorily meets the following conditions: attending the practical sessions, except in duly justified cases of force majeure; making responsible use of generative artificial intelligence tools; and maintaining an appropriate attitude, as well as proper use of the laboratories and teaching resources.

    In this case, the final grade will be calculated as follows:

    NF = 0.35 · NP1 + 0.35 · NP2 + 0.30 · NPF

    where NP1 is the grade obtained in the first midterm exam, NP2 the grade obtained in the second midterm exam, and NPF the grade obtained in the submitted final practical assignments.

    The application of this alternative assessment method will be subject to satisfactory compliance with all the above requirements.

    Only students who have taken the exams and have not passed them may sit the reassessment exam. The maximum grade that may be obtained in the reassessment is 7.

    Bibliography

    Basic

    Previous capacities

    Linear algebra, vector calculus, and probability.
    Data structures and programming