SGBAU TY Computer Engg syllabus

SGBAU · Third Year B.E. Computer Engineering · NEP 2020

Computer Vision

6KE235PE2 · Elective III · Semester VI · 3 credits · IE 40 + ESE 60

One of the Elective III options.

  1. Unit 1: Introduction to Computer Vision and Image Formation

    7 hours

    Human versus computer vision, applications and the components of a vision system, image formation, the pinhole camera, camera geometry and perspective projection, calibration basics, and image acquisition and digitisation.

    Examined in the 60-mark end-semester paper

    • Introduction to computer vision
    • Camera models and calibration
    • Projective geometry and homography
  2. Unit 2: Image Processing and Feature Extraction

    7 hours

    Filtering and smoothing, edge detection with Sobel, Prewitt and Canny, Harris and Shi–Tomasi corner detection, SIFT, SURF and ORB descriptors, and feature matching.

    Examined in the 60-mark end-semester paper

    • Filtering, thresholding and edge detection
    • Corner detection
    • Feature detectors and descriptors
    • Feature matching and tracking
  3. Unit 3: Object Detection and Recognition

    7 hours

    Detection fundamentals, template matching and sliding windows, histogram-based methods, shape- and appearance-based recognition, Viola–Jones face detection and feature-based classification.

    Examined in the 60-mark end-semester paper

    • Template matching and blob analysis
    • Face detection and recognition with eigenfaces
    • Active contours and shape recognition
  4. Unit 4: Motion Analysis and Video Processing

    7 hours

    Video representation, background subtraction, optical flow, motion estimation and tracking, Kalman and particle filters, tracking applications and activity recognition.

    Examined in the 60-mark end-semester paper

    • Optical flow and layered motion
    • Surveillance, particle filters and tracking
  5. Unit 5: Machine Learning and Deep Learning for Computer Vision

    7 hours

    Machine learning in vision, CNN architectures and popular models, transfer learning, YOLO and SSD object detection, and semantic segmentation.

    Examined in the 60-mark end-semester paper

    • CNN architecture
    • CNN architectures: VGG, GoogLeNet, ResNet and DenseNet
    • Transfer learning and data augmentation
    • Object detection and image segmentation
  6. Unit 6: Applications and Advanced Topics in Computer Vision

    7 hours

    Vision in autonomous vehicles, medical imaging, surveillance, biometrics and industrial inspection, integration with AR and VR, ethics, and research directions.

    Examined in the 60-mark end-semester paper

    • In-vehicle vision: road, sign and pedestrian detection
    • Industrial applications of computer vision
    • Medical image processing

Unit contents are summarised from the official SGBAU syllabus . AiCanCode.org is not affiliated with Sant Gadge Baba Amravati University (SGBAU).