Intelligent Vision Systems
BSES | 7th Semester, Section A | University of Lahore | Fall 2026
Intelligent Vision Systems
Welcome to the course website for Intelligent Vision Systems (Applied Computer Vision), the 7th-semester vision course for BSES, Section A at the University of Lahore. This site is the main entry point for course information, lecture slides, the weekly schedule, lab handouts, and resources.
The course follows a complete pipeline: from image formation and classical image processing, through features, geometry and motion, to deep learning and the deployment of real-time vision models on the Raspberry Pi 5 — optionally accelerated with the AI HAT / Hailo NPU and fed by a networked ESP32-CAM. Every one of the 16 weekly sessions pairs 1.5 hours of theory with 1.5 hours of supervised laboratory work, building toward a capstone vision system demonstrated live on target hardware.
Course Material
Syllabus
Course description, outcomes, prerequisites, textbooks, grading policy, and academic integrity.
Schedule
Week-by-week and lecture-by-lecture topic list with readings, slide links, and deadlines.
Labs
Fifteen hands-on labs on the Raspberry Pi 5 plus a capstone project, week by week, with tasks and deliverables.
Lectures
Interactive lecture slides and downloadable PDF versions covering classical and modern vision.
Code & Demos
Python, OpenCV, PyTorch, and on-device inference examples used throughout the course.
Assignments
Take-home problem sets bridging theory and implementation, with supporting files.
Tutorials
Self-study guides for the tools and software used in the course.
About the Course
Intelligent Vision Systems covers both classical and modern computer vision, with a running emphasis on embedded and edge deployment on the Raspberry Pi 5:
- Image formation, sensing, and digital image fundamentals
- Point operations, spatial and frequency-domain filtering, restoration, morphology
- Edges, local features, descriptors, matching, and RANSAC
- Camera calibration, two-view geometry, stereo depth
- Optical flow, tracking, and recursive estimation
- Classical recognition, then CNNs for classification, detection, and segmentation
- Reading & reproducing research papers from scratch: U-Net and the Transformer
- Model optimisation for the edge: quantisation, pruning, ONNX / TFLite / Hailo
- The OpenCV 5.0 deep dive: the new DNN engine, ONNX workflows, migration from OpenCV 4
- Practical work in Python, OpenCV 5.0, and PyTorch on the Raspberry Pi 5 (+ AI HAT / Hailo, Pi Camera, ESP32-CAM)
Course at a Glance
| Course | Intelligent Vision Systems (Applied Computer Vision) |
| Programme | BSES, 7th Semester, Section A |
| Credit Hours | 3 h/week (1.5 h theory + 1.5 h laboratory) |
| Semester | 31 August – 14 December 2026 (16 weekly sessions) · Fall 2026 |
| Instructor | Dr. Muhammad Kazim — Assistant Professor, Department of Intelligent Systems |
| Meeting | Mondays, 11:00 AM–2:00 PM |
| Location | E1-404 Lab |
| Platform | Raspberry Pi 5 (+ AI HAT / Hailo, Pi Camera, ESP32-CAM) |
| Programming | Python (OpenCV 5.0, PyTorch/TensorFlow, Ultralytics YOLO); Google Colab for training |
| Contact | muhammad.kazim@is.uol.edu.pk |
Course Website vs. GitHub Repository
This website is the primary place to browse the course: syllabus, schedule, labs, lectures, and other resources.
The GitHub repository holds the downloadable files, starter code, notebooks, and datasets used in the course.