📊 Data Science Week 1 of 14 BSc · Y3 S2 ⏱ ~50 min

Week 1: Image Processing, CNNs & Object Detection

Learn how machines see: convolutional neural networks, image classification, object detection, segmentation, and real-time vision with OpenCV.

University of America

DS303 — Lecture 1 · BSc Y3 S2

🎬 CC Licensed Lecture

0:00 / —:—— 📺 MIT OpenCourseWare (CC BY-NC-SA)

🎯 Learning Objectives

Implement convolution and pooling operations from scratch
Train a ResNet-style network on an image dataset
Implement YOLO-style object detection
Apply image segmentation techniques

Topics Covered This Lecture

Convolution & Feature Maps

Classic Architectures: VGG, ResNet, EfficientNet

Object Detection: YOLO, Faster R-CNN

Semantic Segmentation: U-Net

📖 Lecture Overview

This first lecture establishes the foundational framework for Computer Vision. By the end of this session, you will have the conceptual grounding and practical starting point needed for the rest of the course.

        Why this matters
        Learn how machines see: convolutional neural networks, image classification, object detection, segmentation, and real-time vision with OpenCV. This lecture sets up everything that follows — make sure you understand the core concepts before proceeding to Week 2.
      

Key Concepts

The lecture introduces the four main pillars of this course: Convolution & Feature Maps, Classic Architectures: VGG, ResNet, EfficientNet, Object Detection: YOLO, Faster R-CNN, Semantic Segmentation: U-Net. Each will be explored in depth over the 14-week curriculum, with hands-on projects reinforcing theory at every stage.

# Quick Start: verify your environment is ready for DS303
import sys
print(f"Python {sys.version}")

# Check key libraries are installed
try:
    import numpy, pandas, matplotlib
    print("✅ Core libraries ready")
except ImportError as e:
    print(f"❌ Missing: {e} — run: pip install numpy pandas matplotlib")

This Week's Focus

Focus on mastering: Convolution & Feature Maps and Classic Architectures: VGG, ResNet, EfficientNet. These are the prerequisites for everything in Week 2. The concepts build on each other — do not skip the practice exercises.

📋 Project 1 of 3 50% of Final Grade

DS303 Project 1: Real-Time Object Detector

Train an object detector on a custom dataset (or COCO subset) and build a real-time inference pipeline using OpenCV. Measure FPS, mAP, and inference latency.

Object detection model (YOLOv5 or custom)
Custom dataset collection and annotation
Real-time inference script with OpenCV
Benchmark: FPS, precision, recall, mAP@50

50%

3 Projects

20%

Midterm Exam

30%

Final Exam

📝 Sample Exam Questions

These represent the style and difficulty of questions you'll see on the midterm and final. Start thinking about them now.

Conceptual Short Answer

What is the receptive field of a neuron in a CNN, and how does it grow with depth?

Analysis Short Answer

Explain the skip connections in ResNet. Why do they solve the degradation problem?

Applied Code / Proof

What is the difference between object detection and semantic segmentation?