Contact
Back to Courses
Fall 2024 • 12 Credits
24-678

Computer Vision for Engineers

This introductory course teaches fundamental computer vision theories and computational methods, preparing students to select appropriate sensors and visual-data processing techniques for engineering applications.

Level Graduate
Semester Fall
Credits 12
Status Active

Course Info

Course Number: 24-678
Credits: 12
Level: Graduate

Prerequisites

  • Basic programming experience
  • Linear algebra
  • Calculus

Learning Outcomes

  • Select appropriate sensors for vision applications
  • Apply image processing techniques to engineering problems
  • Perform motion analysis and tracking
  • Reconstruct 3D scenes from images
  • Process pointcloud data effectively
  • Implement object detection algorithms

Key Topics

  • Sensor Selection
  • Image Processing and Analysis
  • Motion Analysis
  • 3D Reconstruction
  • Pointcloud Processing
  • Feature Tracking
  • Object Detection

Textbooks

Course materials provided online Required
by Prof. Kenji Shimada

Tags

  • Computer Vision
  • Image Processing
  • Graduate
  • Machine Learning

Course Overview

This introductory course teaches fundamental computer vision theories and computational methods. Students gain practical knowledge in selecting appropriate sensors and visual-data processing techniques for engineering applications, preparing them for advanced research-oriented coursework.

Course Format

Meeting Times: Mondays and Wednesdays, 12:00–1:50 PM Location: Posner Hall 152 Format: In-person lectures

Eight Major Topics

The curriculum addresses eight major areas:

  1. Sensor Selection: Choosing the right cameras and imaging systems
  2. Image Processing: Filtering, enhancement, and manipulation
  3. Image Analysis: Feature extraction and pattern recognition
  4. Motion Analysis: Tracking and optical flow
  5. 3D Reconstruction: Building 3D models from 2D images
  6. Pointcloud Processing: Working with depth sensor data
  7. Feature Tracking: Following objects across frames
  8. Object Detection: Identifying and localizing objects

Real-World Applications

The course emphasizes practical applications including:

  • Factory automation and quality control
  • Infrastructure inspection and monitoring
  • Mobile robot navigation
  • Autonomous vehicles
  • Medical diagnosis and imaging

Learning Activities

  • Weekly Problem Sets: Algorithm design, programming, and result presentation
  • Course Project: Group-based final project applying vision techniques
  • Hands-on Implementation: Practical coding with real datasets

Teaching Team

Instructor: Professor Kenji Shimada

Support Staff: One co-instructor, one TA, and four course assistants

Course Philosophy

The course emphasizes both theoretical understanding and practical implementation, positioning students for careers in industry and academia where vision technology has become integral to modern engineering systems.