Event Sensor Course

This is a hands-on course introducing event-based vision through practical experiments and projects using event sensor.

Course Information

Item	Details
Course	Event Camera Exploration
Credits	1
Format	Laboratory / Hands-on
Language	English
Duration	15 Weeks
Hardware	OpenMV X320 Event Camera
Programming	Python
Prerequisites	Basic programming knowledge

Course Description

Unlike conventional cameras that capture complete image frames, event cameras record only changes in brightness, enabling extremely low latency, high dynamic range, and efficient sensing.

This course introduces the fundamentals of event-based vision through practical exercises and project-based learning. Students will learn how event cameras work, collect event streams, process event data, and develop their own event-driven applications.

No prior knowledge of event cameras is required.

Learning Outcomes

After completing this course, students will be able to

Understand the principles of event-based vision
Operate an OpenMV X320 event camera
Capture and visualize event streams
Process event data using Python
Implement simple event-based vision algorithms
Develop a complete event-camera application
Present and demonstrate a working project

Software

Students will use

Python
OpenMV IDE
Git
GitHub
Visual Studio Code (recommended)

Hardware

OpenMV X320 Event Camera
USB Cable
PC (Windows, Linux, or macOS)

Weekly Schedule

Week	Topic	Laboratory
1	Introduction to Event Cameras	Camera demonstration
2	Hardware Setup	Install software and connect the camera
3	Event Streams	Capture and visualize events
4	Motion Sensing	Observe motion-generated events
5	Lighting & Dynamic Range	Indoor and outdoor experiments
6	Event Processing	Filtering and event accumulation
7	Motion Detection	Implement motion detection
8	Object Tracking	Track moving objects
9	Gesture Recognition	Detect simple gestures
10	Event Camera Applications	Explore real-world examples
11	Project Proposal	Design your own project
12	Project Development	Implementation
13	Project Development	Testing and refinement
14	Project Development	Final integration
15	Project Demonstration	Presentation and demo

Repository Structure

.
├── docs/
│   ├── lectures/
│   ├── labs/
│   └── slides/
│
├── examples/
│   ├── basic/
│   ├── motion_detection/
│   ├── tracking/
│   └── gesture/
│
├── datasets/
│
├── projects/
│
├── assignments/
│
├── resources/
│
└── README.md

Labs

Each lab includes

Objectives
Background
Step-by-step instructions
Sample code
Exercises
Challenge tasks

Final Project

Students will design and implement an event-camera application.

Possible topics include

Motion detection
Object tracking
Gesture recognition
Event visualization
High-speed sensing
Human-computer interaction
Robotics
Custom applications

Assessment

Component	Weight
Weekly Labs	30%
Participation	10%
Project Proposal	10%
Final Project	35%
Final Presentation	15%

Resources

Useful references will be provided throughout the course.

Course Philosophy

This course emphasizes

Learning by doing
Exploration over memorization
Experimentation
Creativity
Open-source development
Team collaboration

Students are encouraged to modify examples, perform their own experiments, and share interesting discoveries with the class.

GitHub Workflow

Throughout the semester, students will

Clone the course repository.
Complete weekly laboratory exercises.
Commit changes regularly.
Push their work to GitHub.
Submit assignments through GitHub.
Develop their final project using version control.

License

Unless otherwise specified, all course materials are released for educational use.

Maintainers

Khanh N. Dang (check this page for the contact).
AY2026: Rui Shiota (m5291066@u-aizu.ac.jp)