This course focuses on sensors, information processing methods, and sensing systems for intelligent information extraction
in real-world environments. Students will be able to understand the pros and cons of various sensors such as accelerometers,
gyroscopes, cameras, stereo cameras, RGB-D cameras, LiDARs, and other sensors. They will understand various algorithms and
machine learning techniques that can be used to analyze different types of sensor data ranging from simple acceleration/temperature/other
information to image data and point clouds, etc. in order to extract meaningful information. They will also be able to design
sensing architectures for various situations. Examples include infrastructure inspection and maintenance, agriculture, factories,
construction sites, refineries and oil plants, and others.
In the first half of the course, students will learn about various types of sensors and the information they can obtain, their
pros and cons, their limits, and design considerations. This will also include various methods to process sensor information
ranging from basic geometric/statistical processing to advanced machine learning techniques. The second half of the class
will focus on real life examples of intelligent sensing in various environments such as infrastructure inspection and maintenance,
agriculture, factories, construction sites, refineries and oil plants, and others. Students will also construct a simple demo
on intelligent sensing using image data and analyze real life applications to write reports, and design a sensing framework
for a given task.
- Students can analyze and compare sensing modalities (e.g., camera, stereo camera, LiDAR, inertial and environmental sensors) by explaining their measurable outputs, limitations, noise characteristics, and appropriate application domains.
- Students can analyze real-world intelligent sensing systems by identifying required information layers, the sensors used, and the processing methods necessary to extract meaningful information from raw sensor data.
- Students can design and evaluate an intelligent sensing architecture for a specified real-world task by selecting appropriate sensors, defining the required processing, and evaluating accuracy, robustness, and system constraints.
| Report 1 (analysis) | Report 2 (design) | Discussion and presentation | Report 3 (design) | Total. | |
|---|---|---|---|---|---|
| 1. | 15% | 15% | |||
| 2. | 15% | 10% | 10% | 35% | |
| 3. | 10% | 10% | 30% | 50% | |
| 4. | 0% | ||||
| Total. | 30% | 20% | 20% | 30% | - |
| Class schedule | HW assignments (Including preparation and review of the class.) | Amount of Time Required | |
|---|---|---|---|
| 1． | Guidance Introduction to Intelligent Sensing and digital twins Examples of digital twins, history Introduction to various sensors, principles |
Review of topics | 100minutes |
| 2． | Overview of Sensing Modalities What each sensor can and cannot measure Sensor Characteristics and Limitations Noise sources Resolution vs accuracy vs precision Calibration |
Review of topics | 100minutes |
| 3． | From Raw Signals to Information Geometric processing (projection, triangulation) Statistical filtering Feature extraction When machine learning is necessary |
Review of topics | 100minutes |
| 4． | Machine Learning for Sensor Data Classification vs detection vs regression Image-based learning Point cloud processing Limits of deep learning |
Review of topics | 100minutes |
| 5． | Image Processing Cameras as sensors Why image processing, methods Statistical/geometric methods |
Review of topics | 100minutes |
| 6． | Intelligent Image Processing Machine learning Deep learning Recent advances |
Review of topics | 100minutes |
| 7． | 3D measurement and Point Clouds Depth sensors, LiDARS Various types of 3D sensors, their characteristics and limitations |
Review of topics | 100minutes |
| 8． | Real life examples Infrastructure inspection Construction monitoring Factory automation Report topic selection |
Review of topics | 100minutes |
| Report preparation | 200minutes | ||
| 9． | Real-World Case Studies 2 Agriculture monitoring Oil/refinery inspection Environmental monitoring |
Review of topics | 100minutes |
| Report preparation | 200minutes | ||
| 10． | Designing a Simple Intelligent Sensing Experiment Environment setup Demo task explanation |
Review of topics | 100minutes |
| Environment setup | 200minutes | ||
| Experiment | 200minutes | ||
| 11． | Continuation of measurement task Other image processing demos Final report explanation |
Experiment | 300minutes |
| Report preparation | 200minutes | ||
| 12． | Demo presentation and discussion (1) | Presentation | 100minutes |
| 13． | Demo presentation and discussion (2) | Presentation | 100minutes |
| Report preparation | 200minutes | ||
| 14． | Summary of course Final report analysis and discussion |
Review of topics | 50minutes |
| Discussion | 50minutes | ||
| Total. | - | - | 2800minutes |
Evaluation Method
Evaluation will be based on three reports and an in-class presentation/discussion based on designing a sensing system for a given task
The distribution of scores and the passing criteria are as follows:
Report 1: 30 points, Report 2: 20 points, In-class presentation and discussion: 20 points, Report 3: 30 points
Total: 100 points (Passing score: 60 points or higher)
Evaluation Criteria
A score of 60 points will be given to students who demonstrate basic knowledge of designing a sensing system for a given task.
Evaluation will be based on three reports and an in-class presentation/discussion based on designing a sensing system for a given task
The distribution of scores and the passing criteria are as follows:
Report 1: 30 points, Report 2: 20 points, In-class presentation and discussion: 20 points, Report 3: 30 points
Total: 100 points (Passing score: 60 points or higher)
Evaluation Criteria
A score of 60 points will be given to students who demonstrate basic knowledge of designing a sensing system for a given task.
| ways of feedback | specific contents about "Other" |
|---|---|
| Feedback in/outside the class. |
None. Please feel free to join this course regardless of your English ability. Notes and explanations will be provided in
Japanese also, as required.
英語能力を気にせずにご参加ください．ノートや説明は、必要に応じて、日本語でも可能です．
英語能力を気にせずにご参加ください．ノートや説明は、必要に応じて、日本語でも可能です．
- Zoom, email, after class
(Please email to set appointment. You can visit the lab. and ask, too.)
- Course that cultivates a basic problem-solving skills
- Course that cultivates an ability for utilizing knowledge
| Work experience | Work experience and relevance to the course content if applicable |
|---|---|
| N/A | N/A |
- 9.INDUSTRY, INNOVATION AND INFRASTRUCTURE
- 11.SUSTAINABLE CITIES AND COMMUNITIES
Last modified : Mon Mar 16 04:02:44 JST 2026