DRT 465 · 3(2-3-5) · Year/term 4/2

Intelligent Image Analysis Systems

ระบบวิเคราะห์ภาพอัจฉริยะ

Progress

Notional hours: 150 h (online/self-study 75 · in class/lab 75)

Course description

Intelligent image and video analysis pipelines; image data preparation and annotation; deep-learning object detection, tracking and counting; real-time edge processing; evaluating accuracy, latency and fairness; ethics and personal-data protection.

Thai description

ขั้นตอนการวิเคราะห์ภาพและวิดีโออัจฉริยะ การเตรียมและกำกับข้อมูลภาพ การตรวจจับ ติดตาม และนับวัตถุด้วยการเรียนรู้เชิงลึก การประมวลผลแบบเวลาจริงบนอุปกรณ์ปลายทาง การประเมินความแม่นยำ ความหน่วง และความเป็นธรรมของระบบ จริยธรรมและการคุ้มครองข้อมูลส่วนบุคคล

Description source: New draft for the curriculum committee

Notes for the curriculum committee

ทับซ้อนบางส่วนกับ DRT 337 และ DRT 492 ควรกำหนดให้ DRT 465 เน้นระบบวิดีโอแบบเวลาจริงสำหรับงานเฝ้าระวัง

Course learning outcomes (CLO)

CLO	Outcome	PLO
CLO1	Explain intelligent image analysis pipelines	PLO4
CLO2	Develop detection, tracking and counting systems	PLO4
CLO3	Evaluate accuracy, latency and fairness	PLO4PLO6

Learning modules

1Video analytics
Weeks 1–3 · 30 h2 KU

Online (before class) · 15 h

Study the assigned knowledge units in advance, review media and take the module quiz

Intelligent video analyticsIn development
Computer vision and the path to edge AITH

In class / field · 15 h

Lab or field practice from worksheets with a safety checklist

Learning evidence: Checked worksheets and quiz results

Open module

2Datasets and labelling
Weeks 4–6 · 30 h2 KU

Online (before class) · 15 h

Study the assigned knowledge units in advance, review media and take the module quiz

In class / field · 15 h

Lab or field practice from worksheets with a safety checklist

Learning evidence: Checked worksheets and quiz results

Open module

3Detection and tracking
Weeks 7–9 · 30 h2 KU

Online (before class) · 15 h

Study the assigned knowledge units in advance, review media and take the module quiz

In class / field · 15 h

Lab or field practice from worksheets with a safety checklist

Learning evidence: Checked worksheets and quiz results

Open module

4Edge and real time
Weeks 10–12 · 30 h2 KU

Online (before class) · 15 h

Study the assigned knowledge units in advance, review media and take the module quiz

Deploying AI models to edge devicesIn development
Edge benchmarking and deployment planningTH

In class / field · 15 h

Lab or field practice from worksheets with a safety checklist

Learning evidence: Checked worksheets and quiz results

Open module

5Evaluation and ethics
Weeks 13–15 · 30 h3 KU

Online (before class) · 15 h

Study the assigned knowledge units in advance, review media and take the module quiz

In class / field · 15 h

Lab or field practice from worksheets with a safety checklist

Learning evidence: Checked worksheets and quiz results

Open module

Assessment (draft)

Labs and worksheets	35%
Module quizzes	10%
Midterm examination	20%
Mini-project or practical exam	35%

Knowledge domain

D04 Sensors and embedded systems D09 Law, safety and risk D11 Artificial intelligence and computer vision D13 Surveying, mapping and geoinformatics D14 Inspection, industry and surveillance D18 Management, innovation and professional practice

Key references

Szeliski, R. (2022). Computer vision: Algorithms and applications (2nd ed.). Springer. link
Géron, A. (2022). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow (3rd ed.). O'Reilly.
UNESCO. (2021). Recommendation on the ethics of artificial intelligence. link