3. 강의목표
This course provides students with a theoretical foundation and practical proficiency in computational vision and visual intelligence. Students will learn the principles behind the formation of 2D and 3D visual data and the AI models that process them, developing the core knowledge needed to understand the evolution of computer vision technologies from early methods to modern approaches.
4. 강의선수/수강필수사항
- Students should be familiar with basic mathematical concepts, including linear algebra, multivariate calculus, and probability theory.
- A foundational understanding of programming is required.
- Python will be the primary programming environment for coursework; therefore, prior experience with Python is expected.
5. 성적평가
| 중간고사 |
기말고사 |
출석 |
과제 |
프로젝트 |
발표/토론 |
실험/실습 |
퀴즈 |
기타 |
계 |
|
|
|
|
|
|
|
|
|
|
| 비고 |
Midterm exam (30%), Coursework (40%), Final project (30%)
|
7. 참고문헌 및 자료
Richard Szeliski, Computer Vision: Algorithms and Applications, 2nd ed., 2020
Richard Hartley and Andrew Zisserman, Multiple View Geometry in Computer Vision, 2nd ed., 2004
8. 강의진도계획
- Course overview
- Camera anatomy
- Image representation
- Learning based approaches
- Classification
- Semantic segmentation
- Object detection
- Generative model
- Camera geometry
- 3D understanding
11. 장애학생에 대한 학습지원 사항
- 수강 관련: 문자 통역(청각), 교과목 보조(발달), 노트필기(전 유형) 등
- 시험 관련: 시험시간 연장(필요시 전 유형), 시험지 확대 복사(시각) 등
- 기타 추가 요청사항 발생 시 장애학생지원센터(279-2434)로 요청