본문 바로가기

Others/Odds & Ends

다양한 종류의 LBP(Local Binary Pattern) 알고리즘 테스트 결과

2002년도에 Ojala에 의해서 제안된 LBP(Local Binary Pattern)는 조명 변화에 강건하다는 장점이 있지만, 잡음에 약하며 히스토그램 Bin의 크기가 256개인 만큼 특징의 차원수가 높아진다는 단점이 있다. 이를 개선하고자 다양한 변종의 LBP 알고리즘들이 연구되었다. 차원의 수를 줄이고, 조명 변화에 대한 강건함과 잡음에 대한 강건함을 동시에 만족하며, 스케일에 불변하기 위한 노력들을 위한 많은 알고리즘들이 탄생하였다. 아래는 그 중 몇몇의 결과와 관련 논문들을 보여준다.

결과 영상

 

참고 문헌

1. A Generalized Local Binary Pattern Operator for Multiresolution Gray Scale and Rotation Invariant Texture Classification, 2001

2. Extended Local Binary Pattern Features for Improving Settlement Type Classification of QuickBird Images, 2012

3. Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns, 2002

4. Description of Interest Regions with Center-Symmetric Local Binary Patterns, 2006

5. HYBRID CENTER-SYMMETRIC LOCAL PATTERN FOR DYNAMIC BACKGROUND SUBTRACTION, 2011

6. An eXtended Center-Symmetric Local Binary Pattern for Background Modeling and Subtraction in Videos, 2015

7. Modeling Pixel Process with Scale Invariant Local Patterns for Background Subtraction in Complex Scenes, 2010

8. Real-time background subtraction-based video surveillance of people by integrating local texture patterns, 2013

9. DYNAMIC BACKGROUND SUBTRACTION BASED ON SPATIAL EXTENDED CENTER-SYMMETRIC LOCAL BINARY PATTERN, 2010

10. A texture descriptor: BackGround Local Binary Pattern (BGLBP), 2015