earticle

논문검색

Spectral-based Shadow Detection for Single Image

초록

영어

Shadow detection for single image is difficult but has wide applications. This paper proposes a novel and fast shadow detection method based on the Tricolor Attenuation Model [1]. In this study, we analyze the spectral property of outdoor light sources to estimate the parameters of TAM. Then our shadow detection method is proposed by integrate the TAM feature and intensity information. Our method can extract shadows for a single and uncalibrated image without any prior knowledge, even for complex scenes. Experimental results show the effectiveness of the proposed method.

목차

Abstract
 1. Introduction
 2. Review the Tricolor Attenuation Model
  2.1. m and n Estimation
 3. Shadow Detection Algorithm
 4. Experimental Results
 5. Conclusion
 Acknowledgements
 References

저자정보

  • Xiaoyan Xu College of Information Science and Technology,Dalian Maritime University, Dalian 116026, China
  • Xiaoming Liu College of Information Science and Technology,Dalian Maritime University, Dalian 116026, China

참고문헌

자료제공 : 네이버학술정보

    함께 이용한 논문

      ※ 원문제공기관과의 협약기간이 종료되어 열람이 제한될 수 있습니다.

      0개의 논문이 장바구니에 담겼습니다.