z-logo
open-access-imgOpen Access
Moving shadow detection and removal – a wavelet transform based approach
Author(s) -
Khare Manish,
Srivastava Rajneesh Kumar,
Khare Ashish
Publication year - 2014
Publication title -
iet computer vision
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.38
H-Index - 37
eISSN - 1751-9640
pISSN - 1751-9632
DOI - 10.1049/iet-cvi.2014.0028
Subject(s) - artificial intelligence , shadow (psychology) , computer vision , computer science , discrete wavelet transform , object detection , wavelet , wavelet transform , pattern recognition (psychology) , stationary wavelet transform , psychology , psychotherapist
Shadow detection and removal is an important problem in computer vision. The real challenge in moving shadow detection and removal is to classify moving shadow points which are many times misclassified as moving object points in a video sequences. Various shadow detection and removal algorithms have been proposed for images but only a few works have been done for moving objects. In this study, a novel method for shadow detection and removal is proposed using discrete wavelet transform (DWT). The authors have used DWT because of its multi‐resolution property that decomposes an image into four different bands without loss of the spatial information. For detection and removal of shadow, they have proposed a new threshold in the form of relative standard deviation. The value of threshold is automatically determined and does not require any supervised learning or manual calibration. The proposed method is flexible and depends on only one parameter, namely, wavelet coefficients. Results of shadow detection and removal from moving object after applying the proposed method are compared with the results of other state‐of‐the‐art methods in terms of visual performance and a number of quantitative performance parameters. The proposed method is found to be better and more robust than other methods.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.
Having issues? You can contact us here