In the process of collecting the pavement images, there exists shadows in the pavement images due to various objects on the road and rodside. This seriously affects the auto-identification and classification of the images. In view of this problem, we propose a recognition method which can deal with the shadow. We withdraw the edge subset of the shadow in the image by image division and decompose the image into the light part and shadow part. Then the two sub-images can be classified by the variance of the sub-images. This method is simple, and avoids disturbance of the shadow. The availability of the method has been proven by the experiment's results.
Recognition of Pavement Image with Shadow Based on Image Decomposition
First International Conference on Transportation Engineering ; 2007 ; Southwest Jiaotong University, Chengdu, China
2007-07-09
Conference paper
Electronic Resource
English
Recognition of Pavement Image with Shadow Based on Image Decomposition
British Library Conference Proceedings | 2007
|User-assisted image shadow removal
British Library Online Contents | 2017
|Shadow Imaging of Geosynchronous Satellites: Simulation, Image Reconstruction, and Shadow Prediction
British Library Conference Proceedings | 2016
|