Abstract
The effects of shadow correction on the classification of vegetation and land cover is studied in high resolution (10 × 10 cm) aerial images. Shadow detection reuses the feature set derived from the imagery for vegetation classification. A separate model is used to classify data in the first pass into three classes: water, land and shadows. Areas classified as shadow are then corrected using a regression based model and the shadow pixel features are recalculated and updated into the feature set. The results indicate that shadow correction can significantly improve classification results in vegetation mapping; in our case the classification accuracy increased from 35.1 to 46.1 in a shadowy test area.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
