#357:
D. K. Ufuktepe,
J. Collins,
E. Ufuktepe,
J. Fraser,
T. Krock, and
K. Palaniappan
IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Workshop on Analysis of Aerial Motion Imagery (WAAMI),
2021
Abstract,
Bibtex,
PlainText,
Google Scholar
Shadows, motion parallax, and occlusions pose significant challenges to vision tasks in wide-area motion imagery (WAMI) including object identification and tracking. Although there are many successful shadow detection approaches that work well in indoor scenes, close-range outdoor scenes, and spaceborne satellite images, the methods tend to fail in intermediate altitude aerial WAMI. We propose an automatic shadow mask estimation approach for supervision without manual labeling to provide a large amount of training data for learning-based aerial shadow extraction. Analytical ground-truth shadow masks are generated using 3D point clouds combined with known solar angles. FSDNet, a deep network for shadow detection, is evaluated on aerial imagery. Preliminary results indicate that training using automated shadow mask supervision improves performance, and opens the door for developing new deep architectures for shadow detection and enhancement in WAMI.
@inproceedings{2021a,
author = "D. K. Ufuktepe and J. Collins and E. Ufuktepe and J. Fraser and T. Krock and K. Palaniappan",
title = "Learning-based shadow Detection in Aerial Imagery Using Automatic Training Supervision from 3D Point Clouds",
year = 2021,
journal = "IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Workshop on Analysis of Aerial Motion Imagery (WAAMI)",
month = "Oct"
}
D. K. Ufuktepe, J. Collins, E. Ufuktepe, J. Fraser, T. Krock, and K. Palaniappan. Learning-based shadow Detection in Aerial Imagery Using Automatic Training Supervision from 3D Point Clouds. IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Workshop on Analysis of Aerial Motion Imagery (WAAMI), October 2021.