TY - JOUR
T1 - Comparative Analysis of Different CNN Models for Building Segmentation from Satellite and UAV Images
AU - Sariturk, Batuhan
AU - Kumbasar, Damla
AU - Seker, Dursun Zafer
N1 - Publisher Copyright:
© 2023 American Society for Photogrammetry and Remote Sensing.
PY - 2023/2
Y1 - 2023/2
N2 - Building segmentation has numerous application areas such as urban planning and disaster management. In this study, 12 CNN models (U-Net, FPN, and LinkNet using EfficientNet-B5 backbone, U-Net, SegNet, FCN, and six Residual U-Net models) were gener-ated and used for building segmentation. Inria Aerial Image Labeling Data Set was used to train models, and three data sets (Inria Aerial Image Labeling Data Set, Massachusetts Buildings Data Set, and Syedra Archaeological Site Data Set) were used to evaluate trained models. On the Inria test set, Residual-2 U-Net has the highest F1 and Intersection over Union (IoU) scores with 0.824 and 0.722, respectively. On the Syedra test set, LinkNet-EfficientNet-B5 has F1 and IoU scores of 0.336 and 0.246. On the Massachusetts test set, Residual-4 U-Net has F1 and IoU scores of 0.394 and 0.259. It has been observed that, for all sets, at least two of the top three models used residual connections. Therefore, for this study, residual connections are more successful than conventional convolutional layers.
AB - Building segmentation has numerous application areas such as urban planning and disaster management. In this study, 12 CNN models (U-Net, FPN, and LinkNet using EfficientNet-B5 backbone, U-Net, SegNet, FCN, and six Residual U-Net models) were gener-ated and used for building segmentation. Inria Aerial Image Labeling Data Set was used to train models, and three data sets (Inria Aerial Image Labeling Data Set, Massachusetts Buildings Data Set, and Syedra Archaeological Site Data Set) were used to evaluate trained models. On the Inria test set, Residual-2 U-Net has the highest F1 and Intersection over Union (IoU) scores with 0.824 and 0.722, respectively. On the Syedra test set, LinkNet-EfficientNet-B5 has F1 and IoU scores of 0.336 and 0.246. On the Massachusetts test set, Residual-4 U-Net has F1 and IoU scores of 0.394 and 0.259. It has been observed that, for all sets, at least two of the top three models used residual connections. Therefore, for this study, residual connections are more successful than conventional convolutional layers.
UR - http://www.scopus.com/inward/record.url?scp=85151782294&partnerID=8YFLogxK
U2 - 10.14358/PERS.22-00084R2
DO - 10.14358/PERS.22-00084R2
M3 - Article
AN - SCOPUS:85151782294
SN - 0099-1112
VL - 89
SP - 97
EP - 105
JO - Photogrammetric Engineering and Remote Sensing
JF - Photogrammetric Engineering and Remote Sensing
IS - 2
ER -