TY - GEN
T1 - CNN based suburban building detection using monocular high resolution Google Earth images
AU - Zhang, Qinchuan
AU - Wang, Yunhong
AU - Liu, Qingjie
AU - Liu, Xiangyu
AU - Wang, Wei
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/11/1
Y1 - 2016/11/1
N2 - This paper proposes a deep convolutional neural networks (CNNs) based method to automatically detect suburban buildings from high resolution Google Earth imagery. Traditional methods based on low-level hand-engineered features or mid-level bag of features have great limitations in complex environment, especially in suburban areas. Inspired by the astounding achievement of CNNs in object recognition and detection, we develop a novel method to detect buildings in cluttered images which consists of three main steps. Firstly, a multi-scale saliency computation is employed to extract built-up areas and a sliding windows approach is applied to generate candidate regions. Then, a CNN is applied to classify the regions. Finally, an improved non maximum suppression is used to remove false buildings. We test our method on a collection of very challenging Google Earth images and achieve 89% precision, which shows robustness and efficiency of our method.
AB - This paper proposes a deep convolutional neural networks (CNNs) based method to automatically detect suburban buildings from high resolution Google Earth imagery. Traditional methods based on low-level hand-engineered features or mid-level bag of features have great limitations in complex environment, especially in suburban areas. Inspired by the astounding achievement of CNNs in object recognition and detection, we develop a novel method to detect buildings in cluttered images which consists of three main steps. Firstly, a multi-scale saliency computation is employed to extract built-up areas and a sliding windows approach is applied to generate candidate regions. Then, a CNN is applied to classify the regions. Finally, an improved non maximum suppression is used to remove false buildings. We test our method on a collection of very challenging Google Earth images and achieve 89% precision, which shows robustness and efficiency of our method.
KW - CNN
KW - building detection
KW - multi-scale saliency
KW - suburban
UR - https://www.scopus.com/pages/publications/85007492103
U2 - 10.1109/IGARSS.2016.7729166
DO - 10.1109/IGARSS.2016.7729166
M3 - 会议稿件
AN - SCOPUS:85007492103
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 661
EP - 664
BT - 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016
Y2 - 10 July 2016 through 15 July 2016
ER -