Volume XLII-3
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3, 475-480, 2018
https://doi.org/10.5194/isprs-archives-XLII-3-475-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3, 475-480, 2018
https://doi.org/10.5194/isprs-archives-XLII-3-475-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

  30 Apr 2018

30 Apr 2018

TARGETS MASK U-NET FOR WIND TURBINES DETECTION IN REMOTE SENSING IMAGES

M. Han1,2, H. Wang1,2, G. Wang2, and Y. Liu2 M. Han et al.
  • 1School of Geomatics, Liaoning Technical University, Fuxin, People's Republic of China
  • 2Satellite Survey and Mapping Centre, Beijing, People's Republic of China

Keywords: object detection, VHRRSI, wind turbines, shadow, wide-field detector, U-Net

Abstract. To detect wind turbines precisely and quickly in very high resolution remote sensing images (VHRRSI) we propose target mask U-Net. This convolution neural network (CNN), which is carefully designed to be a wide-field detector, models the pixel class assignment to wind turbines and their context information. The shadow, which is the context information of the target in this study, has been regarded as part of a wind turbine instance. We have trained the target mask U-Net on training dataset, which is composed of down sampled image blocks and instance mask blocks. Some post-processes have been integrated to eliminate wrong spots and produce bounding boxes of wind turbine instances. The evaluation metrics prove the reliability and effectiveness of our method for the average F1-score of our detection method is up to 0.97. The comparison of detection accuracy and time consuming with the weakly supervised targets detection method based on CNN illustrates the superiority of our method.