Volume XLII-4/W18
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-4/W18, 687–692, 2019
https://doi.org/10.5194/isprs-archives-XLII-4-W18-687-2019
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-4/W18, 687–692, 2019
https://doi.org/10.5194/isprs-archives-XLII-4-W18-687-2019
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

  18 Oct 2019

18 Oct 2019

SINGLE-IMAGE DEHAZING ON AERIAL IMAGERY USING CONVOLUTIONAL NEURAL NETWORKS

M. Madadikhaljan1,2, R. Bahmanyar1, S. M. Azimi1, P. Reinartz1, and U. Sörgel2 M. Madadikhaljan et al.
  • 1DLR, German Aerospace Center, Earth Observation Center (EOC), Münchener Str. 20, 82234 Wessling, Germany
  • 2Institute of Photogrammetry (ifp), University of Stuttgart, Germany

Keywords: Single-image Dehazing, Convolutional Neural Networks, Aerial Imagery, Haze Removal, Hazy Image Generation

Abstract. Haze contains floating particles in the air which can result in image quality degradation and visibility reduction in airborne data. Haze removal task has several applications in image enhancement and can improve the performance of automatic image analysis systems, namely object detection and segmentation. Unlike rich haze removal literature in ground imagery, there is a lack of methods specifically designed for aerial imagery, considering the fact that there is a characteristic difference between the aerial imagery domain and ground one. In this paper, we propose a method to dehaze aerial images using Convolutional Neural Networks (CNNs). Currently, there is no available data for dehazing methods in aerial imagery. To address this issue, we have created a syntheticallyhazed aerial image dataset to train the neural network on aerial hazy image dataset. We train All-in-One dehazing network (AODNet) as the base approach on hazy aerial images and compare the performance of our proposed approach against the classical model. We have tested our model on natural as well as the synthetically-hazed aerial images. Both qualitative and quantitative results of the adapted network show an improvement in dehazing results. We show that the adapted AOD-Net on our aerial image test set increases PSNR and SSim by 2.2% and 9%, respectively.