Ground-based remote sensing cloud detection using dual pyramid network and encoder–decoder constraint

Zhang, Zhong and Yang, Shuzhen and Liu, Shuang and Cao, Xiaozhong and Durrani, Tariq S. (2022) Ground-based remote sensing cloud detection using dual pyramid network and encoder–decoder constraint. IEEE Transactions on Geoscience and Remote Sensing, 60. ISSN 0196-2892 (https://doi.org/10.1109/tgrs.2022.3163917)

[thumbnail of Zhang-etal-IEEE-TGRS-2022-Ground-based-remote-sensing-cloud-detection-using-dual]
Preview
Text. Filename: Zhang_etal_IEEE_TGRS_2022_Ground_based_remote_sensing_cloud_detection_using_dual.pdf
Accepted Author Manuscript
License: Strathprints license 1.0

Download (1MB)| Preview

Abstract

Many methods for ground-based remote sensing cloud detection learn representation features using the encoder–decoder structure. However, they only consider the information from single scale, which leads to incomplete feature extraction. In this article, we propose a novel deep network named dual pyramid network (DPNet) for ground-based remote sensing cloud detection, which possesses an encoder–decoder structure with dual pyramid pooling module (DPPM). Specifically, we process the feature maps of different scales in the encoder through dual pyramid pooling. Then, we fuse the outputs of the dual pyramid pooling in the same pyramid level using the attention fusion. Furthermore, we propose the encoder–decoder constraint (EDC) to relieve information loss in the process of encoding and decoding. It constrains the values and the gradients of probability maps from the encoder and the decoder to be consistent. Since the number of cloud images in the publicly available databases for ground-based remote sensing cloud detection is limited, we release the TJNU Large-scale Cloud Detection Database (TLCDD) that is the largest database in this field. We conduct a series of experiments on TLCDD, and the experimental results verify the effectiveness of the proposed method.