High-resolution remote sensing images (HRRSIs) contain abundant details and texture information. Existing lossy compression methods employ quantization to eliminate redundant information, but this leads to irreversible effects on the subtle details of HRRSIs. This paper proposes a quantization loss compensation network to address this issue. We use a trainable variational autoencoder to learn the details and texture information of HRRSIs from the error between pre-and post-quantized latent representations. During the encoding of HRRSIs, the quantization errors are inputted into the encoding module of the compensation network to generate bitstreams. When it comes to image decoding, using the decoding module of the compensation network to generate quantization loss compensation information, which, together with the quantization latent representations, contributes to the HRRSIs reconstruction. To validate the effectiveness of our approach in reconstructing details of HRRSIs, we conducted experiments on two remote sensing datasets. The experimental results also indicate that our method exhibits superior compression performance.

With the increasing volume of high-resolution satellite images, image compression technology has become a research hotspot in the field of remote sensing image processing; however, the existing remote sensing image compression methods, such as JPEG2000, fail to ensure high-ratio and high-fidelity compression. To address this issue, we use a deep neural network to build a learned image compression model named HL-RSCompNet, which is specifically designed for remote sensing images. This model considers both high-frequency and low-frequency features in remote sensing images. We use discrete wavelet transformation (DWT) to divide the image features into two components: the high-frequency feature component and the low-frequency feature component. In addition, we introduce a frequency domain encoding-decoding module with the goal of bolstering the model’s capacity to represent both high-frequency and low-frequency features effectively. This approach allows the model to preserve more high-frequency information, thereby enhancing the overall compression performance of the learned image compression model. Extensive experimental and validation works are performed on four high-resolution remote sensing image datasets. The results indicate that our method outperforms existing traditional compression methods like JPEG2000 and even surpasses the performance of state-of-the-art learned image compression models. Our project is available athttps://github.com/shao15xiang/HL-RSCompNet.

High-ratio image compression has always been a hotspot for remote sensing satellite image transmission. Especially for a resource-limited environment on board, image compression plays an important role in data storage and transmission. This article proposes a novel method for integrating information extraction network and image compression network into a comprehensive compression framework in order to achieve high-ratio image codec. To reconstruct region-of-interest (ROI) latent representations, we propose a latent feature selection (LFS) module. Some of the channel representations are removed according to the spatial location of the background, but the channel representations of ROI are entirely retained. To effectively validate the performance of our method, we conduct extensive experiments on multiple datasets. The experimental results show that the proposed framework is better at satellite data compression than traditional codecs.

The main purpose of cloud detection is to estimate cloud coverage and thus determine whether to transmit remote sensing images to earth or execute subsequent tasks based on cloud coverage. Fast and accurate cloud coverage estimation is a necessary preprocessing step on board. Therefore, we propose a new approach for cloud coverage estimation using a regression network to directly predict the coverage. A cloud coverage estimation network, which is termed$\text{C}^{2}\text{E}$-Net, is proposed in this work. The proposed network consists of three modules, including an encoder for representation feature extraction, a coverage estimation for predicting the cover rate of clouds, and an auxiliary supervision module for improving the performance of the model. To verify the effectiveness of our method, experiments are performed on two open-source datasets (Landset 8 Biome dataset and GaoFen-1 WFV dataset). Our method effectively improves the efficiency of cloud detection by at least doubling, while keeping the estimation error low.

High-ratio image compression is difficult because remote sensing images have complex background and rich information, and the correlation between features is weak. An accurate entropy model is an important way to solve the problem by enhancing the representation ability of the compression models. The entropy model is more suited to estimate the probability distributions with the sparse latent representations. This study proposes a novel entropy model (DWTGMM) based on discrete wavelet transform (DWT) and Gaussian mixture model (GMM) for remote sensing image compression. The method uses DWT to transform the latent representations into wavelet domain and obtains four sparse representations, and then uses the proposed DWTGMM to model them separately to estimate the probability distribution of each element. It is noteworthy that the DWT used in our approach does not require learning parameters and can be combined with other entropy models to acquire the distribution of latent representations. To evaluate our method, we construct three remote sensing image datasets, i.e., GoogleMap, GF1, and GF7. We compare our method with several popular learned compression models and traditional codecs. Experimental results show that the proposed method can achieve excellent performance with low complexity. Especially with the same model architecture, the DWTGMM achieves the best compression performance.

In recent years, with the development of high-resolution remote sensing (RS) images and deep learning technology, high-quality source data and state-of-the-art methods have become increasingly available, and great progress has been made in change detection (CD) in RS fields. However, existing methods still suffer from weak network feature representation and poor CD performance. To address these problems, we propose a novel CD network, called dual-pathway CD network (DP-CD-Net), which can help enhance feature representation and achieve a more accurate difference map. The proposed method contains a dual-pathway feature difference network (FDN), an adaptive fusion module (AFM), and an auxiliary supervision strategy. Dual-pathway FDNs can effectively enhance feature representation by supplementing the detailed information from the encoding layers. Then, we use the AFM method to fuse the difference maps. To solve the problem of training difficulty, we use the auxiliary supervision strategy to improve the performance of DP-CD-Net. We conduct extensive experiments to validate the performance of the proposed method on the LEVIR-CD dataset. The results demonstrate that the proposed method performs better than existing methods.

Semantic segmentation plays a vital role in the segmentation of remote sensing field for its wide range of applications. The major current method for segmentation of remotely sensed imagery is using multiple scales strategy to improve the performance of segmentation networks. However, the ground object with uncertain scale in high-resolution aerial imagery is difficult to be segmented with conventional models. To address this problem, an adaptive feature selection module is designed, in which attention module learns weight contributions of each feature blocks in different scales. We employ the pyramid scene parsing network (PSPNet), DeepLabV3, and U-Net with the proposed module to conduct experiments on two benchmarks (the Vaihingen set and the WHU Building data set). The experimental results and comprehensive analysis validate the efficiency and practicability of the proposed method in semantic segmentation of remote sensing images.

Precise skin lesion classification is still challenging due to two problems, i.e., (1) inter-class similarity and intra-class variation of skin lesion images, and (2) the weak generalization ability of single Deep Convolutional Neural Network trained with limited data. Therefore, we propose a Global-Part Convolutional Neural Network (GP-CNN) model, which treats the fine-grained local information and global context information with equal importance. The Global-Part model consists of a Global Convolutional Neural Network (G-CNN) and a Part Convolutional Neural Network (P-CNN). Specifically, the G-CNN is trained with downscaled dermoscopy images, and is used to extract the global-scale information of dermoscopy images and produce the Classification Activation Map (CAM). While the P-CNN is trained with the CAM guided cropped image patches and is used to capture local-scale information of skin lesion regions. Additionally, we present a data-transformed ensemble learning strategy, which can further boost the classification performance by integrating the different discriminant information from GP-CNNs that are trained with original images, color constancy transformed images, and feature saliency transformed images, respectively. The proposed method is evaluated on the ISIC 2016 and ISIC 2017 Skin Lesion Challenge (SLC) classification datasets. Experimental results indicate that the proposed method can achieve the state-of-the-art skin lesion classification performance (i.e., an AP value of 0.718 on the ISIC 2016 SLC dataset and an Average Auc value of 0.926 on the ISIC 2017 SLC dataset) without any external data, compared with other current methods which need to use external data.