Multispectral and synthetic aperture radar (SAR) image fusion is one of the key technologies to improve image quality. The fusion method of multiscale decomposition includes two aspects: the decomposition of the image and the design of the fusion rule. There are some problems in the traditional decomposition methods, such as gradient reversals, halos, and other artifacts, and limited scale separation of space overlapping features. In addition, the quality of fusion images is greatly affected by the fusion rule design. Therefore, a novel method based on least squares (LS) optimization rolling guidance filtering (RGF) for multiscale decomposition is proposed. All gradients of RGF are optimized by LS to suppress artifacts, such as gradient inversion, and then combined with Gaussian filtering for image decomposition to eliminate interference texture and speckle noise while preserving edge details. At the same time, the decomposition of the image is extended to multiscale space to achieve scale separation of space-overlapping features, which is convenient for multilevel fusion of image features. In the end, based on the scale of decomposition, the results fall into three layers, and coupled neural P (CNP) system and other rules are designed for different layers of information fusion. The results indicate that this method has a good visual effect and outperforms all the other comparison methods on nine evaluation indexes.

Spectral information and backscatter information are both exclusively important bases for land cover classification, and these two kinds of information are found in multispectral images and SAR images, respectively. Therefore, the fusion of complementary information of multispectral and SAR images can effectively improve land cover classification accuracy. However, the existing fusion methods of multispectral and SAR images generally have some problems, such as insensitivity to edge information, serious interference by speckle noise, and unreasonable settings of fusion rules, which lead to unsatisfactory results of land cover classification. To solve this issue, a fusion method based on adaptive multiscale Gaussian co-occurrence filtering decomposition is proposed. Firstly, parameters controlling Gaussian distribution scale in co-occurrence filter are adaptive according to pixel intensity skewness. Gaussian filtering and adaptive co-occurrence filtering are applied to the original image to smooth out speckle noise and interference edges within the textures while preserving edge information between textures. Secondly, difference calculation among the original image, Gaussian filtered image and adaptive co-occurrence filtered image is carried out to realize the decomposition of detail information, edge information and basic information. Compared with the decomposition method that only decomposes detail information and basic information, it can effectively preserve boundary structure between the features. The image decomposition is extended to multi-scale space for multi-layer fusion of image features at the same time. Finally, according to the decomposition scale, the decomposition results are divided into three layers, and corresponding rules of fusion are formulated based on their feature information, so as to generate fusion image with low noise interference, clear boundary and homogeneous pixel convergence. Experimental results show that the proposed method generally performs the best in eight evaluation indexes compared with ten other methods. The overall accuracy, average accuracy and Kappa coefficient of land cover classification are increased by 7.674%, 6.776% and 0.098 respectively compared with those of the original multispectral image in Area 1, and by 6.904%, 7.649% and 0.089 respectively compared with those of the original multispectral image in Area 2.

Remote sensing image fusion can effectively solve the inherent contradiction between spatial resolution and spectral resolution of imaging systems. At present, the fusion methods of remote sensing images based on multi-scale transform usually set fusion rules according to local feature information and pulse-coupled neural network (PCNN), but there are problems such as single local feature, as fusion rule cannot effectively extract feature information, PCNN parameter setting is complex, and spatial correlation is poor. To this end, a fusion method of remote sensing images that combines low-level visual features and a parameter-adaptive dual-channel pulse-coupled neural network (PADCPCNN) in a non-subsampled shearlet transform (NSST) domain is proposed in this paper. In the low-frequency sub-band fusion process, a low-level visual feature fusion rule is constructed by combining three local features, local phase congruency, local abrupt measure, and local energy information to enhance the extraction ability of feature information. In the process of high-frequency sub-band fusion, the structure and parameters of the dual-channel pulse-coupled neural network (DCPCNN) are optimized, including: (1) the multi-scale morphological gradient is used as an external stimulus to enhance the spatial correlation of DCPCNN; and (2) implement parameter-adaptive representation according to the difference box-counting, the Otsu threshold, and the image intensity to solve the complexity of parameter setting. Five sets of remote sensing image data of different satellite platforms and ground objects are selected for experiments. The proposed method is compared with 16 other methods and evaluated from qualitative and quantitative aspects. The experimental results show that, compared with the average value of the sub-optimal method in the five sets of data, the proposed method is optimized by 0.006, 0.009, 0.009, 0.035, 0.037, 0.042, and 0.020, respectively, in the seven evaluation indexes of information entropy, mutual information, average gradient, spatial frequency, spectral distortion, ERGAS, and visual information fidelity, indicating that the proposed method has the best fusion effect.

Performing privacy-preserving remote sensing image retrieval-based tasks in cloud environments has gained widespread attention. This has raised concerns about the efficiency and accuracy of retrieval, the security of image content, the privacy of the retrieval process, the traceability of data distribution, and the authenticity of retrieval results. Therefore, in this paper, we propose a secure and efficient remote sensing image retrieval method with verifiable and traceable in cloud environment. The method applies the CNN model to extract features. Then it performs dimensionality reduction mapping based on spectral hashing with spectral rotation and clustering into meaningful clusters to improve retrieval efficiency and accuracy. Then secure encrypted searchable indexes are generated based on the modified tuples of asymmetric scalar-product preserving encryption to realize privacy protection in the retrieval process. Image encryption is performed after making space for watermark embedding through prediction error labeling and pixel rearrangement to ensure the security of image content. The process allows flexible embedding and extraction of copyright information and user information, which facilitates copyright authentication and tracing of illegally distributed data. In addition, the authenticity of the retrieval results is verified by constructing a Merkel tree. The security analysis and performance evaluation of the experiments verify the accuracy, privacy, and usability of the proposed method to achieve secure and efficient remote sensing image retrieval.

Most existing zero-watermarking algorithms for remote sensing images are designed for panchromatic or multispectral data. When applied to hyperspectral data, these methods fail to fully utilize the unique characteristics of hyperspectral images, resulting in poor robustness. This study proposes a novel zero-watermarking method specifically tailored for hyperspectral remote sensing images, leveraging both spectral and spatial features. First, principal component analysis is applied to reduce the dimensionality of the hyperspectral image, and the leading principal component is used for K-means clustering. The frequency of each category is calculated based on the clustering results, and the category frequency vector is used as the spectral feature vector. Simultaneously, Zernike moments are employed to extract spatial features, generating the spatial feature vector. These spectral and spatial feature vectors are combined to form the carrier image feature vector. Next, the watermark image is scrambled using Zigzag scanning and binarized. The mixed linear-nonlinear coupled map lattice chaotic system generates a random sequence, which is XORed with the binarized watermark sequence to produce the final binary watermark sequence. Finally, the carrier image feature vector and the binary watermark sequence are XORed to generate the zero watermark. The experimental results show that under the common attacks such as geometric attack, noise attack, filtering attack, and combination attack, the normalized correlation (NC) values of the proposed algorithm are high, all above 0.9, the values of BER are low, and the NC values of fusing spectral and spatial features are higher than that of extracting only spectral or spatial features. These results show that the proposed method effectively exploits the data characteristics of hyperspectral remote sensing images, is robust to various attacks, does not cause loss of accuracy, and is suitable for copyright protection of hyperspectral remote sensing image data.

Road information plays an essential role in many fields. To prevent failed extraction of heterogeneous regions, fracture of extracted roads and others resulted from vehicles and trees when using very high resolution remote sensing images, a remote sensing image road extraction method based on HSRoadNet is proposed in this paper. Firstly, road extraction task is divided into three correlated subtasks to reduce the impact of vehicles and trees in road extracting; Secondly, normalization layer is adopted to prevent gradient levels from vanishing and exploring and avoid fracture of the extracted road; Then, adopting Hard-Swish activation function to improve the accuracy of road extracting; In the finality, using the improved Squeeze-Excitation module to make the trained net a full use of the characteristic information of the road that do not increase excessive capacity. Comparison experimental results indicate that, in various indicators, the proposed method performs serviceably, it respectively increased by 16.8%, 2.2%, 1.5% and 8.5% over the sub-optimal in F-score, global accuracy, class average accuracy, and recall ratio. The MIou value of the proposed method was the suboptimum with a disparity of 0.2% from the optimal. Ablation experiments show that the proposed method performs best in various indexes, and the global accuracy, MIoU, class average accuracy and recall rate are im-proved by 0.5%, 0.1%, 0.5% and 0.2%, respectively, compared with the sub-optimal method. The F-score is sub-optimal, with a 0.3% difference from the best.