Search

Objectives: The green channel received by Luojia3-01 satellite in Bayer imaging mode has relatively strong signals. The camera often adopts a fixed exposure and gain setting for images containing high saturation pixel values, which comprehensively leads to the color deviation of the images with partial snow or cloud cover captured by Luojia3-01 satellite. Methods: To solve the above problems, a histogram overlapping white balance method combining color compensation and cross-correlation is proposed. First, in order to further improve the details of the image, the Gamma function is constructed through the distribution proportion of the region of low gray value to enable adaptive gamma correction processing. In order to improve the similarity of the distribution of color channels, the standard deviation of the image is used to calculate the weight to compensate for the attenuation channels, and the brightness information is maintained based on YCbCr color space to avoid the background brightness change of the image. Then, in order to improve the color deviation and maintain the overlap of the color mean, the color histogram is overlapped by using the cross-correlation relationship, and the parameters are adjusted according to the features of the images with partial snow or cloud cover. Finally, subjective analysis and objective evaluation of the corrected images are carried out. Results: The proposed method has the best processing effect in retaining the information of other ground objects except snow or cloud, and the information entropy value is the largest. The calculated value of the color correlation index obtained by processing the scene images with different amounts of snow and ice or cloud coverage also reaches the optimal value, and the color correlation is the highest compared with other methods. Other color correction methods, such as gray-world algorithm and gray-edge algorithm, are not effective, and it is difficult for other methods to achieve a balance between improving the color cast and preserving image information. Conclusions: The proposed method has better color correction effect, more natural color, and can better preserve feature information. [ABSTRACT FROM AUTHOR]

Objectives: In order to alleviate the pressure of satellite image data transmission between satellite and ground, the Bayer imaging mode is increasingly being used in remote sensing satellite imaging systems. The information loss occurs because each pixel in the Bayer image only stores information from one color channel. Therefore, a full-color image must be reconstructed by Bayer interpolation for subsequent applications. However, the existing interpolation methods suffer from false colors at image details and overall color tone shift issues. Methods: In response to the above issues, this article proposes a Bayer interpolation method by integrating color-difference gradient and color correlation. First, the proposed method extracts the color difference gradient information between each channel of the original Bayer image, and uses a normalized color difference gradient function to assign corresponding weights to the estimated color difference values in each direction. The interpolation is carried out along the edge direction to protect the detail information at the edge. Then, the color ratio constraints are set according to the correlation between different color channels, and the relative proportion of the three channels in the local sliding window is adjusted to improve the color shift phenomenon in the interpolation results, which makes the reconstructed full-color image have real color tones and complete details. Results: The experimental comparison is conducted on simulated images and real Bayer images obtained from Luojia3-01 satellite, and the proposed method has significantly improved the false color problem at the edges of ground objects. Compared the comparison methods, the proposed method has the highest peak signal-to-noise ratio and structural similarity index, and the lowest mean square error and natural image quality evaluation score. Conclusions: The proposed method can effectively improve the problem of missing details at the edges of ground features and enhance the quality of reconstruction. It has been successfully applied to the data processing system of Luojia3-01 satellite to interpolate Bayer images in orbit and on the ground, providing effective guarantees for the various applications of Luojia3-01 satellite data. [ABSTRACT FROM AUTHOR]

Objectives: The conventional group sparse representation (GSR) model encounters challenges in precisely estimating the sparsity of individual image groups, because the influence of noise results in distortion in the restoration of original image group. Methods: This paper introduces a strategy denominated as the group sparse residual constraint. This strategy leverages non-local self-similarity priors to derive precise estimate of sparse coefficients for each original image group. Subsequently, the sparse coefficients of corresponding degraded image groups are constrained to approximate this estimate. Furthermore, the intricate nature of noise in area-array satellite images (e. g., Luojia3-01 satellite images), surpasses the simplicity of additive white Gaussian noise (AWGN). Consequently, conventional GSR model tailored for AWGN exhibits a reduction in efficacy when deployed in real image denoising scenarios. To address this, this paper introduces two distinct weight matrices into the data fidelity term and regularization, respectively, with the intent of characterizing the statistical features inherent in both images and noise. This paper adopts the alternating direction method of multipliers for optimizing the proposed image denoising task. Results: The effectiveness of the proposed model is validated by the experiments using simulated data and real images obtained from the Luojia3-01 satellite. In the experiments of simulated data, the proposed model outperforms other methods in removing AWGN and spatially variant noise. In the experiments of real images, the entropy of denoised images by the proposed model shows improvements of 2.03%, 1.18%, 1.26%, 1.24%, and 2.10%, compared to the block-matching and 3-D filtering method, multi-channel weighted nuclear norm minimization method, nonlocally centralized sparse representation method, low-rankness guided group sparse representation method, and trilateral weighted sparse coding method, respectively. Conclusions: The proposed method exhibits good performance in processing area-array satellite images with low signal-to-noise ratios and complex noise structures, significantly enhancing the quality of the image. By effectively reducing noise while preserving crucial details and edges, it provides a reliable solution for enhancing the usability and interpretability of area-array satellite images, particularly in challenging conditions. [ABSTRACT FROM AUTHOR]

Copyright of Geomatics & Information Science of Wuhan University is the property of Geomatics & Information Science of Wuhan University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Objectives: The distribution of buildings is an important indicator to measure regional development. Automatic extraction of building information from remote sensing images is of great significance for urban and rural planning. Most existing methods underestimate building details such as boundaries and tiny buildings. Methods: In order to increase attention to building details, a dual-stream detail-concerned network (DSDCNet) is proposed in an encoder-decoder manner. First, a dual-stream feature extraction module is used to extract semantic features and detail-concerned features. They are fed into the decoder consisting of a series of detail refinement modules where detail-concerned features make up for the missing details of semantic features and the semantic features enhance semantic continuity of detail-concerned features. Then, a semantic-detail fusion module is used to fuse and squeeze two refined features. Furthermore, deep supervision is conducted and the multi-level outputs are used in detail-concerned loss function so as to strengthen the supervision of building details. Results: Five mainstream networks are selected for comparison in WHU dataset, ISPRS Vaihingen dataset and a domestic high-resolution dataset. The evaluation results show that DSDCNet has better performance than other networks, especially in F1-score and intersection over union without introducing too much network complexity. Conclusions: DSDCNet not only manages to improve the overall performance of building extraction results, but also effectively maintains the integrity of building boundaries and reduces the missed detection of small buildings. It has better extraction effect on the buildings with small size and complex context. [ABSTRACT FROM AUTHOR]

Copyright of Geomatics & Information Science of Wuhan University is the property of Geomatics & Information Science of Wuhan University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Geomatics & Information Science of Wuhan University is the property of Geomatics & Information Science of Wuhan University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)