Search

Instance segmentation of remote sensing images can not only provide object-level positioning information but also provide pixel-level positioning information. This pixel-level information annotation has a wide range of uses in the field of remote sensing, and it is of great value for environmental detection and resource management. Because optical images generally have complex terrain environments and changeable object shapes, SAR images are affected by complex scattering phenomena, and the mask quality obtained by the traditional instance segmentation method used in remote sensing images is not high. Therefore, it is a challenging task to improve the mask quality of instance segmentation in remote sensing images. Since the traditional two-stage instance segmentation method consists of backbone, neck, bbox head, and mask head, the final mask quality depends on the product of all front-end work quality. Therefore, we consider the difficulty of optical and SAR images to bring instance segmentation to the targeted improvement of the neck, bbox head, and mask head, and we propose the Context-Aggregated and SAM-Guided Network (CSNet). In this network, the plain feature fusion pyramid network (PFFPN) can generate a pyramid for the plain feature and provide a feature map of the appropriate instance scale for detection and segmentation. The network also includes a context aggregation bbox head (CABH), which uses the context information and instance information around the instance to solve the problem of missed detection and false detection in detection. The network also has a SAM-Guided mask head (SGMH), which learns by using SAM as a teacher, and uses the knowledge learned to improve the edge of the mask. Experimental results show that CSNet significantly improves the quality of masks generated under optical and SAR images, and CSNet achieves 5.1% and 3.2% AP increments compared with other SOTA models. [ABSTRACT FROM AUTHOR]

In the mosaic creation of multiple high-resolution synthetic aperture radar (SAR) images, achieving an optimal seamline in overlapping areas is crucial for seamless and visually satisfactory results. Many existing seamline generation methods are designed primarily for optical remote sensing images, but due to the differing characteristics of SAR images and optical images, applying these methods directly to SAR images poses challenges in finding the optimal seamline. In response, this paper proposes a segmentation-based optimal seamline generation (SOSG) method for SAR image mosaics. The SOSG method involves a multi-step process. First, SAR image joint segmentation is performed within the overlapping areas. Subsequently, homogeneous areas are identified based on the segmentation results. Following this, a pixel cost matrix is constructed, incorporating homogeneous areas and intensity differences. Finally, the minimum path cost from the starting pixel to the end pixel is computed using the Dijkstra algorithm to determine the optimal path. To assess the feasibility and effectiveness of the proposed method, experiments are conducted using multiple SAR images from the Chinese Gaofen-3 01 satellite as datasets. The experimental results demonstrate that the proposed method yields seamless mosaic images when compared to other methods, while delivering satisfactory outcomes. This indicates the potential of the proposed method in addressing the unique challenges posed by SAR images and enhancing the quality of SAR image mosaics. [ABSTRACT FROM AUTHOR]

Synthetic Aperture Radar (SAR) satellite image ortho-rectification requires pixel-level calculations, which are time-consuming. Moreover, for SAR images with large overlapping areas, the processing time for ortho-rectification increases linearly, significantly reducing the efficiency of SAR satellite image mosaic. This paper thoroughly analyzes two geometric positioning models for SAR images. In order to address the high computation time of pixel-by-pixel ortho-rectification in SAR satellite images, a GPU-accelerated pixel-by-pixel correction method based on a rational polynomial coefficients (RPCs) model is proposed, which improves the efficiency of SAR satellite image ortho-rectification. Furthermore, in order to solve the problem of linearly increasing processing time for the ortho-rectification of multiple SAR images in large overlapping areas, a multi-GPU collaborative acceleration strategy for the ortho-rectification of multiple SAR images in large overlapping areas is proposed, achieving efficient ortho-rectification processing of multiple SAR image data in large overlapping areas. By conducting ortho-rectification experiments on 20 high-resolution SAR images from the Gaofen-3 satellite, the feasibility and efficiency of the multi-GPU collaborative acceleration processing algorithm are verified. [ABSTRACT FROM AUTHOR]

The unique imaging modality of synthetic aperture radar (SAR) has posed significant challenges for object detection, making it more complex to acquire and interpret than optical images. Recently, numerous studies have proposed cross-domain adaptive methods based on convolutional neural networks (CNNs) to promote SAR object detection using optical data. However, existing cross-domain methods focus on image features, lack improvement on input data, and ignore the valuable supervision provided by few labeled SAR images. Therefore, we propose a semi-supervised cross-domain object detection framework that uses optical data and few SAR data to achieve knowledge transfer for SAR object detection. Our method focuses on the data processing aspects to gradually reduce the domain shift at the image, instance, and feature levels. First, we propose a data augmentation method of image mixing and instance swapping to generate a mixed domain that is more similar to the SAR domain. This method fully utilizes few SAR annotation information to reduce domain shift at image and instance levels. Second, at the feature level, we propose an adaptive optimization strategy to filter out mixed domain samples that significantly deviate from the SAR feature distribution to train feature extractor. In addition, we employ Vision Transformer (ViT) as feature extractor to handle the global feature extraction of mixed images. We propose a detection head based on normalized Wasserstein distance (NWD) to enhance objects with smaller effective regions in SAR images. The effectiveness of our proposed method is evaluated on public SAR ship and oil tank datasets. [ABSTRACT FROM AUTHOR]

With the emergence of the Smart City concept, the rapid advancement of urban three-dimensional (3D) reconstruction becomes imperative. While current developments in the field of 3D reconstruction have enabled the generation of 3D products such as Digital Surface Models (DSM), challenges persist in accurately reconstructing shadows, handling occlusions, and addressing low-texture areas in very-high-resolution remote sensing images. These challenges often lead to difficulties in calculating satisfactory disparity maps using existing stereo matching methods, thereby reducing the accuracy of 3D reconstruction. This issue is particularly pronounced in urban scenes, which contain numerous super high-rise and densely distributed buildings, resulting in large disparity values and occluded regions in stereo image pairs, and further leading to a large number of mismatched points in the obtained disparity map. In response to these challenges, this paper proposes a method to refine the disparity in urban scenes based on open-source GIS data. First, we register the GIS data with the epipolar-rectified images since there always exists unignorable geolocation errors between them. Specifically, buildings with different heights present different offsets in GIS data registering; thus, we perform multi-modal matching for each building and merge them into the final building mask. Subsequently, a two-layer optimization process is applied to the initial disparity map based on the building mask, encompassing both global and local optimization. Finally, we perform a post-correction on the building facades to obtain the final refined disparity map that can be employed for high-precision 3D reconstruction. Experimental results on SuperView-1, GaoFen-7, and GeoEye satellite images show that the proposed method has the ability to correct the occluded and mismatched areas in the initial disparity map generated by both hand-crafted and deep-learning stereo matching methods. The DSM generated by the refined disparity reduces the average height error from 2.2 m to 1.6 m, which demonstrates superior performance compared with other disparity refinement methods. Furthermore, the proposed method is able to improve the integrity of the target structure and present steeper building facades and complete roofs, which are conducive to subsequent 3D model generation. [ABSTRACT FROM AUTHOR]

Remote sensing image registration is one of the crucial steps in remote sensing image processing, where ground control information is essential. Maintenance of control point databases is complex and expensive. Consequently, lightweight feature databases are emerging. Lightweight feature databases need to store stable and reproducible features. In this context, region features exhibit a distinct advantage. In feature registration methods, the reproducibility of regional features is typically stronger than with individual points. A popular feature region matching method is currently the combination of maximally stable extremal regions (MSER) and scale-invariant feature transform (SIFT). However, the direct combining of MSER and SIFT has difficulties primarily due to redundancy and overlap in regions extracted by MSER, as well as the conflict in applying texture descriptors on homogeneous regions. In this research, we first suggest a salient MSER detection approach that combines frequency-tuned salient region detection and effective nonmaximum suppression filtering to get rid of redundant information and enhance the stability and dependability of the feature region; afterward, we describe the feature region using the unique, enhanced segment distance-weighted gradient location-orientation histogram, which aims to comprehensively describe the feature regions by incorporating more information about the gradient at the edges of the regions. In the experimental phase, we validate the proposed method using multiple remote sensing images. The experimental results confirm the superiority of the proposed method and demonstrate the significant potential and advantages of feature region matching in the context of lightweight feature databases and remote sensing image registration. [ABSTRACT FROM AUTHOR]

On-board processing is increasingly prevalent due to its efficient utilization of satellite resources. Among these resources, geometric rectification can significantly enhance positioning accuracy for subsequent tasks, such as object detection. This approach mitigates the heavy burden on downlink bandwidth and minimizes time delays by transmitting targeted patches rather than raw data. However, existing rectification methods are often unsuitable due to the limitations and conditions imposed on satellites. Factors like hardware quality, heat dissipation, storage space, and geographic positioning are frequently constrained and prone to inaccuracies. This paper proposes a novel on-board rectification method. The method introduces a two-step matching framework to address substantial positioning errors and incorporates a feature-compression strategy to reduce the storage space of reference patches. Quantitative and practical experiments demonstrate the method's efficacy in terms of storage space, time efficiency, and geometric rectification accuracy. [ABSTRACT FROM AUTHOR]

Complex motion can cause serious defocusing phenomena in high resolution spaceborne SAR cases, which then lead to decreased image resolution. In this study, we built a simulation model to quantitatively analyze the signature and effect on maritime fluctuating targets in high resolution cases. To deal with formed Single-Look Complex (SLC) SAR images containing fluctuating targets, we implement a motion-compensation and fine-focusing method to obtain refocused images and the fluctuation parameters. We demonstrate the effectiveness and correctness of the proposed approach in focusing and estimating the parameters of fluctuating targets by processing the simulation results and archived images acquired by Terra-SAR in hybrid spotlight mode.

Change detection plays a crucial role in remote sensing by identifying surface modifications between two sets of temporal remote sensing images. Recent advancements in deep learning techniques have yielded significant achievements in this field. However, there are still some challenges: (1) Existing change feature fusion methods often introduce redundant information. (2) The complexity of network structures leads to a large number of parameters and difficulties in model training. To overcome these challenges, this paper proposes a Multi-Scale Feature Subtraction Fusion Network (MFSF-Net). It comprises two primary modules: the Multi-scale Feature Subtraction Fusion (MFSF) module and the Feature Deep Supervision (FDS) module. MFSF enhances change features and reduces redundant pseudo-change features. FDS provides additional supervision on different scales of change features in the decoder, improving the training efficiency performance of the network. Additionally, to address the problem of imbalanced samples, the Dice loss strategy is introduced as a means to mitigate this issue. Through comprehensive experiments, MFSF-Net achieves an F1 score of 91.15% and 95.64% on LEVIR-CD and CDD benchmark datasets, respectively, outperforming six state-of-the-art algorithms. Moreover, it attains an improved balance between model complexity and performance, showcasing the efficacy of the proposed approach. [ABSTRACT FROM AUTHOR]

Edge detection is a technique used to identify inherent structures within an image, and it is an essential requirement for synthetic aperture radar (SAR) applications. In particular, ratio-based edge detectors have been widely used in SAR image registration because of their ability to extract invariant features and reduce the effects of speckle noise. However, current edge detectors often struggle to accurately detect multiscale objects and low-contrast structures. To address this issue, we present a robust multiscale edge detector that uses a modified convolution kernel to improve the extensibility of edge features and aggregates multiscale feature responses. We also propose a local scale estimation module to enhance edge responses in low-contrast areas and reduce noise effects. The experimental results demonstrate that our proposed method effectively preserves the integrity, continuity, and robustness of multiscale and low-contrast structures. By incorporating our proposed edge detector into feature and template matching frameworks, we are able to significantly improve matching accuracy and outperform state-of-the-art SAR image registration methods. [ABSTRACT FROM AUTHOR]