This paper presents a novel, compact overactuated tricopter featuring a servo-driven twisting and tilting mechanism, preventing the adverse effects of internal force contradiction during flight. Each arm’s vectored thrust is provided by a single motor, with the twisting and tilting angles controlled by two vertically mounted servos. These components are collectively mounted within a 3D-printed semi-ring structure, and are rigidly attached to the fuselage via carbon tubes at the twist end. To address the asymmetry inherent in the tricopter configuration, we conducted a qualitative analysis of the disturbances introduced by the actuators. Additionally, we emphasize the need to include gyroscopic torque effects caused by arm rotations. This issue is addressed using a control allocation method, with our proposed improved Force Decomposition (FD)-based iteration offering a low-cost computational solution. The dynamic models of the motion of rotational joints, identified and employed as virtual sensors, contribute to the estimation of the improved control effective matrix. This overactuated tricopter can operate like a conventional rotorcraft, with the added capability of achieving attitude adjustments through manual control inputs. Finally, we demonstrate the tricopter’s advantages by comparing simulations and flight experiments, both with and without the application of the improved method.

Reducing speckle while preserving complex structures in images has always been a significant challenge in processing of Synthetic Aperture Radar (SAR) images. This paper proposes a new despeckling method for dual-polarimetric SAR images based on the conditional diffusion model. By explicitly learning specific distributions from the training data, this method better restores the image structures. To support this research, a VV-VH dual-polarimetric dataset is constructed using multitemporal fusion techniques with data obtained from the Sentinel-1 satellite. The proposed method is compared with five other SAR despeckling methods. The results show that this method performs better in preserving image details and effectively removing speckle. Furthermore, this paper introduces a new sampling method for SAR despeckling. Compared to the two existing methods, it achieves better despeckling results and superior structural preservation.

Spatiotemporal fusion aims to reconstruct sequence remote sensing images in an economically efficient way, for which we observe that the sensor and scale errors can approach the distribution of Gaussian noise. To model the random noise, a spatiotemporal fusion method based on a conditional diffusion model is proposed. A new encoder-decoder network is designed to fuse multi-source images. The new model learns the noise distribution at the forward diffusion stage, and employs an iterative removal of the noise at the backward diffusion stage, which enhances the model against the Gaussian noise. The proposed method is evaluated on two datasets and compared with seven state-of-the-art algorithms, in which the average root mean square errors decrease from 0.0198 to 0.0188 for Landsat-7 and from 0.0155 to 0.0141 for Landsat-5, respectively. The experimental results also demonstrate that the proposed method can preserve clearer details and adapt better for abrupt phenological changes.

Satellite images of synthetic aperture radar (SAR) sensors are contaminated by speckles from the coherent imaging mechanism. Although removing or mitigating speckle has been a critical issue for SAR applications, effective reduction continues to be a significant challenge for existing methods when preserving the intricate structures within SAR images. To address this issue, this work proposes a novel conditional diffusion model for SAR despeckling (DiffusionSAR). The new method explicitly learns data distributions by forward diffusion toward multiplicative gamma noise. The logarithmic and Yeo–Johnson (log-Yeo–Johnson) transformation are harnessed in preprocessing for fine-tuning or hybrid training. A prolonging steps technique is suggested in fine-tuning to match the preprocessing. A new synthetic dataset is designed for satellite SAR despeckling. The proposed method is compared with eight state-of-the-art methods using both synthetic and real-world SAR satellite images. The qualitative and quantitative evaluations confirm the effectiveness of the proposed method in structural preservation as well as noise reduction. A fine-tuning experiment using stacked multitemporal data shows the necessity of tine-tuning training in bridging the domain gap when trained with synthetic data and tested with real-world SAR data.

Due to parallax and inadequate key points, it is difficult to stitch unmanned aerial vehicle (UAV) images that are not rich in structure, which is addressed in this letter. Global matching is judged along with local similarity by a trained transformer, which provides the possibility of finding plenty of key points in low-feature regions. A new point matching constraint is designed based on the scores from the transformer. Line protection and distortion resistance are also used in local correction to alleviate global aberrations. The experiment shows that our method outperforms four state-of-the-art algorithms significantly, which reduces the position error by half in stitching inconspicuous features, such as woodland, bare land, and river.

Remote sensing images of different moments or sensors can be stitched together to produce a new image under uniform geographic coordinate systems, where the overlapping areas were needed for color harmony. In this letter, a reference-based mosaicking method is proposed for images either with or without overlapping areas. The new method introduces a low-resolution image for spectral reference that spans all the mosaicking scope. A generative adversarial network is harnessed for color harmony, which transfers all the mosaicking images to the time of the reference image for further stitch with the graph cut and pyramid gradient methods. The proposed method is compared with three color harmony methods or tools by mosaicking the red, green, and blue bands of Landsat-8 images with MODIS as the reference. The digital evaluations demonstrate that the new method outweighs other methods regarding radiometric and spectral fidelity.

Due to the limitations of hardware technology, satellite sensors cannot obtain images with high temporal, spatial, and spectral resolutions at the same time. Current spatiotemporal fusion methods try to solve the contradiction between temporal resolution and spatial resolution, which cannot achieve good reconstruction accuracy partly because the data sources are from heterogeneous platforms with long chains difficult to be modeled. Different from the crossing-platform fusion, this work proposes to improve the spatial and temporal resolutions on a single platform. For the 2-m panchromatic images, 8-m multispectral images, and 16-m wide-field-view images captured by the Gaofen-1 satellite, our goal is to produce 2-m multispectral images with high temporal resolutions. Two convolutional neural networks are built to solve this spatiotemporal-spectral fusion issue with pansharpening and spatiotemporal fusion in serial. In the validation stage, the 2-m multispectral images are built and evaluated with the panchromatic images and 8-m multispectral images. The digital and visual evaluations show that our method can produce visually acceptable fusion quality, which may enhance the feasibility of the Gaofen-1 data.

Existing point cloud registration models suffer from large performance loss in low overlap scenarios, while the generalization ability of most models are weak. In this paper, we design a new model for point cloud registration pursing better low-overlap performance and generalization ability. On the one hand, to solve the registration problem in low-overlap scenes, we propose a novel full convolutional network searching for super points located in the overlapping region and generating feature descriptors at the super points simultaneously. The new network aims at extracting points beyond non-overlapping or smooth regions. On the other hand, we introduce a rotation-invariant convolution strategy for the fully convolutional model so that the extracted feature descriptors have rotation invariance, which improves the generalization performance of the features. Our method is tested on 3DMatch, 3DLoMatch, KITTI, and ETH, and compared with state-of-the-art methods. The experimental results demonstrate that our method can achieve the best performance in low-overlap registration tasks, and it performs well across unseen scenarios with different sensor modalities.

The newly emerging classifier using deep network architectures and pyramid bottleneck modules exhibits stronger capability than traditional classifiers. However, they are only suitable for color images or hyperspectral images due to the structural, textural and spectral differences against multispectral images. In this paper, a new network is designed for the classification of high-resolution multispectral images. The new network follows the architecture of pyramid residual network, but the input size, filter size, and filter number of each layer are totally different. These designs make the pyramid residual network conforming to the multispectral advantages of spatial resolutions so as to improve classification performance. Experiments on the satellite multispectral data from GF-1 and RapidEye demonstrate the superiority of the new network.

The fusion of remote sensing images with different spatial and temporal resolutions is needed for diverse Earth observation applications. A small number of spatiotemporal fusion methods that use sparse representation appear to be more promising than weighted- and unmixing-based methods in reflecting abruptly changing terrestrial content. However, none of the existing dictionary-based fusion methods consider the downsampling process explicitly, which is the degradation and sparse observation from high-resolution images to the corresponding low-resolution images. In this paper, the downsampling process is described explicitly under the framework of compressed sensing for reconstruction. With the coupled dictionary to constrain the similarity of sparse coefficients, a new dictionary-based spatiotemporal fusion method is built and named compressed sensing for spatiotemporal fusion, for the spatiotemporal fusion of remote sensing images. To deal with images with a high-resolution difference, typically Landsat-7 and Moderate Resolution Imaging Spectrometer (MODIS), the proposed model is performed twice to shorten the gap between the small block size and the large resolution rate. In the experimental procedure, the near-infrared, red, and green bands of Landsat-7 and MODIS are fused with root mean square errors to check the prediction accuracy. It can be concluded from the experiment that the proposed methods can produce higher quality than five state-of-the-art methods, which prove the feasibility of incorporating the downsampling process in the spatiotemporal model under the framework of compressed sensing.

Remote sensing image reconstruction from sparsely observed data is eagerly demanded by the onboard imaging system to cut down data volume and maintain image quality. High-order Markov random fields describe the neighborhood constraints in the statistical form that could be integrated into compressed sensing to improve the reconstruction performance of remote sensing images. To this end, we built a new energy model with high-order model of Markov random fields to reconstruct remote sensing images from sparse signals. The split Bregman method is used to solve the problem. The proposed method is tested on some multispectral satellite imageries to make clear that it outweighs state-of-the-art methods such as Orthogonal Matching Pursuit, Group-based Sparse Representation, and total variation in maintaining fidelity and high visual details.

In this paper, the blind restoration of a degraded image with an auxiliary image from another sensor is considered. In a typical multispectral satellite imaging system, multiple images from different sensors of the same area are available. When one of those images in a multiple image set is degraded, another image in the set can be used as a prior image for restoration. A hybrid algorithm based on the sparse representation using an auxiliary image is proposed in this paper. In this approach, the cost function for regularization has two terms: regularization from the degraded image being restored and the regularization from the auxiliary image. The amount of prior information from the auxiliary image to be used in the hybrid algorithm is determined based on the similarity between the auxiliary image and the degraded image. The proposed algorithm is applied to both simulated and real multispectral images, and the performance of the proposed algorithm is compared with those of other image restoration algorithms. In both quantitative and qualitative comparisons, the proposed algorithm performed better than other algorithms.

Remote sensing image reconstruction from undersampled data is very much required by the onboard imaging system to cut down data volume and maintain image quality. Nonlocal low-rank regularization deriving from group sparsity, low rank, singular-value thresholding, and nonconvex surrogate functions have recently emerged for image recovery. To use nonlocal low-rank compressed sensing for remote sensing image reconstruction, spectral and temporal redundancy are considered in this letter by utilizing the similarity of correlated bands or historical records. Prior structural knowledge helps to group nonlocal similar blocks more accurately. Oversmoothness of low-rank regularization is improved by injecting referenced structures selectively. The proposed compressed sensing method is tested on satellite images from MODIS, LandSat-7, LandSat-8, IKONOS, and Google Earth to make clear that it outweighs state-of-the-art methods in maintaining fidelity and high visual details.

SUMMARY This article is dedicated to techniques and theories of image fusion in automatic ways and addresses two issues—the parameter setting and quality assessment. Optimal parameters are in demand for specific applications or comparison between fusion methods because, as basic evidence, different parameters bring different fusion effects varying over a large range. In this paper, we propose a general framework of online parameter training to search optimal values that best suit input images. Furthermore, we optimized the compute‐intensive training process using parallelization and genetic algorithm, as well as patches extraction. We also propose a metric—spatial and spectral distortion—as the learning target. The spatial and spectral distortion is a fuzzy combination of mean potential energy measuring spatial distortion and Q4 measuring spectral distortion. Optimization validation on weighted Gram–Schmidt fusion indicated linear or superlinear acceleration ability, which proved that the proposed learning framework can speed up the learning process of image fusion to an acceptable time, and can thus be applied to high‐performance platforms to process large volumes of data. Copyright © 2013 John Wiley & Sons, Ltd.