Guangliang Han

Existing remote sensing hyperspectral imaging sensors (HISs) typically capture hyperspectral images (HSIs) with relatively low spatial resolution due to the trade-off between spectral and spatial resolution. As a solution, hyperspectral pansharpening aims to improve the spatial resolution of HISs by fusing HSIs with panchromatic images (PANs). Existing hyperspectral pansharpening methods often face challenges such as inadequate fusion of spectral and spatial information, excessive GPU memory usage, and prolonged inference times. To address these issues, we propose HyperESSANet, an end-to-end network for efficient hyperspectral pansharpening. Specifically, HyperESSANet consists of the gated channel attention block (GCA-Block) encoder, the efficient spatialspectral attention network (ESSA-Net), and the convolutional block (Conv Block) decoder. The GCA-Block encoder introduced a novel gated channel attention module, which allows the encoder to focus better on important spectral features. The ESSA-Net is a novel spatial-spectral attention network with a weight-shared downsampling strategy, which promotes cross-scale fusion of deep spatial-spectral features. The Conv Block decoder is utilized to effectively reconstruct the high-resolution HSI. Furthermore, the ESSA-Net is integrated between the encoder and the decoder, allowing the network to dynamically fuse spatial and spectral information across multiple scales. Experimental results on public HSI datasets show that the proposed HyperESSANet outperforms existing methods in both image quality and memory efficiency. The proposed HyperESSANet is implemented in PyTorch and will be available at https: //github.com/Anywayany/HyperESSAN.

Addressing the common issues of low brightness, poor contrast, and blurred details in images captured under conditions such as night, backlight, and adverse weather, we propose a zero-reference dual-path network based on multi-scale depth curve estimation for low-light image enhancement. Utilizing a no-reference loss function, the enhancement of low-light images is converted into depth curve estimation, with three curves fitted to enhance the dark details of the image: a brightness adjustment curve (LE-curve), a contrast enhancement curve (CE-curve), and a multi-scale feature fusion curve (MF-curve). Initially, we introduce the TCE-L and TCE-C modules to improve image brightness and enhance image contrast, respectively. Subsequently, we design a multi-scale feature fusion (MFF) module that integrates the original and enhanced images at multiple scales in the HSV color space based on the brightness distribution characteristics of low-light images, yielding an optimally enhanced image that avoids overexposure and color distortion. We compare our proposed method against ten other advanced algorithms based on multiple datasets, including LOL, DICM, MEF, NPE, and ExDark, that encompass complex illumination variations. Experimental results demonstrate that the proposed algorithm adapts better to the characteristics of images captured in low-light environments, producing enhanced images with sharp contrast, rich details, and preserved color authenticity, while effectively mitigating the issue of overexposure.

Point cloud registration is a critical problem because it is the basis of many 3D vision tasks. With the popularity of deep learning, many scholars have focused on leveraging deep neural networks to address the point cloud registration problem. However, many of these methods are still sensitive to partial overlap and differences in density distribution. For this reason, herein, we propose a method based on rotation-invariant features and using a sparse-to-dense matching strategy for robust point cloud registration. Firstly, we encode raw points as superpoints with a network combining KPConv and FPN, and their associated features are extracted. Then point pair features of these superpoints are computed and embedded into the transformer to learn the hybrid features, which makes the approach invariant to rigid transformation. Subsequently, a sparse-to-dense matching strategy is designed to address the registration problem. The correspondences of superpoints are obtained via sparse matching and then propagated to local dense points and, further, to global dense points, the byproduct of which is a series of transformation parameters. Finally, the enhanced features based on spatial consistency are repeatedly fed into the sparse-to-dense matching module to rebuild reliable correspondence, and the optimal transformation parameter is re-estimated for final alignment. Our experiments show that, with the proposed method, the inlier ratio and registration recall are effectively improved, and the performance is better than that of other point cloud registration methods on 3DMatch and ModelNet40.

Visual object tracking is a key technology that is used in unmanned aerial vehicles (UAVs) to achieve autonomous navigation. In recent years, with the rapid development of deep learning, tracking algorithms based on Siamese neural networks have received widespread attention. However, because of complex and diverse tracking scenarios, as well as limited computational resources, most existing tracking algorithms struggle to ensure real-time stable operation while improving tracking performance. Therefore, studying efficient and fast-tracking frameworks, and enhancing the ability of algorithms to respond to complex scenarios has become crucial. Therefore, this paper proposes a cross-parallel attention and efficient match transformer for aerial tracking (SiamEMT). Firstly, we carefully designed the cross-parallel attention mechanism to encode global feature information and to achieve cross-dimensional interaction and feature correlation aggregation via parallel branches, highlighting feature saliency and reducing global redundancy information, as well as improving the tracking algorithm’s ability to distinguish between targets and backgrounds. Meanwhile, we implemented an efficient match transformer to achieve feature matching. This network utilizes parallel, lightweight, multi-head attention mechanisms to pass template information to the search region features, better matching the global similarity between the template and search regions, and improving the algorithm’s ability to perceive target location and feature information. Experiments on multiple drone public benchmark tests verified the accuracy and robustness of the proposed tracker in drone tracking scenarios. In addition, on the embedded artificial intelligence (AI) platform AGX Xavier, our algorithm achieved real-time tracking speed, indicating that our algorithm can be effectively applied to UAV tracking scenarios.

A hyperspectral image (HSI) has a very high spectral resolution, which can reflect the target’s material properties well. However, the limited spatial resolution poses a constraint on its applicability. In recent years, some hyperspectral pansharpening studies have attempted to integrate HSI with PAN to improve the spatial resolution of HSI. Although some achievements have been made, there are still shortcomings, such as insufficient utilization of multi-scale spatial and spectral information, high computational complexity, and long network model inference time. To address the above issues, we propose a novel U-shaped hyperspectral pansharpening network with channel cross-concatenation and spatial–spectral attention mechanism (CCC-SSA-UNet). A novel channel cross-concatenation (CCC) method was designed to effectively enhance the fusion ability of different input source images and the fusion ability between feature maps at different levels. Regarding network design, integrating a UNet based on an encoder–decoder architecture with a spatial–spectral attention network (SSA-Net) based on residual spatial–spectral attention (Res-SSA) blocks further enhances the ability to extract spatial and spectral features. The experiment shows that our proposed CCC-SSA-UNet exhibits state-of-the-art performance and has a shorter inference runtime and lower GPU memory consumption than most of the existing hyperspectral pansharpening methods.

UAV visual-object-tracking technology based on Siamese neural networks has great scientific research and practical application value, and it is widely used in geological surveying, reconnaissance monitoring, and environmental monitoring. Due to the limited onboard computational resources and complex real-world environments of drones, most of the existing tracking systems based on Siamese neural networks struggle to combine excellent performance with high efficiency. Therefore, the key issue is to study how to improve the accuracy of target tracking under the challenges of real-time performance and the above factors. In response to this problem, this paper proposes a real-time UAV tracking system based on interframe saliency transformer and lightweight multidimensional attention network (SiamITL). Specifically, interframe saliency transformer is used to continuously perceive spatial and temporal information, making the network more closely related to the essence of the tracking task. Additionally, a lightweight multidimensional attention network is used to better capture changes in both target appearance and background information, improving the ability of the tracker to distinguish between the target and background. SiamITL is effective and efficient: extensive comparative experiments and ablation experiments have been conducted on multiple aerial tracking benchmarks, demonstrating that our algorithm can achieve more robust feature representation and more accurate target state estimation. Among them, SiamITL achieved success and accuracy rates of 0.625 and 0.818 in the UAV123 benchmark, respectively, demonstrating a certain level of leadership in this field. Furthermore, SiamITL demonstrates the potential for real-time operation on the embedded platform Xavier, highlighting its potential for practical application in real-world scenarios.

Based on the versatility and effectiveness of the siamese neural network, the technology of unmanned aerial vehicle visual object tracking has found widespread application in various fields including military reconnaissance, intelligent transportation, and visual positioning. However, due to complex factors, such as occlusions, viewpoint changes, and interference from similar objects during UAV tracking, most existing siamese neural network trackers struggle to combine superior performance with efficiency. To tackle this challenge, this paper proposes a novel SiamSTM tracker that is based on Slight Aware Enhancement Transformer and Multiple matching networks for real-time UAV tracking. The SiamSTM leverages lightweight transformers to encode robust target appearance features while using the Multiple matching networks to fully perceive response map information and enhance the tracker’s ability to distinguish between the target and background. The results are impressive: evaluation results based on three UAV tracking benchmarks showed superior speed and precision. Moreover, SiamSTM achieves over 35 FPS on NVIDIA Jetson AGX Xavier, which satisfies the real-time requirements in engineering.

Convolutional neural networks (CNNs) have demonstrated impressive performance and have been broadly applied in hyperspectral image (HSI) classification. However, two challenging problems still exist: the first challenge is that redundant information is averse to feature learning, which damages the classification performance; the second challenge is that most of the existing classification methods only focus on single-scale feature extraction, resulting in underutilization of information. To resolve the two preceding issues, this article proposes a multiscale cross interaction attention network (MCIANet) for HSI classification. First, an interaction attention module (IAM) is designed to highlight the distinguishability of HSI and dispel redundant information. Then, a multiscale cross feature extraction module (MCFEM) is constructed to detect spectral–spatial features at different scales, convolutional layers, and branches, which can increase the diversity of spectral–spatial features. Finally, we introduce global average pooling to compress multiscale spectral–spatial features and utilize two fully connection layers, two dropout layers to obtain the output classification results. Massive experiments on three benchmark datasets demonstrate the superiority of our presented method compared with the state-of-the-art methods.

Recently, hyperspectral image (HSI) classification methods based on convolutional neural networks (CNN) have shown impressive performance. However, HSI classification still faces two challenging problems: the first challenge is that most existing classification approaches only focus on exploiting the fixed-scale convolutional kernels to extract spectral–spatial features, which leads to underutilization of information; the second challenge is that HSI contains a large amount of redundant information and noise, to a certain extent, which influences the classification performance of CNN. In order to tackle the above problems, this article proposes a multibranch crossover feature attention network (MCFANet) for HSI classification. The MCFANet involves two primary submodules: a cross feature extraction module (CFEM) and rearranged attention module (RAM). The former is devised to capture joint spectral–spatial features at different convolutional layers, scales and branches, which can increase the diversity and complementarity of spectral–spatial features, while the latter is constructed to spontaneously concentrate on recalibrating spatial-wise and spectral-wise feature responses, meanwhile exploit the shifted cascade operation to rearrange the obtained attention-enhanced features to dispel redundant information and noise, and thus, boost the classification performance. Compared with the state-of-the-art classification methods, massive experiments on four benchmark datasets demonstrate the meliority of our presented method.