In Press Peer Reviewed Articles

As a convenience to ASPRS members, in-press peer reviewed articles approved for publication in forthcoming issues of PE&RS are listed below.

Manuscript number: 24-00008R2
Development of an Automatic Feature Point Classification Method for Three-Dimensional Mapping Around Slewing and Derricking Cranes
Hisakazu Shigemori, Junichi Susaki, Mizuki Yoneda, and Marek Ososinski

Crane automation requires a three-dimensional (3D) map around cranes that should be reconstructed and updated quickly. In this study, a high-precision classification method was developed to distinguish stationary objects from moving objects in moving images captured by a monocular camera to stabilize 3D reconstruction. To develop the method, a moving image was captured while the crane was slewed with a monocular camera mounted vertically downward at the tip of the crane. The boom length and angle data were output from a control device, a controller area network. For efficient development, a simulator that imitated the environment of an actual machine was developed and used. The proposed method uses optical flow to track feature points. The classification was performed successfully, independent of derricking motion. Consequently, the proposed method contributes to stable 3D mapping around cranes in construction sites.

Manuscript number: 23-00076R2
Semantic Segmentation of Point Cloud Scene via Multi-Scale Feature Aggregation and Adaptive Fusion
Baoyun Guo, Xiaokai Sun, Cailin Li, Na Sun, Yue Wang, and Yukai Yao

Point cloud semantic segmentation is a key step in 3D scene understanding and analysis. In recent years, deep learning–based point cloud semantic segmentation methods have received extensive attention from researchers. Multi-scale neighborhood feature learning methods are suitable for inhomogeneous density point clouds, but different scale branching feature learning increases the computational complexity and makes it difficult to accurately fuse different scale features to express local information. In this study, a point cloud semantic segmentation network based on RandLA-Net with multi-scale local feature aggregation and adaptive fusion is proposed. The designed structure can reduce computational complexity and accurately express local features. The mean intersection-over-union is improved by 1.1% on the SemanticKITTI data set with an inference speed of nine frames per second, while the mean intersection-over-union is improved by 0.9% on the S3DIS data set, compared with RandLA-Net. We also conduct ablation studies to validate the effectiveness of the proposed key structure.

Manuscript number: 23-00086R2
A Robust Star Identification Algorithm for Resident Space Object Surveillance
Liang Wu, Pengyu Hao, Kaixuan Zhang, Qian Zhang, Ru Han, and Dekun Cao

Star identification algorithms can be applied to resident space object (RSO) surveillance, which includes a large number of stars and false stars. This paper proposes an eﬀicient, robust star identification algorithm for RSO surveillance based on a neural network. First, a feature called equal-frequency binning radial feature (EFB-RF) is proposed for guide stars, and a superficial neural network is constructed for feature classification. Then the training set is generated based on EFB-RF. Finally, the remaining stars are identified using a residual star matching method. The simulation experiment and results show that the identification rate of our algorithm can reach 99.82% under 1 pixel position noise, and it can reach 99.54% under 5% false stars. When the percentage of missing stars is 15%, it can reach 99.40%. The algorithm is verified by RSO surveillance.

Manuscript number: 24-00002R2
Wavelets for Self-Calibration of Aerial Metric Camera Systems
Jun-Fu Ye, Jaan-Rong Tsay, and Dieter Fritsch

In this paper, wavelets are applied to develop new models for the self-calibration of aerial metric camera systems. It is well known and mathematically proven that additional parameters (APs) can compensate image distortions and remaining error sources by a rigorous photogrammetric bundle-block adjustment. Thus, kernel functions based on orthogonal wavelets (e.g., asymmetric Daubechies wavelets, least asymmetric Daubechies wavelets, Battle-Lemarié wavelets, Meyer wavelets) are used to build the wavelets-based family of APs for self-calibrating digital frame cameras. These new APs are called wavelet APs. Its applications in rigorous tests are accomplished by using aerial images taken by an airborne digital mapping camera in situ and practical calibrations. The test results demonstrate that these orthogonal wavelet APs are applicable and largely avoid the risk of over-parameterization. Their external accuracy is evaluated using reliable and high precision check points in the calibration field.

Manuscript number: 24-00015R2
Attention Heat Map-Based Black-Box Local Adversarial Attack for Synthetic Aperture Radar Target Recognition
Xuanshen Wan, Wei Liu, Chaoyang Niu, and Wanjie Lu

Synthetic aperture radar (SAR) automatic target recognition (ATR) models based on deep neural networks (DNNs) are susceptible to adversarial attacks. In this study, we proposed an SAR black-box local adversarial attack algorithm named attention heat map-based black-box local adversarial attack (AH-BLAA). First, we designed an attention heat map extraction module combined with the layer-wise relevance propagation (LRP) algorithm to obtain the high concerning areas of the SAR-ATR models. Then, to generate SAR adversarial attack examples, we designed a perturbation generator module, introducing the structural dissimilarity (DSSIM) metric in the loss function to limit image distortion and the differential evolution (DE) algorithm to search for optimal perturbations. Experimental results on the MSTAR and FUSAR-Ship datasets showed that compared with existing adversarial attack algorithms, the attack success rate of the AH-BLAA algorithm increased by 0.63% to 33.59% and 1.05% to 17.65%, respectively. Moreover, the lowest perturbation ratios reached 0.23% and 0.13%, respectively.

Manuscript number: 24-00015R2
Attention Heat Map-Based Black-Box Local Adversarial Attack for Synthetic Aperture Radar Target Recognition
Xuanshen Wan, Wei Liu, Chaoyang Niu, and Wanjie Lu

Manuscript number: 24-00034R2
Exploring the Potential of the Hyperspectral Remote Sensing Data China Orbita Zhuhai-1 in Land Cover Classification
Caixia Li, Xiaoyan Xiong, Lin Wang, Yunfan Li, Jiaqi Wang, and Xiaoli Zhang

cResponding to the shortcomings of China’s civil remote sensing data in land cover classification, such as the difficulty of data acquisition and the low utilization rate, we used Landsat-8, China Orbita Zhuhai-1 hyperspectral remote sensing (OHS) data, and Landsat-8 + OHS data combined with band (red, green, and blue) and vegetation index features to classify land cover using maximum likelihood (ML), Mahalanobis distance (MD), and support vector machine (SVM). The results show that Landsat-8 + OHS data have the highest classification accuracy in SVM, with an overall accuracy of 83.52% and a kappa coefficient of 0.71, and this result is higher than that of Landsat-8 images and OHS images separately. In addition, the classification accuracy of OHS images was higher than that of Landsat-8 images. The results of the study provide a reference for the use of civil satellite remote sensing data in China.

Manuscript number: 23-00077R2
Teacher-Student Prototype Enhancement Network for a Few-Shot Remote Sensing Scene Classification
Ye Zhu, Shanying Yang, and Yang Yu

Few-shot remote sensing scene classification identifies new classes from limited labeled samples where the great challenges are intraclass diversity, interclass similarity, and limited supervision. To alleviate these problems, a teacher-student prototype enhancement network is proposed for a few-shot remote sensing scene classification. Instead of introducing an attentional mechanism in mainstream studies, a prototype enhancement module is recommended to adaptively select high-confidence query samples, which can enhance the support prototype representations to emphasize intraclass and interclass relationships. The construction of a few-shot teacher model generates more discriminative predictive representations with inputs from many labeled samples, thus providing a strong supervisory signal to the student model and encouraging the network to achieve accurate classification with a limited number of labeled samples. Extensive experiments of four public datasets, including NWPU -remote sensing image scene classification (NWPU-RESISC45), aerial image dataset (AID), UC Merced, and WHU-RS19, demonstrate that this method achieves superior competitive performance than the state-of-the-art methods on five-way, one-shot, and five-shot classifications.

Manuscript number: 24-00014R2
Morphology-Based Feature Extraction Network for Arbitrary-Oriented SAR Vehicle Detection
Ting Chen and Xiaohong Huang

In recent years, synthetic aperture radar (SAR) vehicle detection has become a research hotspot. However, algorithms using horizontal bounding boxes can lead to redundant detection areas due to the varying aspect ratio and arbitrary orientation of vehicle targets. This paper proposes a morphology-based feature extraction network (MFE-Net), which fully uses the prior shape knowledge of the vehicle targets. Specifically, we adopt rotatable bounding boxes to predict the targets, and a novel rectangular rotation-invariant coordinate convolution (RRICC) is proposed to extract the feature, which can determine more accurately the convolutional sampling location of the vehicles. The adaptive thresholding denoising module (ATDM) is designed to suppress background clutter. Furthermore, inspired by the convolutional neural networks (CNNs) and self-attention, we propose the hybrid representation enhancement module (HREM) to highlight the vehicle target features. The experiment results show that the proposed model obtains an average precision (AP) of 93.1% on the SAR vehicle detection data set (SVDD).

Manuscript number: 24-00007R2
Spatial-Spectral Middle Cross-Attention Fusion Network for Hyperspectral Image Superresolution
Xiujuan Lang, Tao Lu, Yanduo Zhang, Junjun Jiang, and Zixiang Xiong

The spatial and spectral features of hyperspectral images exhibit complementarity, and neglecting them prevents the full exploitation of useful information for superresolution. This article proposes a spatial-spectral middle cross-attention fusion network to explore the spatial-spectral structure correlation. Initially, we learn spatial and spectral features through spatial and spectral branches instead of single ones to reduce information compression. Then, a novel middle-cross attention fusion block that includes middle features fusion strategy and cross-attention is proposed to fuse spatial-spectral features to enhance their mutual effects, which aims to explore the spatial-spectral structural correlations. Finally, we propose a spectral feature compensation mechanism to provide complementary information for adjacent band groups. The experimental results show that the proposed method outperforms state-of-the-art algorithms in object values and visual quality.

Manuscript number: 24-00026R2
Machine Learning and New-Generation Spaceborne Hyperspectral Data Advance Crop Type Mapping
Itiya Aneece, Prasad S. Thenkabail, Richard McCormick, Haireti Alifu, Daniel Foley, Adam J. Oliphant, Pardhasaradhi Teluguntla

Hyperspectral sensors provide near-continuous spectral data that can facilitate advancements in agricultural crop classification and characterization, which are important for addressing global food and water security issues. We investigated two new-generation hyperspectral sensors, Germany’s Deutsches Zentrum für Luft- und Raumfahrt Earth Sensing Imaging Spectrometer (DESIS) and Italy’s PRecursore IperSpettrale della Missione Applicativa (PRISMA), within California’s Central Valley in August 2021 focusing on five irrigated agricultural crops (alfalfa, almonds, corn, grapes, and pistachios). With reference data from the U.S. Department of Agriculture Cropland Data Layer, we developed a spectral library of the crops and classified them using three machine learning algorithms (support vector machines [SVMs], random forest [RF], and spectral angle mapper [SAM]) and two philosophies: 1. Full spectral analysis (FSA) and 2. Optimal hyperspectral narrowband (OHNB) analysis. For FSA, we used 59 DESIS four-bin product bands and 207 of 238 PRISMA bands. For OHNB analysis, 9 DESIS and 16 PRISMA nonredundant OHNBs for studying crops were selected. FSA achieved only 1% to 3% higher accuracies relative to OHNB analysis in most cases. SVM provided the best results, closely followed by RF. Using both DESIS and PRISMA image OHNBs in SVM for classification led to higher accuracy than using either image alone, with an overall accuracy of 99%, producer’s accuracies of 9% to 100%, and user’s accuracies of 95% to 100%.

Manuscript number: 24-00038R2
A Variable-Iterative Fully Convolutional Neural Network for Sparse Unmixing
Fanqiang Kong, Zhijie Lv, Kun Wang, Xu Fang, Yuhan Zheng, and Shengjie Yu

Neural networks have greatly promoted the development of hyperspectral unmixing (HU). Most data-driven deep networks extract features of hyperspectral images (HSIs) by stacking convolutional layers to achieve endmember extraction and abundance estimation. Some model-driven networks have strong interpretability but fail to mine the deep feature. We propose a variable-iterative fully convolutional neural network (VIFCNN) for sparse unmixing, combining the characteristics of these two networks. Under the model-driven iterative framework guided by sparse unmixing by variable splitting and augmented lagrangian (SUnSAL), a data-driven spatial-spectral feature learning module and a spatial information updating module are introduced to enhance the learning of data information. Experimental results on synthetic and real datasets show that VIFCNN significantly outperforms several traditional unmixing methods and two deep learning–based methods. On real datasets, our method improves signal-to-reconstruction error by 17.38%, reduces abundance root-mean-square error by 25.24%, and reduces abundance spectral angle distance by 31.40% compared with U-ADMM-BUNet.