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: 22-00051R2
A GPU-Accelerated PCG Method for the Block Adjustment of Large-Scale High-Resolution Optical Satellite Imagery Without GCPs
Qing Fu, Xiaohua Tong, Shijie Liu, Zhen Ye, Yanmin Jin, Hanyu Wang, and Zhonghua Hong
The precise geo-positioning of high-resolution satellite imagery (HRSI) without ground control points (GCPs) is an important and fundamental step in global mapping, three-dimensional modeling, and so on. In this paper, to improve the efficiency of large-scale bundle adjustment (BA), we propose a combined Preconditioned Conjugate Gradient (PCG ) and Graphic Processing Unit (GPU) parallel computing approach for the BA of large-scale HRSI without GCPs. The proposed approach consists of three main components: 1) construction of a BA model without GCPs; 2) reduction of memory consumption using the Compressed Sparse Row sparse matrix format; and 3) improvement of the computational efficiency by the use of the combined PCG and GPU parallel computing method. The experimental results showed that the proposed method: 1) consumes less memory consumption compared to the conventional full matrix format method; 2) demonstrates higher computational efficiency than the single-core, Ceres-solver and multi-core central processing unit computing methods, with 9.48, 6.82, and 3.05 times faster than the above three methods, respectively; 3) obtains comparable BA accuracy with the above three methods, with image residuals of about 0.9 pixels; and 4) is superior to the parallel bundle adjustment method in the reprojection error.
Manuscript number: 22-00111R2
Lightweight Parallel Octave Convolutional Neural Network for Hyperspectral Image Classification
Dan Li, Hanjie Wu, Yujian Wang, Xiaojun Li, Fanqiang Kong, and Qiang Wang
Although most deep learning-based methods have achieved excellent performance for hyperspectral image (HSI) classification, they are often limited by complex networks and require massive training samples in practical applications. Therefore, designing an efficient, lightweight model to obtain better classification results under small samples situations remains a challenging task. To alleviate this problem, a novel, lightweight parallel octave convolutional neural network (LPOCNN) for HSI classification is proposed in this paper. First, the HSI data is preprocessed to construct two three-dimensional (3D) patch cubes with different spatial and spectral scales for each central pixel, removing redundancy and focusing on extracting spatial features and spectral features, respectively. Next, two non-deep parallel branches are created for the two inputs, which design octave convolution rather than classical 3D convolution to facilitate light weighting of the model. Then two-dimensional convolutional neural network is used to extract deeper spectral-spatial features when fusing spectral-spatial features from different parallel layers. Moreover, the spectral-spatial attention is designed to promote the classification performance even further by adaptively adjusting the weights of different spectral-spatial features according to their contribution to classification. Experiments show that our suggested LPOCNN acquires a significant advantage on classification performance over other competitive methods under small sample situations.
Manuscript number: 22-00119R2
Model-driven precise degradation analysis method of highway marking using Mobile Laser Scanning point clouds
Ruifeng Ma, Xuming Ge, Qing Zhu, Xin Jia, Min Chen, Liu Tao
Highway markings (HMs) are representative elements of inventory digitalization in highway scenes. The accurate position, semantics, and maintenance information of HMs provide significant support for the intelligent management of highways. This article presents a robust and efficient approach for extracting, reconstructing, and degrading analyzing HMs in complex highway scenes. Compared with existing road marking extraction methods, not only can extract HMs in presence of wear and occlusion from point clouds, but we also perform a degradation analysis for HMs. First, the HMs candidate area is determined accurately by sophisticated image processing. Second, the prior knowledge of marking design rules and edge-based matching model that leverages the standard geometric template and radiometric appearance of HMs is used for accurately extracting and reconstructing solid lines and nonsolid markings of HMs, respectively. Finally, two degradation indicators are constructed to describe the completeness of the marking contour and consistency within the marking. Comprehensive experiments on two existing highways revealed that the proposed methods achieved an overall performance of 95.4% and 95.4% in the recall and 93.8% and 95.5% in the precision for solid line and nonsolid line markings, respectively, even with imperfect data. Meanwhile, a database can be established to facilitate agencies’ efficient maintenance.
Manuscript number: 22-00092R2
Identification of Drought Events in Major Basins of Africa from GRACE Total Water Storage and Modeled Products
Ayman M. Elameen, Shuanggen Jin, and Daniel Olago
Terrestrial water storage (TWS) plays a vital role in climatological and hydrological processes. Most of the developed drought indices from the Gravity Recovery and Climate Experiment (GRACE) over Africa neglected the influencing roles of individual water storage components in calculating the drought index and thus may either underestimate or overestimate drought characteristics. In this paper, we proposed a Weighted Water Storage Deficit Index for drought assessment over the major river basins in Africa (i.e., Nile, Congo, Niger, Zambezi, and Orange) with accounting for the contribution of each TWS component on the drought signal. We coupled the GRACE data and WaterGAP Global Hydrology Model through utilizing the component contribution ratio as the weight. The results showed that water storage components demonstrated distinctly different contributions to TWS variability and thus drought signal response in onset and duration. The most severe droughts over the Nile, Congo, Niger, Zambezi, and Orange occurred in 2006, 2012, 2006, 2006, and 2003, respectively. The most prolonged drought of 84 months was observed over the Niger basin. This study suggests that considering the weight of individual components in the drought index provides more reasonable and realistic drought estimates over large basins in Africa from GRACE.
Manuscript number: 22-00112R2
Spherical Hough Transform for Robust Line Detection toward a 2D-3D Integrated Mobile Mapping System
Bo Xu, Daiwei Zhang, Han Hu, Qing Zhu, Qiang Wang, Xuming Ge, Min Chen, Yan Zhou
Line features are of great importance for the registration of the Vehicle-Borne Mobile Mapping System that contains both lidar and multiple-lens panoramic cameras. In this work, a spherical straight-line model is proposed to detect the unified line features in the panoramic imaging surface based on the Spherical Hough Transform. The local topological constraints and gradient image voting are also combined to register the line features between panoramic images and lidar point clouds within the Hough parameter space. Experimental results show that the proposed method can accurately extract the long strip targets on the panoramic images and avoid spurious or broken line-segments. Meanwhile, the line matching precision between point clouds and panoramic images are also improved.
Manuscript number: 22-00113R2
Automatic Satellite Images Ortho-rectification using K-means based Cascaded Meta-heuristic Algorithm
Oussama Mezouar, Fatiha Meskine, Issam Boukerch
Orthorectification of high-resolution satellite images using a terrain-dependent rational function model (RFM) is a difficult task requiring a well-distributed set of ground control points (GCPs), which is often time-consuming and costly operation. Further, RFM is sensitive to over-parameterization due to its many coefficients, which have no physical meaning. Optimization-based meta-heuristic algorithms appear to be an efficient solution to overcome these limitations. This paper presents a complete automated RFM terrain-dependent orthorectification for satellite images. The proposed method has two parts; the first part suggests automating the GCP extraction by combing Scale-Invariant Feature Transform and Speeded Up Robust Features algorithms; and the second part introduces the cascaded meta-heuristic algorithm using genetic algorithms and particle swarm optimization. In this stage, a modified K-means clustering selection technique was used to support the proposed algorithm for finding the best combinations of GCPs and RFM coefficients. The obtained results are promising in terms of accuracy and stability compared to other literature methods.
Manuscript number: 22-00114R2
Blind and Robust Watermarking Algorithm for Remote Sensing Images Resistant to Geometric Attacks
Xinyan Pang, Na Ren, Changqing Zhu, Shuitao Guo, Ying Xiong
To address the problem of weak robustness against geometric attacks of remote sensing images’ digital watermarking, a robust watermarking algorithm based on template watermarking is pro-posed in this paper, which improves the robustness of digital watermarking against geometric at-tacks by constructing stable geometric attack invariant features. In this paper, the Discrete Fourier Transform domain template watermark is used as the invariant feature against geometric attacks, and the embedding of the cyclic watermark is used to improve the watermark robustness for re-covering the watermark synchronization relationship. To achieve blind extraction of the watermark, a parameter extraction method based on noise extraction is designed. The experimental results demonstrate that the proposed method can effectively improve the robustness of digital water-marking of remote sensing images against geometric attacks. Meanwhile, it can also resist common image processing attacks and compound attacks.