2024

• Record 313 of
  
  Title:A reversible data hiding method based on bitmap prediction for AMBTC compressed hyperspectral images
  
  Author(s):Zhang, Xiaoran(1,2); Pan, Zhibin(2,5); Zhou, Quan(3); Fan, Guojun(2); Dong, Jing(4)
  Source: Journal of Information Security and Applications  Volume: 81  Issue:   DOI: 10.1016/j.jisa.2023.103697  Published: March 2024  
  Abstract:In the transmission of hyperspectral images that have been compressed using absolute moment block truncation coding (AMBTC), confidentiality and security of crucial information is often a concern. Although many data hiding (DH) methods based on AMBTC work well in guaranteeing a large amount of secret information can be embedded, the requirements of actual user scenarios, such as reversibility and imperceptibility, are degraded sometimes. To address these challenges, we propose an embedding pattern that utilizes bitmap prediction to embed secret information within the bitmaps while preserving the standard format of AMBTC codes and enabling recovery of the cover image without loss. Our proposed method, therefore, belongs to the category of reversible data hiding (RDH) techniques. Since the embedding distortion (ED) reduction is an essential object, an adaptive embedding order based on the features of AMBTC codes is conducted. Furthermore, we propose a dynamical embedding scheme to reduce ED when we are striving to achieve a larger embedding capacity (EC). © 2024 Elsevier Ltd
  Accession Number: 20240315396843
• Record 314 of
  
  Title:Bit Error Rate Performance Study of UWOC System Based on Multiple Degenerate Composite Channels
  
  Author(s):Zhang, Jianlei(1); Zhang, Pengwei(1); Zhu, Yunzhou(2); Tian, Yuxin(1); Li, Jieyu(1); Yang, Yi(1); He, Fengtao(1)
  Source: Guangzi Xuebao/Acta Photonica Sinica  Volume: 53  Issue: 3  DOI: 10.3788/gzxb20245303.0301002  Published: March 2024  
  Abstract:Underwater Wireless Optical Communication (UWOC) capitalizes on the blue-green segment of the light spectrum which is subject to minimal attenuation in marine environments, thereby rendering it optimal for the conveyance of information. The advantages of UWOC are manifold, it boasts of swift data transmission, negligible latency, and fortified confidentiality. However, UWOC grapples with significant barriers which encompass the limitation of transmission range and the deleterious effects attributable to the intrinsic properties of seawater, as well as marine turbulence-factors like absorption, scattering, bubbles and turbulence that collectively compromise communicative efficiency. To systematically confront these impediments and to gauge the comprehensive influence of the aforementioned factors on UWOC system efficacy, this inquiry has formulated an integrative underwater wireless optical channel model. This archetype not only encapsulates solitary influences but also their concomitant interactions and aggregate impact on signal transmission. By harnessing the Mie scattering theorem, the research meticulously delineates the volume scattering function, the scattering coefficient, and the phase function of microbubble assemblages in seawater—pivotal determinants essential for the assessment of scattering phenomena on the propagation of optical signals. Addressing turbulence, an elaborate channel model featuring a mixed exponential generalized Gamma distribution is employed, defining the statistical behavior of turbulence to faithfully represent the stochastic and unpredictable nature of the channel. This study extends its analysis to include the repercussion of signal attenuation and acoustic noise as a consequence of turbulence, effectively projecting these perturbations onto the optical signals disseminated through the composite channel. Importantly, it elucidates a closed-form expression for the Bit Error Ratio (BER) within the composite channel, employing On-Off Keying (OOK) modulation, thus establishing a theoretical groundwork for the analysis of UWOC system performance. The research delves into the impact of critical determinants such as turbulence strength, bubble density, transmission range, and marine water quality on the BER metrics of UWOC systems. It is discerned that heightened turbulence intensity incrementally necessitates a greater minimum Signal to Noise Ratio (SNR) at the receiver end to maintain a predetermined average BER. Consistent with this SNR, an augmentation in turbulence intensity conspicuously degrades system throughput, inducing a systematic deterioration in BER performance. Within a transparent seawater milieu at a transmission span of 20 m, with a bubble concentration of 3 × 106 per cubic volume, the system′s mean BER is recorded at 4.57 × 10-4. As the bubble density escalates to 9 × 106 and subsequently to 9 × 107 per cubic volume, the average BER correspondingly declines to 5.76 × 10-4 and 1.19 × 10-2. In scenarios of turbulence characterized by a scintillation index of 1.932 8, the system is adept at sustaining low BER transmissions. Ensuring dependable communication quality with an average BER falling below 10-3 across an array of aquatic environments—be it crystalline seawater, littoral waters, or murky harbor waters—the utmost permissible transmission distances with bubble presence(at a density of 1 × 107 per cubic volume)are confined to 22.5 m, 10.4 m, and 2.3 m respectively. Absent bubble interference, these distances are extendable to 28.0 m, 13.5 m, and 2.7 m. Given the pronounced absorption and scattering induced by elevated turbidity and suspended particulates, securing long-range communication in silt-laden harbor waters presents a significant hurdle. Additionally, the study substantiates that elevating the link distance precipitates an almost linear augmentation in BER, indicative of a noteworthy degeneration in signal integrity. The outcomes not only underscore the exigency of crafting and fine-tuning UWOC systems attuned to the vicissitudes of the oceanic realm but also accentuate the latent efficacy of modulation methodologies and channel coding strategies as instrumental in amplifying system competence. © 2024 Chinese Optical Society. All rights reserved.
  Accession Number: 20241215775065
• Record 315 of
  
  Title:Optical design of a visible/short-wave infrared common-aperture optical system with a long focal length and a wide field-of-view
  
  Author(s):Yan, Aqi(1,2); Chen, Weining(1,2); Li, Qianxi(1,3); Guo, Min(1); Wang, Hao(1,2)
  Source: Applied Optics  Volume: 63  Issue: 9  DOI: 10.1364/AO.517643  Published: February 20, 2024  
  Abstract:Addressing the urgent need for long-distance dim target detection with a wide field-of-view and high sensitivity, this paper proposes a visible and short-infrared dual-band common-aperture optical system characterized by a broad field and extended focal length. To achieve system miniaturization and high-sensitivity target detection, the visible and infrared optical systems share a Ritchey-Chretien primary and secondary mirror. The primary optical path is segmented into visible light (0.45–0.75 µm) and short-wave infrared (SWIR) (2–3 µm) bands by a dichroic spectral splitter prism. The SWIR optical system utilizes four short-wave cooled infrared detectors, and wide-field stitching is achieved using a field-of-view divider. While ensuring the high cold-shield efficiency of cooled infrared detectors, this common-aperture optical system delivers visible and SWIR dual-band images with expansive fields, elongated focal lengths, and sizable apertures. The visible-light optical system has a focal length of 277 mm, a field-of-view of 2.3◦ × 2.3◦, and an entrance pupil diameter of 130 mm. Meanwhile, the SWIR optical system features a focal length of 480 mm, a field-of-view of 2.26◦ × 1.8◦ and an entrance pupil diameter of 160 mm. The design outcomes suggest that the imaging quality of the optical system approaches the diffraction limit. This visible/SWIR common-aperture optical system exhibits high sensitivity, a large field-of-view, compact structure, and excellent imaging quality, thereby meeting the requirements for long-distance dim target detection and imaging. © 2024 Optica Publishing Group.
  Accession Number: 20241315795896
• Record 316 of
  
  Title:Fast sampling based image reconstruction algorithm for sheared-beam imaging
  
  Author(s):Chen, Ming-Lai(1,2,3); Ma, Cai-Wen(1,2,3); Liu, Hui(1,2,3); Luo, Xiu-Juan(1,2,3); Feng, Xu-Bin(1,2); Yue, Ze-Lin(1,3); Zhao, Jing(1,3)
  Source: Wuli Xuebao/Acta Physica Sinica  Volume: 73  Issue: 2  DOI: 10.7498/aps.73.20231254  Published: January 20, 2024  
  Abstract:Sheared-beam imaging (SBI) is an unconventional ground-based optical imaging technique. It breaks through the traditional optical imaging concept by using three coherent laser beams, which are laterally displaced at the transmit plane, to illuminate the target, reconstructing the target image from echo signals. However, the echo data sampling of the imaging system is still not fast enough to reconstruct the high resolution and clear image of the target when imaging the target that is at rapidly changing position and attitude. In order to solve this problem, in this work an image reconstruction method is proposed based on five-beam fast sampling. An emitted beam array arranged in the cross shape with a central symmetrical structure is proposed, and the encoding and decoding method of the imaging system are changed. With a single exposure, the echo signals carry more spectrum information of the target, and the number of reconstructed images can be increased from 1 to 8, which quickly suppresses the speckle effect of the reconstructed image. Firstly, the principle of the imaging technique based on fast sampling is presented. Then, an image reconstruction algorithm based on fast sampling is studied. Eight groups of phase differences and amplitude information of the target can be extracted from echo signals. The wavefront phases are solved by the least-squares method, and wavefront amplitude can be obtained by the algebraic operation of speckle amplitude. The target image is reconstructed by the inverse Fourier transform. The simulation results show that comparing with the traditional three-beam image reconstruction method, the sampling times of echo data needed to obtain the same quality image are reduced from 20 to 5, which greatly reduces the sampling times of echo data and improves the sampling rate of echo data. © 2024 Chinese Physical Society.
  Accession Number: 20240815605338
• Record 317 of
  
  Title:Fabrication of large aspect ratio single crystal diamond microchannel by femtosecond laser
  
  Author(s):Wang, Ning(1,2); Zhang, Jingzhou(1,2); Zhao, Hualong(1,2); Zhao, Wei(1)
  Source: Proceedings of SPIE - The International Society for Optical Engineering  Volume: 13104  Issue:   DOI: 10.1117/12.3016198  Published: 2024  
  Abstract:As heat dispersing materials, Diamond has high thermal conductivity, extremely low coefficient of thermal expansion, low coefficient of friction, and good chemical stability, which have broad application prospects in the field of high-power device heat dissipation. This study aims to address the inability of traditional laser processing methods to meet the processing requirements of high aspect ratio diamond heat dissipation microchannels. Based on a femtosecond laser fiveaxis machining system, a five-axis attitude alternating machining method is used to study the forming size, surface roughness, and aspect ratio of femtosecond laser surface microchannels, and to compare it with the direct machining method using a galvanometer. The experimental results show that using a super depth of field optical microscope for detection, the cross-sectional shape of diamond microchannels processed using a galvanometer direct machining method is triangular, with an edge unilateral taper of 62°. The cross-sectional shape of diamond microchannels processed using a five axis attitude alternating machining method is ladder shaped, with a maximum edge unilateral taper of 88°, approaching a vertical state of 90°. As the width of microchannels increases, the unilateral taper value increases. By using a confocal microscope, the roughness of diamond microchannels processed using a galvanometer direct machining method is Ra0.88, and the optimal roughness of diamond microchannels processed using a five axis attitude alternating machining method is Ra0.29. The use of five-axis attitude alternating machining method is superior to the use of galvanometer direct machining in terms of unilateral taper and roughness. Finally, diamond rectangular microchannels were prepared using a five axis attitude alternating machining method, with a maximum aspect ratio of 10.7:1 and a maximum depth of 1.072mm. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.
  Accession Number: 20241816027699
• Record 318 of
  
  Title:A Path Planning Method for Collaborative Coverage Monitoring in Urban Scenarios
  
  Author(s):Xu, Shufang(1,2); Zhou, Ziyun(1); Liu, Haiyun(1); Zhang, Xuejie(3); Li, Jianni(1); Gao, Hongmin(1)
  Source: Remote Sensing  Volume: 16  Issue: 7  DOI: 10.3390/rs16071152  Published: April 2024  
  Abstract:In recent years, unmanned aerial vehicles (UAVs) have become a popular and cost-effective technology in urban scenarios, encompassing applications such as material transportation, aerial photography, remote sensing, and disaster relief. However, the execution of prolonged tasks poses a heightened challenge owing to the constrained endurance of UAVs. This paper proposes a model to accurately represent urban scenarios and an unmanned system. Restricted zones, no-fly zones, and building obstructions to the detection range are introduced to make sure the model is realistic enough. We also introduced an unmanned ground vehicle (UGV) into the model to solve the endurance of the UAVs in this long-time task scenario. The UGV and UAVs constituted a heterogeneous unmanned system to collaboratively solve the path-planning problem in the model. Building upon this model, this paper designs a Three-stage Alternating Optimization Algorithm (TAOA), involving two crucial steps of prediction and rolling optimization. A three-stage scheme is introduced to rolling optimization to effectively address the complex optimization process for the unmanned system. Finally, the TAOA was experimentally validated in both synthetic scenarios and scenarios modeled based on a real-world location to demonstrate their reliability. The experiments conducted in the synthetic scenarios aimed to assess the algorithm under hypothetical conditions, while the experiments in the scenarios based on real-world locations provided a practical evaluation of the proposed methods in more complex and authentic environments. The consistent performance observed across these experiments underscores the robustness and effectiveness of the proposed approaches, supporting their potential applicability in various real-world scenarios. © 2024 by the authors.
  Accession Number: 20241615917025
• Record 319 of
  
  Title:Design of Mantis-Shrimp-Inspired Multifunctional Imaging Sensors with Simultaneous Spectrum and Polarization Detection Capability at a Wide Waveband
  
  Author(s):Wang, Tianxin(1,2); Wang, Shuai(1); Gao, Bo(1); Li, Chenxi(1); Yu, Weixing(1,2)
  Source: Sensors  Volume: 24  Issue: 5  DOI: 10.3390/s24051689  Published: March 2024  
  Abstract:The remarkable light perception abilities of the mantis shrimp, which span a broad spectrum ranging from 300 nm to 720 nm and include the detection of polarized light, serve as the inspiration for our exploration. Drawing insights from the mantis shrimp’s unique visual system, we propose the design of a multifunctional imaging sensor capable of concurrently detecting spectrum and polarization across a wide waveband. This sensor is able to show spectral imaging capability through the utilization of a 16-channel multi-waveband Fabry–Pérot (FP) resonator filter array. The design incorporates a composite thin film structure comprising metal and dielectric layers as the reflector of the resonant cavity. The resulting metal–dielectric composite film FP resonator extends the operating bandwidth to cover both visible and infrared regions, specifically spanning a broader range from 450 nm to 900 nm. Furthermore, within this operational bandwidth, the metal–dielectric composite film FP resonator demonstrates an average peak transmittance exceeding 60%, representing a notable improvement over the metallic resonator. Additionally, aluminum-based metallic grating arrays are incorporated beneath the FP filter array to capture polarization information. This innovative approach enables the simultaneous acquisition of spectrum and polarization information using a single sensor device. The outcomes of this research hold promise for advancing the development of high-performance, multifunctional optical sensors, thereby unlocking new possibilities in the field of optical information acquisition. © 2024 by the authors.
  Accession Number: 20241115750294
• Record 320 of
  
  Title:TMCFN: Text-Supervised Multidimensional Contrastive Fusion Network for Hyperspectral and LiDAR Classification
  
  Author(s):Yang, Yueguang(1); Qu, Jiahui(2); Dong, Wenqian(2,3); Zhang, Tongzhen(2); Xiao, Song(2,4); Li, Yunsong(2)
  Source: IEEE Transactions on Geoscience and Remote Sensing  Volume: 62  Issue:   DOI: 10.1109/TGRS.2024.3374372  Published: 2024  
  Abstract:The joint classification of hyperspectral images (HSIs) and LiDAR data plays a crucial role in Earth observation missions. Most advanced methods are based on discrete label supervision. However, since discrete labels only convey limited information that a sample belongs to a single definite class and lack of prior information, it is difficult to supervise the model to capture rich inherent semantic information in complex data distributions, hindering the classification performance. To this end, we propose a text-supervised multidimensional contrastive fusion network (TMCFN), which leverages class text information to guide the learning of visual representations while establishing a semantic association of text and visual features for classification using multidimensionally incorporated contrastive learning (CL) paradigms. Specifically, TMCFN is composed of text information encoding (TIE), visual features representation (VFR), and text-visual features alignment and classification (TVFAC). TIE is employed to extract semantic information from class text extended from class names, intrinsic attributes and inter-class relationships. VFR mainly comprises a new fusion-based contrastive feature learning module (FCFLM) to extract discriminative visual features and a text-guided attention feature fusion module (TAF2M) to fuse visual features under the guidance of text information. TVFAC optimizes the learning of visual features under the supervision of text information while using a CL paradigm to align text and visual features for establishing the semantic association, and achieves the classification by directly computing the similarity between the visual features and each text feature without an additional classifier. Experiments with three standard datasets verify the effectiveness of TMCFN. © 1980-2012 IEEE.
  Accession Number: 20241115732523
• Record 321 of
  
  Title:Optical-signal token guided change detection network for heterogeneous remote sensing image
  
  Author(s):Liu, Qinsen(1); Sun, Bangyong(1,2)
  Source: National Remote Sensing Bulletin  Volume: 28  Issue: 1  DOI: 10.11834/jrs.20233067  Published: 2024  
  Abstract:Change Detection (CD) is a vital technique for identifying and analyzing changes over time in a specific area using optical signals from remote sensing images. This technique has been extensively utilized in various fields, including national defense security, environmental monitoring, and urban construction. However, some challenges in achieving accurate and reliable CD are still encountered due to inherent disparities in imaging mechanisms, spectral ranges, and spatial resolutions among heterogeneous images. These challenges lead to issues such as inadequate accuracy, missed detections, and false detections. Heterogeneous remote sensing images can be regarded as sequences of different optical signals from the channel perspective. For example, RGB and infrared images can be regarded as sequences of spectral signals from different ranges. Transformers employ a multi-head attention mechanism that can effectively handle and analyze sequence information to achieve accurate heterogeneous CD. Thus, the paper proposes an optical signal token guided CD network for heterogeneous remote sensing images. This paper presents a novel heterogeneous CD network, primarily comprising the optical-signal token transformer (OT-Former) and the cross-temporal transformer (CT-Former). The proposed method demonstrates the capacity to effectively handle diverse remote sensing images of distinct categories and attain precise CD results. Specifically, OT-Former can encode diverse heterogeneous images in channel-wise for adaptively generating the optical-signal tokens. Meanwhile, CT-Former can use the optical-signal tokens as a guide to interact with the patch token for the learning of change rules. Moreover, a Difference Amplification Module (DAM) is embedded into the network to enhance the extraction of difference information. This module utilizes a 1×2 convolutional kernel to effectively fuse difference information. Finally, the differential token is predicted by multilayer perceptron to output the CD results. Experiments were conducted on three heterogeneous datasets and one homogeneous dataset to evaluate the performance of the proposed method. Furthermore, the proposed method was compared with six typical CD methods and evaluated the performance using overall accuracy (OA), Kappa coefficient, and F1-score, among other evaluation metrics, to validate the effectiveness of the proposed network in this study. A limited number of samples were utilized for training during the experiment. Under identical experimental conditions, the proposed method demonstrated exceptional performance in homogeneous and heterogeneous CD. The results show that the proposed approach surpasses existing state-of-the-art methods in terms of qualitative and visual performance. Additionally, ablation experiments and parameter analyses were conducted to validate the effectiveness of the proposed methods, including the OT-Former, CT-Former, and DAM modules, and to assess the impact of various parameters within the network. Overall, the current study presents a novel heterogeneous CD network based on the transformer framework. Within this network, OT-Former is proposed to achieve the adaptive generation of optical-signal tokens from diverse remote sensing images. Moreover, the CT-Former utilizes these optical-signal tokens as a guide to facilitate interaction with patch tokens for the learning of change rules. Additionally, DAM modules were embedded into the network to effectively extract the difference information. An extremely limited number of samples were utilized only for training in the experiments. Remarkably, the proposed method outperformed the existing state-of-the-art methods, achieving a significantly advanced performance in heterogeneous CD. © 2024 Science Press. All rights reserved.
  Accession Number: 20241515892473
• Record 322 of
  
  Title:Rapid Solidification of Invar Alloy
  
  Author(s):He, Hanxin(1); Yao, Zhirui(2); Li, Xuyang(3); Xu, Junfeng(2)
  Source: Materials  Volume: 17  Issue: 1  DOI: 10.3390/ma17010231  Published: January 2024  
  Abstract:The Invar alloy has excellent properties, such as a low coefficient of thermal expansion, but there are few reports about the rapid solidification of this alloy. In this study, Invar alloy solidification at different undercooling (ΔT) was investigated via glass melt-flux techniques. The sample with the highest undercooling of ΔT = 231 K (recalescence height 140 K) was obtained. The thermal history curve, microstructure, hardness, grain number, and sample density of the alloy were analyzed. The results show that with the increase in solidification undercooling, the XRD peak of the sample shifted to the left, indicating that the lattice constant increased and the solid solubility increased. As the solidification of undercooling increases, the microstructure changes from large dendrites to small columnar grains and then to fine equiaxed grains. At the same time, the number of grains also increases with the increase in the undercooling. The hardness of the sample increases with increasing undercooling. If ΔT ≥ 181 K (128 K), the grain number and the hardness do not increase with undercooling. © 2023 by the authors.
  Accession Number: 20240315384601
• Record 323 of
  
  Title:Adaptive location method for film cooling holes based on the design intent of the turbine blade
  
  Author(s):Hou, Yaohua(1); Wang, Jing(1); Mei, Jiawei(2); Zhao, Hualong(1)
  Source: International Journal of Advanced Manufacturing Technology  Volume: 132  Issue: 3-4  DOI: 10.1007/s00170-024-13456-4  Published: May 2024  
  Abstract:Due to the inevitable deviation of the casting process, the dimensional error of the turbine blade is introduced. As a result, the location datum of the film cooling holes is changed, which has an impact on the machining accuracy. The majority of pertinent studies concentrate on the rigid location approach for the entire blade, which results in a modest relative position error of the blade surface but still fails to give the exact position and axial direction of the film cooling holes of the deformed blade. In this paper, the entire deformation of the blade cross-section curve is divided into a number of deformation combinations of the mean line curve based on the construction method of the blade design intent. The exact location of the film cooling holes in the turbine blade with deviation is therefore efficiently solved by a flexible deformation of the blade that optimises the position and axial direction of the holes. The verification demonstrates that the novel method can significantly reduce both the contour deviation of the blade surface and the location issue of the film cooling holes. After machining experiments, the maximum position deviation of the holes is reduced by approximately 80% compared to the rigid location method of the entire blade, and the average value and standard deviation are also decreased by about 70%. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.
  Accession Number: 20241215791556
• Record 324 of
  
  Title:Hyperspectral scene classification dataset based on Zhuhai-1 images
  
  Author(s):Liu, Yuan(1,2); Zheng, Xiangtao(3); Lu, Xiaoqiang(3)
  Source: National Remote Sensing Bulletin  Volume: 28  Issue: 1  DOI: 10.11834/jrs.20233283  Published: 2024  
  Abstract:Hyperspectral remote sensing is a key technology for remotely obtaining the physical parameters of ground objects and realizing fine identification. It can not only get geometrical properties of the target scenes but also obtain radiance that reflects the characteristics of ground objects. With the development of hyperspectral remote sensing data to unprecedented spatial, spectral, temporal resolution and large data volume, how to adapt to the requirements of massive data and achieve efficient and rapid processing of hyperspectral remote sensing data has become the current research focus. Researchers are introducing scene classification into hyperspectral image classification, integrating the spatial and spectral information to obtain semantic information oriented to larger observation units. However, almost all existing multispectral/hyperspectral scene classification datasets have a number of limitations, including inconsistent spectral and spatial resolutions or spatial resolutions too large to meet the needs of fine-grained classification. Based on the hyperspectral images of Xi’an taken by the "Zhuhai-1" constellation, we combine the result of unsupervised spectral clustering and Google Earth to establish a hyperspectral satellite image scene classification dataset named HSCD-ZH (Hyperspectral Scene Classification Dataset from Zhuhai-1). It consists of 737 images divided into six categories: urban, agriculture, rural, forest, water, and unused land. Each image with a size of 64 × 64 pixels consists of 32 bands covering the wavelength in the range of 400—1000 nm. In addition, we conduct spatial-based and spectral-based experiments to analyze the performance of existing datasets, and the benchmark results are reported as a valuable baseline for subsequent research. We choose false-color image for the spatial-based experiments and then use popular deep and non-deep learning scene classification techniques. In the experiments based on spectral, the spectral vectors at the pixel are directly used as local spectral features, and BoVW, IFK, and LLC are used to encode them to generate global representations for the scene. Using SVM as the classifier, the optimal overall classification achieved by the two experiments on the proposed dataset is 92.34% and 88.96%, respectively. Considering that those methods have a large amount of information loss, we cascade the features extracted by the two approaches to generate spatial-spectral features. The highest overall accuracy obtained reaches 94.64%, which is the highest improvement in overall accuracy compared to the other datasets. We construct HSCD-ZH by effectively exploiting both spectral and spatial features of hyperspectral images, selecting various scenes that either have representative spectral compositions, clear spatial textures, or both. It has the advantages of big intraclass diversity, strong scalability, and adapting to satellite hyperspectral intelligent information extraction requirements. Both dataset and experiments can provide effective data support for remote sensing scene classification research in the hyperspectral field. Meanwhile, experiments can indicate that extracting features based on spatial or spectral misses a large amount of available information, and integrating the features extracted by the two methods can compensate for this deficiency. In our future work, we aim to expand the number of categories and images of HSCD-ZH and continue to explore algorithms for integrating spatial and spectral information that can accelerate the interpretation and efficient exploitation of hyperspectral scene cubes. © 2024 Science Press. All rights reserved.
  Accession Number: 20241515892427