检索结果-内蒙古大学图书馆

Radar remote sensing image retrieval algorithm based on improved Sobel operator

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2020年 71卷 102720-102720页

作者： Chen, Guobin Jiang, Zhiyong Kamruzzaman, M. M. Chongqing Technol & Business Univ Chongqing Key Lab Spatial Data Min & Big Data Int Rongzhi Coll Chongqing 401320 Peoples R China Guilin Univ Aerosp Technol Practice Teaching Dept Guilin 541004 Guangxi Zhuang Peoples R China Jouf Univ Dept Comp & Informat Sci Sakaka Al Jouf Saudi Arabia

Aiming at the time-consuming problem caused by large computational load of radar image retrieval, based on blocking histogram, Sobel edge detection operator and gray level co-occurrence matrix (GLCCM), new radar remote sensing image retrieval algorithm based on improved Sobel operator is proposed. Firstly, the Sobel edge detection algorithm is used to process the image, the edge image is acquired, the radar remote sensing image is analyzed from different angles, and then the different radar remote sensing images are transformed. Then, based on the above processing, Radar Remote Sensing Image Retrieval Algorithm is acquired;finally, the plurality of statistic of the matrix is recorded as a feature vector describing the radar image, and the image is retrieved according to the feature vector of the radar image. Through a large number of experiments, Radar Remote Sensing Image Retrieval algorithm can greatly reduce the retrieval time, and it also has a good retrieval effect for images with rich texture. (c) 2019 Elsevier Inc. All rights reserved.

关键词： Radar image retrieval Blocking histogram Sobel operator Gray level co-occurrence matrix (GLCCM)

来源：评论

学校读者我要写书评

暂无评论

Rethinking Lightweight Convolutional Neural Networks for Efficient and High-Quality Pavement Crack Detection

引用

IEEE TRANSACTIONS ON intELLIGENT TRANSPORTATION SYSTEMS 2024年第1期25卷 237-250页

作者： Li, Kai Yang, Jie Ma, Siwei Wang, Bo Wang, Shanshe Tian, Yingjie Qi, Zhiquan Peking Univ Natl Engn Res Ctr Visual Technol Sch Comp Sci Beijing 100871 Peoples R China Univ Chinese Acad Sci Sch Math Sci Beijing 100049 Peoples R China Peking Univ Adv Inst Informat Technol Hangzhou 310005 Peoples R China Univ Int Business & Econ Sch Informat Technol & Management Beijing 100029 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Univ Chinese Acad Sci MOE Social Sci Lab Digital Econ Forecasts & Policy Beijing 100190 Peoples R China

Pixel-level road crack detection has always been a challenging task in intelligent transportation systems. Due to the external environments, such as weather, light, and other factors, pavement cracks often present low contrast, poor continuity, and different sizes in length and width. However, most of the existing studies pay less attention to crack data under different situations. Meanwhile, recent algorithms based on deep convolutional neural networks (DCNNs) have promoted the development of cutting-edge models for crack detection. Nevertheless, they usually focus on complex models for good performance, but ignore detection efficiency in practical applications. In this article, to address the first issue, we collected two new databases (i.e. Rain365 and Sun520) captured on rainy and sunny days respectively, which enrich the data of the open source community. For the second issue, we reconsider how to improve detection efficiency with excellent performance, and then propose our lightweight encoder-decoder architecture termed CarNet. Specifically, we introduce a novel olive-shaped structure for the encoder network, a lightweight multi-scale block and a new up-sampling method in the decoder network. Numerous experiments show that our model can better balance detection performance and efficiency compared with previous models. Especially, on the Sun520 dataset, our CarNet significantly advances the state-of-the-art performance with ODS F-score from 0.488 to 0.514. Meanwhile, it does so with an improved detection speed (104 frames per second) which is orders of magnitude faster than some recent DCNNs-based algorithms specially designed for crack detection.

关键词： Performance evaluation Deconvolution databases Source coding Roads Decoding Convolutional neural networks Crack detection lightweight model efficient inference multi-scale feature feature up-sampling

来源：评论

学校读者我要写书评

暂无评论

Spectral classification of ecological spatial polarization SAR image based on target decomposition algorithm and machine learning

引用

NEURAL COMPUTING & APPLICATIONS 2020年第10期32卷 5449-5460页

作者： Chen, Guobin Wang, Lukun Kamruzzaman, M. M. Chongqing Technol & Business Univ Chongqing Key Lab Spatial Data Min & Big Data Int Rongzhi Coll Chongqing 401320 Peoples R China Shandong Univ Sci & Technol Dept Informat Engn Tai An 271019 Shandong Peoples R China Jouf Univ Dept Comp & Informat Sci Sakaka Al Jouf Saudi Arabia

With the development of science and technology, the classification of polarimetric SAR images has become an important part of the research of target recognition and image interpretation. However, for the research method is relatively simple and the accuracy is low, this paper carries out the work from the two aspects of feature extraction and feature classification of the ground object, and analyzes and studies the application and value of the polarimetric SAR system. The basic algorithm of polarization SAR image classification is proposed. A polarimetric SAR image feature classification method based on polarization target decomposition and support vector machine is proposed. Four kinds of scattering features and Freeman decomposition are obtained by Cloude decomposition. The simulation results show that the accuracy of using combined features is about 6.5% higher than that of single features. A polarization classification model based on polarization target decomposition and limit learning method is proposed. The simulation experiment shows ELM learning. The algorithm is indeed much faster than SVM learning. In this paper, a polarimetric SAR image classification method based on improved scattering mechanism coefficients is proposed, and the effectiveness of the polarimetric SAR image classification method based on improved scattering mechanism coefficients is verified. Experimental results show that after feature selection, the method of combining Freeman decomposition and Wishart classifier can get better classification results.

关键词： Polarimetric SAR Target decomposition Machine learning Image feature classification Extreme learning

来源：评论

学校读者我要写书评

暂无评论

Initial soil moisture conditions affect the responses of colloid mobilisation and associated cadmium transport in opposite directions

引用

JOURNAL OF HAZARDOUS MATERIALS 2023年第1期448卷 130850页

作者： Zhang, Wei Liang, Yun Sun, Honglei Wang, Xingmin Zhou, Qigang Tang, Xiangyu Chongqing Technol & Business Univ Sch Publ Adm Dept Land Resources Management Chongqing 400067 Peoples R China Chongqing Key Lab Spatial Data Min & Big Data Inte Chongqing 400067 Peoples R China Chongqing Technol & Business Univ Sch Environm & Resources Chongqing 400067 Peoples R China Yunnan Hexu Environm Technol Co Ltd Mianyang 621002 Peoples R China Zhejiang A&F Univ State Key Lab Subtrop Silviculture Hangzhou 311300 Peoples R China Zhejiang A&F Univ 666 Wusu Ave Hangzhou 311300 Peoples R China

The effects of initial soil moisture on colloid-associated transport are still poorly understood given the well -recognized significance of colloid-facilitated transport of strongly-sorbing contaminants. In this study, Cd leaching was sequentially conducted in an intact soil column under three initial moisture conditions (near saturation, field capacity and dryness). Soil colloids were always the dominant carriers for Cd. However, upon the lowering of initial soil moisture, increased transport of colloids (96.2-101.0-168.2 mg) was observed, surprisingly, along with decreased transport of colloid-associated Cd (C-Cd) (23.9-10.7-8.2 mu g) and enrich-ment factor (248.4-105.9-48.8 mg/kg) of Cd on colloids, resulting from pH reduction which increased Cd desorption and colloid size increase and/or zeta-potential decrease that showed lower affinity for Cd. Correlation, redundancy analysis and structural equation modelling revealed the dominantly positive role of colloids, EC plus cations (Ca2+ and Mg2+) in the release of C-Cd and dissolved Cd (D-Cd), respectively, under initial moistures of near saturation and field capacity. Under initially dry conditions, soil water potential showed dominantly negative effects on the transport of both C-Cd and D-Cd. These findings highlighted the critical role of initial moisture conditions in modulating colloid-facilitated Cd mobilisation, providing insights into the environmental risk assessment of heavy metals in other leaching scenarios.

关键词： Colloid -facilitated transport Cadmium Drying Soil column experiment Leaching

来源：评论

学校读者我要写书评

暂无评论

Reservoir operation-induced hydrodynamic disturbances affect the distributions of Cd, Cu, and Pb in the riparian soil of the water-level-fluctuation zone

引用

JOURNAL OF SOILS AND SEDIMENTS 2021年第6期21卷 2343-2356页

作者： Zhang, Wei Sun, Honglei Liang, Yun Tang, Xiangyu Fang, Yuxiao Cui, Junfang Wang, Xingmin Zhou, Qigang Chongqing Technol & Business Univ Sch Publ Adm Chongqing 400067 Peoples R China Yunnan Hexu Environm Technol Co Ltd Mianyang 621002 Sichuan Peoples R China Southwest Jiaotong Univ Fac Geosci & Environm Engn Chengdu 611756 Peoples R China Chongqing Technol & Business Univ Sch Environm & Resources Chongqing 400067 Peoples R China Chinese Acad Sci Inst Mt Hazards & Environm Key Lab Mt Surface Proc & Ecol Regulat 9Block 4Renminnanlu Rd Chengdu 610041 Peoples R China Chongqing Key Lab Spatial Data Min & Big Data Int Chongqing 400067 Peoples R China

Purpose This study aimed to relate the altitudinal and vertical distributions and occurrences of major heavy metals (HMs) to soil physicochemical properties in the riparian soils subject to periodic and intense wet-dry cycles Materials and methods Cadmium (Cd), copper (Cu), and lead (Pb) and their chemical fractions were investigated in the riparian soil (0-40 cm) of the upland and within the water-level-fluctuation zone (WLFZ) at two tributary backwaters of the Three Gorges Reservoir (TGR) in China. Selected soil basic properties and pore structures determining the distribution of HMs and their fractions were identified using correlation and redundancy analysis Results and discussions Cd showed moderate-strong contamination and prevailed in non-residual fraction (>73.2%) in the riparian soil of the tributary backwaters in the TGR. In contrast, Cu and Pb exhibited slight contamination and prevailing in residual fraction (>50.3%). Enrichment of HMs in the lower end relatively flat WLFZ where flow rate decreased abruptly and dramatically was observed. Cd exhibited the largest coefficient of variation (CV, up to 0.263) across soil profiles while Cu showed a relatively homogeneous profile distribution in the riparian soil. Soil organic matter (SOM), cation exchange capacity (CEC), and pH were identified to be the primary factors determining the distributions of Cd, Cu, Pb, and their chemical fractions, respectively, in the riparian soil with a high macroporosity. Nevertheless, soil porosity was the dominant factor (>65.0%) determining the distributions of all the three HMs and their fractions in the non-drainable micropore-dominated riparian soil Conclusions Soil basic property and pore structure variations due to periodic hydrodynamic disturbances from reservoir operation are closely related to the redistribution of HMs in the riparian soil. The coupling of these two variations is strongly suggested to assist reliable evaluation of various contaminants, including but n

关键词： Heavy metals Riparian zone Three Gorges Reservoir Distribution Cadmium

来源：评论

学校读者我要写书评

暂无评论

BLEI: Research on a Novel Remote Sensing Bare Land Extraction Index

引用

REMOTE SENSING 2024年第9期16卷

作者： He, Chaokang Wang, Qinjun Yang, Jingyi Xu, Wentao Yuan, Boqi Chinese Acad Sci Aerosp Informat Res Inst Key Lab Digital Earth Sci Beijing 100094 Peoples R China Int Res Ctr Big Data Sustainable Dev Goals Beijing 100094 Peoples R China Univ Chinese Acad Sci Coll Resources & Environm Yanqi Lake Campus Beijing 101408 Peoples R China China Univ Min & Technol Beijing Coll Geosci & Surveying Engn Beijing 100083 Peoples R China Kashi Aerosp Informat Res Inst Kashi 844199 Peoples R China Hainan Aerosp Informat Res Inst Key Lab Earth Observat Hainan Prov Sanya 572029 Peoples R China

Bare land, as a significant land cover type on the Earth's surface, plays a crucial role in supporting land-use planning, urban management, and ecological environmental research through the investigation of its spatial distribution. However, due to the diversity of land-cover types on the Earth's surface and the spectral complexity exhibited by bare land under the influence of environmental factors, it is prone to confusion with urban and other land features. In order to extract bare land rapidly and efficiently, this study introduces a novel bare land extraction index called the Bare Land Extraction Index (BLEI). Then, considering both Ganzi Tibetan Autonomous Prefecture and Urumqi, China as the study areas, we compared BLEI with three presented indices: the Bare-soil Index (BI), Dry Bare Soil Index (DBSI), and Bare Soil Index (BSI). The results show that BLEI exhibits excellent efficacy in distinguishing bare land and urban areas. It gets the most outstanding accuracy in bare land identification and mapping, with overall accuracy (OA), kappa coefficient, and F1-score of 98.91%, 0.97, and 97.89%, respectively. Furthermore, BLEI is also effective in distinguishing bare land from sandy soil, which can not only improve the mapping accuracy of bare land in soil-deserted areas but also provide technological support for soil research and land-use planning.

关键词： bare land sandy soil Landsat 9 Bare Land Extraction Index (BLEI) remote sensing spectral indices

来源：评论

学校读者我要写书评

暂无评论

Event-Driven intrinsic Plasticity for Spiking Convolutional Neural Networks

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2022年第5期33卷 1986-1995页

作者： Zhang, Anguo Li, Xiumin Gao, Yueming Niu, Yuzhen Fuzhou Univ Coll Phys & Informat Engn Fuzhou 350108 Peoples R China Key Lab Med Instrumentat & Pharmaceut Technol Fuj Fuzhou 350116 Peoples R China Ruijie Networks Co Ltd Res Inst Ruijie Fuzhou 350002 Peoples R China Chongqing Univ Coll Automat Chongqing 400030 Peoples R China Fuzhou Univ Coll Math & Comp Sci Fujian Key Lab Network Comp & Intelligent Informa Fuzhou 350108 Fujian Peoples R China Minist Educ Key Lab Spatial Data Min & Informat Sharing Fuzhou 350108 Fujian Peoples R China

The biologically discovered intrinsic plasticity (IP) learning rule, which changes the intrinsic excitability of an individual neuron by adaptively turning the firing threshold, has been shown to be crucial for efficient information processing. However, this learning rule needs extra time for updating operations at each step, causing extra energy consumption and reducing the computational efficiency. The event-driven or spike-based coding strategy of spiking neural networks (SNNs), i.e., neurons will only be active if driven by continuous spiking trains, employs all-or-none pulses (spikes) to transmit information, contributing to sparseness in neuron activations. In this article, we propose two event-driven IP learning rules, namely, input-driven and self-driven IP, based on basic IP learning. Input-driven means that IP updating occurs only when the neuron receives spiking inputs from its presynaptic neurons, whereas self-driven means that IP updating only occurs when the neuron generates a spike. A spiking convolutional neural network (SCNN) is developed based on the ANN2SNN conversion method, i.e., converting a well-trained rate-based artificial neural network to an SNN via directly mapping the connection weights. By comparing the computational performance of SCNNs with different IP rules on the recognition of MNIST, FashionMNIST, Cifar10, and SVHN datasets, we demonstrate that the two event-based IP rules can remarkably reduce IP updating operations, contributing to sparse computations and accelerating the recognition process. This work may give insights into the modeling of brain-inspired SNNs for low-power applications.

关键词： IP networks Neurons Biological neural networks Computational modeling Biological system modeling Encoding Biomembranes Event-driven intrinsic plasticity (IP) input-driven IP IP self-driven IP spiking neural network (SNN)

来源：评论

学校读者我要写书评

暂无评论

Dynamic Visual Landscape Assessment of Disused Railway in Complex Terrain: A Study of Jingmen Railway

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2024年 17卷 10877-10892页

作者： Wang, Yueyi Wang, Shaohua Wang, Xin Huang, Xiaoyu Li, Xiao Zhang, Xueyan Li, Ziqiong Beijing Jiaotong Univ Sch Architecture & Design Beijing 100044 Peoples R China Int Res Ctr Big Data Sustainable Dev Goals Beijing 100094 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Key Lab Digital Earth Sci Beijing 100094 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst State Key Lab Remote Sensing Sci Beijing 100094 Peoples R China Lanzhou Jiaotong Univ Fac Geomat Lanzhou 730070 Peoples R China Univ Southern Calif Viterbi Sch Engn Los Angeles CA 90089 USA UCL Bartlett Ctr Adv Spatial Anal London W1T 4TJ England

Against the backdrop of the partially idle resources of conventional railways and the continuous growth of suburban leisure tourism demand, it is required to develop railway tourism by utilizing the disused resources of conventional railways in China. Therefore, restoring, analyzing, and evaluating the visual landscapes seen when traveling on conventional trains are extremely important. The innovation of this study is proposing a dynamic visual landscape interface for disused railways, which establishes a connection between the "seeing" and "perceiving" for passengers and describes the visual landscape they observe. By analyzing the dynamic visual factors of passengers and combining DEM data, the temporal-spatial relationship of the visual landscapes along the railway is described as a dynamic visual landscape interface model. Based on this, the study proposes criteria and indicators for analyzing and evaluating the dynamic visual landscapes of railways, using typical landscapes along the Jingmen railway as an example for evaluation and validation. The research results provide analytical and decision-making tools for repurposing disused railways as tourist railways.

关键词： Rail transportation Visualization Transportation Urban areas Image restoration Rails Dynamic scheduling Complex terrain disused railway dynamic visual landscape Jingmen railway tourist and recreational attractiveness

来源：评论

学校读者我要写书评

暂无评论

Evaluation of SDGSAT-1 MII data in total suspended matter estimation in clear to extremely turbid rivers

引用

intERNATIONAL JOURNAL OF DIGITAL EARTH 2024年第1期17卷

作者： Wang, Shenglei Mao, Zichen Zhang, Bing Yu, Xiaolong Zhao, Fenqi Song, Xiaofei Dou, Changyong Zhang, Fangfang Li, Junsheng Int Res Ctr Big Data Sustainable Dev Goals Beijing Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Key Lab Digital Earth Sci Beijing 100094 Peoples R China Univ Chinese Acad Sci Coll Resources & Environm Beijing Peoples R China Xiamen Univ Coll Ocean & Earth Sci State Key Lab Marine Environm Sci Xiamen Peoples R China China Univ Min & Technol Key Lab Land Environm & Disaster Monitoring Minist Nat Resources Xuzhou Peoples R China China Univ Geosci Beijing Inst Geosci & Resources Beijing Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing Peoples R China

The Multispectral Imager (MII) onboard the newly launched SDGSAT-1 holds significant promise for monitoring and understanding variations in water quality within nearshore water systems, with an impressive spatial resolution of 10 m, seven spectral bands in the visible and near-infrared domain and a wide swath of 300 km. This paper evaluates the MII data in estimating the concentration of total suspended matter (TSM) in rivers and estuaries from clear to extremely turbid conditions. For atmospheric correction, the ACOLITE model showed superior performance compared to the FLAASH and 6SV, with average unbiased relative error (AURE) ranging from 11.8% to 26.4% in the four visible bands of MII. Through comparison, a TSM model based on the visible band ratio (i.e., Rrs(660)/Rrs(560)) was proposed to ensure the application of MII data in both clear and turbid waters, with an overall AURE of 40.9%. The model was then applied to map the TSM variations in the Hai and Liao Rivers in northern China using the MII data, where reliable spatial and temporal patterns were observed. The study concludes by discussing the applicability of MII data in water quality mapping in nearshore waters, along with key considerations such as model applicability, atmospheric correction, and land adjacency.

关键词： SDGSAT-1 multispectral imager TSM River SDG 6.3

来源：评论

学校读者我要写书评

暂无评论

Benefits of Calibrating a Global Hydrological Model for Regional Analyses of Flood and Drought Projections: A Case Study of the Yangtze River Basin

引用

WATER RESOURCES RESEARCH 2025年第3期61卷

作者： Zhao, Fang Nie, Ning Liu, Yang Yi, Congrui Guillaumot, Luca Wada, Yoshihide Burek, Peter Smilovic, Mikhail Frieler, Katja Buechner, Matthias Schewe, Jacob Gosling, Simon N. East China Normal Univ Sch Geog Sci Key Lab Geog Informat Sci Minist Educ Shanghai Peoples R China MNR Key Lab Spatial Temporal Big Data Anal & Applicat Shanghai Peoples R China Potsdam Inst Climate Impact Res PIK Potsdam Germany Leibniz Assoc Potsdam Germany Int Inst Appl Syst Anal IIASA Biodivers & Nat Resources Program Water Secur Res Grp Laxenburg Austria Lanzhou Univ Coll Atmospher Sci Lanzhou Peoples R China Bur Rech Geol & Minieres Orleans France Int Inst Appl Syst Anal Biodivers & Nat Resources Program Laxenburg Austria King Abdullah Univ Sci & Technol Div Biol & Environm Sci & Engn Climate & Livabil Thuwal Saudi Arabia Univ Nottingham Sch Geog Nottingham England

Uncalibrated global hydrological models are primarily used to inform projections of flood and drought changes under global warming and their impacts, but it remains unclear how model calibration might benefit these projections. Using the Yangtze River Basin as a case study, we compare projected changes in flood and drought frequencies and their impacts-area, population, and gross domestic product affected-at various warming levels, from uncalibrated and calibrated simulations with the Community Water Model. These projections are driven by 10 General Circulation Models (GCMs) from Coupled Model intercomparison Project Phase 6, within the inter-Sectoral Impact Model intercomparison Project framework. Calibration significantly improves simulated discharge, yet the impact of calibration under climate change on projected increases in flood frequency and their associated impacts is minor, in contrast to its notable role in drought projections. We further quantify the relative contribution of GCMs, emission scenarios, and calibration approaches to the projected impacts, finding that GCMs primarily drive projected flood changes, while emission scenarios and calibration contribute more significantly to the variance in drought projections after 2050. The differing sensitivities to calibration are attributed to the dominance of extreme precipitation in flood generation and the influence of long-term evapotranspiration trends on drought occurrence. The findings imply that future projections of relative changes in flood frequency and risks based on uncalibrated hydrological models are likely still quite reliable for warm and humid regions. However, careful calibration and model improvement is crucial for enhancing the reliability of future drought impact assessments.

关键词： hydrological modeling climate change calibration floods and droughts Yangtze River Basin projection

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：