检索结果-内蒙古大学图书馆

Automatic extraction of economically important forest tree species using deep learning and image processing techniques

引用

Current Science 2025年第9期128卷 899-907页

作者： Bajpai, Anju Varghese, A.O. Kumar, T.P. Girish Sreenivasan, G. Regional Remote Sensing Centre-Central National Remote Sensing Centre Indian Space Research Organisation Nagpur440 033 India

Trees are crucial for the structure and functioning of forests and play a significant ecological and economic role. Certain tree species in forests have a key economic impact by providing timber and non-timber forest products (NTFPs) and contributing to the economic productivity and the livelihood of forest-dependent communities. Therefore, it is vital to accurately identify and quantify these economically important species to prioritise resource allocation and support rural livelihoods. While previous studies have focused on identifying tree species in more uniform temperate forest regions, few studies have concentrated on tropical, heterogeneous forests. Trees like Madhuca longifolia (Mahua), Dendrocalamus strictus (Bamboo), Tectona grandis (Teak), and Hardwickia binata (Anjan) are widely found in the Central regions of India. This study aimed to automatically identify economically important tree species using object-based image processing techniques, such as segmentation, object-based image classification, graphic analysis of spectral reflectance curve, and deep learning methods applied to Pléiades Neo Satellite data. Trees possess specific crown characteristics, tone, texture, pattern and shadows, which produce distinctive spectral and spatial signatures. The study automatically extracted the targeted trees from India’s highly diverse tropical forests, achieving an intersection over union (IoU) of 0.806. The Kappa coefficient turned out to be 0.81321, with omission error of 3% and commission error of 8%. © (2025), (Indian Academy of Sciences). All rights reserved.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Quantification of Hyperspectral Planes Effectiveness - A Semantic Segmentation Perspective

Quantification of Hyperspectral Planes Effectiveness - A Sem...

引用

Workshop on Hyperspectral image and Signal processing: Evolution in remote sensing, WHISPERS

作者： Corneliu Florea Andrei Racoviteanu Mihai Ivanovici Image Processing Analysis Laboratory National University of Science and Technology POLITEHNICA Bucharest Romania MIV Laboratory Transilvania University of Braşov Braşov Romania

ISBN: (数字)9798331513139

ISBN: (纸本)9798331513146

Automatic monitoring of agricultural crops with remote sensing data allows significant improvement in the face of climate change and environmental degradation. Hyperspectral imaging supports this process with spectrally detailed data, which goes beyond visible spectrum. In this paper we investigate how much information is actually brought by the richness and the details of additional spectral information. The assumed perspective is that of agricultural crop semantic segmentation approached with a powerful visual transformer based solution. Into more detail, we explore the effectiveness of various spectral bands in hyperspectral images, used as input, measured by five metrics quantifying the performance of agricultural crop segmentation. The evaluation relies on the UAV-HSI database. The primary conclusion is that there is significant redundancy in hyperspectrum, yet the full spectrum provides always top results. A secondary conclusion is that the recognition of specific crops such as “cotton” and “holly” benefits from removal of certain bands.

关键词： Measurement Visualization Semantic segmentation Face recognition Redundancy Crops Signal processing Transformers Monitoring Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Memory Consumption and Computation Efficiency Improvements of Viola-Jones Object Detection Method for remote sensing Applications

引用

pattern recognition AND image ANALYSIS 2021年第3期31卷 571-579页

作者： Usilin, S. A. Slavin, O. A. Arlazarov, V. V. Russian Acad Sci Fed Res Ctr Comp Sci & Control Bldg 244Vavilov Str Moscow 119333 Russia Smart Engines Serv LLC Moscow 121205 Russia

In this paper, we consider object classification and detection problems. We propose an algorithm that is effective from the point of view of computational complexity and memory consumption. The proposed algorithm can be successfully used as a basic tool for building different remote sensing systems which are, in general, installed on UAVs. The algorithm is based on the Viola-Jones method. It is shown in the paper, that the Viola-Jones method is the most preferable approach to detect objects on-board UAVs, because it needs the least amount of memory and the number of computational operations to solve the object detection problem. To ensure sufficient accuracy, we use a modified feature: rectangular Haar-like features, calculated over the magnitude of the image gradient. To increase computational efficiency, the L1 norm was used to calculate the magnitude of the image gradient. To train orientation-independent complex classifier we use a more generic decision tree form of complex classifier instead of a cascade scheme. All mentioned improvements were evaluated during detection of the following objects: the PSN-10 inflatable life raft (an example of an object that is detected during rescue operations using UAVs), oil tank storage (such kind of objects are usually detected during the inspection of industrial infrastructure), and aircraft on an area of hardstand. The performance of the trained detectors was estimated on real data (including data obtained during the rescue operation of the trawler Dalniy Vostok and a subset of real images from the DOTA dataset).

关键词： machine learning object detection Viola-Jones classification remote sensing unmanned aerial vehicle edge computing memory consumption computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Research on Full-Sky Star Identification Based on Spatial Projection and Reconfigurable Navigation Catalog

引用

remote sensing 2025年第9期17卷

作者： Wu, Siyao Sun, Ting Xing, Fei Liu, Haonan Song, Jiahui Yu, Shijie Beijing Informat Sci & Technol Univ Sch Instrument Sci & Optoelect Engn Beijing 100192 Peoples R China Beijing Informat Sci & Technol Univ Lab Intelligent Microsyst Beijing 100192 Peoples R China Tsinghua Univ Dept Precis Instrument Beijing 100084 Peoples R China

A star tracker is widely used as a high-precision attitude measurement device for spacecraft. It calculates attitude by extracting the magnitude and the position of presumed detected stars by a CCD/CMOS sensor and matching them with stars in the star catalog. The traditional star identification methods typically require the selection of specific anchor stars, which may cause insufficient identification accuracy as the number of stars used in the rough search is limited. In this paper, we propose a star identification method based on spatial projection, which starts with preprocessing. Then, a method for online expansion and reconstruction of the star catalog is proposed, which provides more stored star data. After the rough recognition and coordinate system transformation, the final identification is realized in the polar coordinate system. All the star points in the star image are identified, and the attitude information is obtained at the same time. The performance of the identification method is verified by real night sky experiments. Stray light experiments are also carried out to prove good noise immunity capabilities. Compared with the traditional subgraph isomorphism method, the proposed method makes it easier to adjust the number of recognizable stars in the field of view and better recognition of specific areas. The method is of great significance for future tasks such as attitude measurement, celestial navigation, remote sensing measurement, and space target observation and tracking.

关键词： star identification star image processing spatial projection reconfigurable navigation catalog celestial navigation

来源：评论

学校读者我要写书评

暂无评论

Satellite Multispectral and Hyperspectral image De-Noising with Enhanced Adaptive Generalized Gaussian Distribution Threshold in the Wavelet Domain

引用

remote sensing 2021年第1期13卷 1-16页

作者： Golilarz, Noorbakhsh Amiri Gao, Hui Pirasteh, Saied Yazdi, Mohammad Zhou, Junlin Fu, Yan Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Peoples R China Southwest Jiaotong Univ Fac Geosci & Environm Engn Chengdu 611756 Peoples R China Univ Lisbon Inst Super Tecn P-1049001 Lisbon Portugal

The presence of noise in remote sensing satellite images may cause limitations in analysis and object recognition. Noise suppression based on thresholding neural network (TNN) and optimization algorithms perform well in de-noising. However, there are some problems that need to be addressed. Furthermore, finding the optimal threshold value is a challenging task for learning algorithms. Moreover, in an optimization-based noise removal technique, we must utilize the optimization algorithm to overcome the problem. These methods are effective at reducing noise but may blur some parts of an image, and they are time-consuming. This flaw motivated the authors to develop an efficient de-noising method to discard un-wanted noises from these images. This study presents a new enhanced adaptive generalized Gaussian distribution (AGGD) threshold for satellite and hyperspectral image (HSI) de-noising. This function is data-driven, non-linear, and it can be fitted to any image. Applying this function provides us with an optimum threshold value without using any least mean square (LMS) learning or optimization algorithms. Thus, it is possible to save the processing time as well. The proposed function contains two main parts. There is an AGGD threshold in the interval [-sigma(n), sigma(n)], and a new non-linear function behind the interval. These combined functions can tune the wavelet coefficients properly. We applied the proposed technique to various satellite remote sensing images. We also used hyperspectral remote sensing images from AVIRIS, HYDICE, and ROSIS sensors for our experimental analysis and validation process. We applied peak signal-to-noise ratio (PSNR) and Mean Structural Similarity Index (MSSIM) to measure and evaluate the performance analysis of different de-noising techniques. Finally, this study shows the superiority of the developed method as compared with the previous TNN and optimization-based noise suppression methods. Moreover, as the results indicate, the pr

关键词： adaptive enhanced AGGD image de-noising optimization algorithm remote sensing TNN AVIRIS sensor HYDICE sensor ROSIS sensor

来源：评论

学校读者我要写书评

暂无评论

Multi Class Spectral Discriminative Convolutional Neural Network Towards Hyperspectral image Classification of Crop Disease on Inclusion of Spectral Spatial Feature Fusion Mechanism 4

Multi Class Spectral Discriminative Convolutional Neural Net...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Boopathi Raja, A.S. Poovarasan, K. Udhayakiran, S. Muhammed Aleem, Shaik Tharageswari, K. Karpagam Academy of Higher Education Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798331523923

Crop diseases occurs due to bacterial, viral, parasitic and fungal infection leads to various challenges to farmer and agricultural based business as crop diseases effects the normal growth of the crop and it spreads to other crops surrounding it. Especially those crop infection leads to great economic damage to the farmers and to the entire country. In order to prevent, classify and mitigate those crop infections, effective measures have to be carried out. Manual observation by biologist and agriculturist leads to misinterpretation and time consuming. In particular, remote sensing technologies using hyperspectral imaging techniques helps to monitor and acquire the agriculture information in various target regions effectively. Due to development of computer vision technique and artificial intelligence approaches in form of machine learning and deep learning architectures, countermeasure against the crop disease can be achieved easily on processing the acquired information in form of hyperspectral images. However traditional architecture faces multiple challenges in form of the spectral signatures unmixing as boundaries of the objects of different diseases types is very complex to be filtered. Thus, a new spectral unmixing based object recognition method has to be constructed to categorizes different form of crop disease in the agriculture region. In this paper, Multi Class Spectral Discriminative Convolution Neural Network(MCSD-CNNN) using spectral and spatial feature fusion towards hyperspectral image classification for detect, classify and mitigate the crop diseases on various climate and various regions. Initially image preprocessing is carried out to eliminate the spectral noises. Preprocessed image is projected to convolution layer of the network to extract the endmembers of the spectral band representing the various crop species in the different climate and spatial regions. Extracted end member of the spectral band is represented spectral disease index map. Th

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Multi-Scale Ship Detection Through Joint Multi-Source image Training

Enhanced Multi-Scale Ship Detection Through Joint Multi-Sour...

引用

International Conference on Information, Communication and Networks (ICICN)

作者： Yuan Huang Minghua Cao Yue Zhang Cheng Ning School of Computer and Communication Lanzhou University of Technology Lanzhou China

ISBN: (数字)9798350355802

ISBN: (纸本)9798350355819

In order to improve the detection performance of traditional single-source remote sensing image ship detection methods in terms of anti-interference capability and multi-scale targets. We develop an improved algorithm based on YOLOv8, called Sea-YOLOv8, and obtain the multi-source remote sensing image detection model SAR-YOLOv8 through migration ***, Efficient Multi-Scale Convolution (EMSConv) is used to improve the ability of the C2f module in capturing the features of ships at different scales by using different sizes of convolution kernels. scale ship features using different sized convolution kernels. Secondly, Large Separable Kernel Attentio (LSKAtt) is applied to the SPPF module to decompose the 2D convolution kernel into horizontal and vertical 1D kernels, which improves the computational efficiency while maintaining the high efficiency image processing capability. Experimental results on the SeaShips and SSDD datasets show that Sea-YOLOv8 has a good performance in terms of R, mAP, model parameters and FPS have achieved satisfactory results. Finally, the optimal transfer learning strategy was determined through layer-by-layer freezing, training and validation, which led to the construction of the multi-source remote sensing image recognition model SAR-YOLOv8.

关键词： Training image recognition Convolution Transfer learning Object detection Feature extraction Radar polarimetry Marine vehicles Kernel remote sensing

来源：评论

学校读者我要写书评

暂无评论

Research on Intelligent Monitoring Technology of Substation Equipment Based on Artificial Intelligence

Research on Intelligent Monitoring Technology of Substation ...

引用

2023 IEEE International Conference on Sensors, Electronics and Computer Engineering, ICSECE 2023

作者： Kexin, Zhang Siwei, Han Yang, Lin Jianquan, Liang Yue, Wang Chunfeng, Yue Lu, Li Dewen, Zhang Jian, Zhang State Grid Heilongjiang Electric Power Research Institute Harbin China

ISBN: (纸本)9798350313734

In this paper, based on fusion monitoring technology, communication technology, information processing technology, the establishment of substation remote intelligent inspection system. The system adopts browser/server (B/S) three-layer network distribution structure, which is divided into application end, network communication end and server end. Intelligent multi-dimensional image monitoring system realizes the remote real-time video monitoring function of substation, automatic inspection function of substation equipment, video intelligent analysis and remote alarm function. The system obtains substation surveillance video data through the unified video surveillance platform (SG-UVP). The intelligent identification and judgment of the running state of key equipment in substation by using video can realize the centralization, intellectualization and visualization of inspection. The practice proves that the system has significant economic and social benefits to improve the efficiency of substation operation and maintenance. © 2023 IEEE.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Morphological slum index for slum extraction from high-resolution remote sensing imagery over urban areas

引用

GEOCARTO INTERNATIONAL 2022年第26期37卷 13904-13922页

作者： Prabhu, R. Parvathavarthini, B. Anna Univ Dept Elect & Commun Engn St Josephs Coll Engn Chennai Tamil Nadu India Anna Univ Dept Comp Sci & Engn St Josephs Coll Engn Chennai Tamil Nadu India

This article proposes the Morphological Slum Index (MSI) approach for extracting slum areas from Very High Resolution (VHR) satellite images. An MSI is built by using different morphological operators. Since, the non-slum objects (buildings, vegetation, roads and open areas) are brighter than their neighbourhoods and show similar spectral properties as those of slums, MSI classifies the non-slum objects as slum objects. To optimize the misclassification of MSI, a post-processing technique called Morphological Spatial pattern Analysis (MSPA) is used. Three different VHR images acquired by the WorldView-2 sensor (1.84 m resolution) of Madurai city, India and one image acquired by the WorldView-3 Sensor (0.31 m resolution) of Kibera, Kenya are used as the test images to investigate the qualitative and quantitative results of the proposed technique. From the classified outputs, the proposed MSI with MSPA approach attains an overall accuracy of 95.78%, 96.42%, 95.12% and 92.64% for test images 1, 2, 3 and 4, respectively.

关键词： Morphological slum index slums morphological spatial pattern analysis WorldView-2 WorldView-3

来源：评论

学校读者我要写书评

暂无评论

Rotated Multi-Scale Interaction Network for Referring remote sensing image Segmentation

Rotated Multi-Scale Interaction Network for Referring Remote...

引用

Conference on Computer Vision and pattern recognition (CVPR)

作者： Sihan Liu Yiwei Ma Xiaoqing Zhang Haowei Wang Jiayi Ji Xiaoshuai Sun Rongrong Ji Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University P.R. China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Referring remote sensing image Segmentation (RRSIS) is a new challenge that combines computer vision and natu-ral language processing. Traditional Referring image Seg-mentation (RIS) approaches have been impeded by the com-plex spatial scales and orientations found in aerial imagery, leading to suboptimal segmentation results. To address these challenges, we introduce the Rotated Multi-Scale In-teraction Network (RMSIN), an innovative approach de-signed for the unique demands of RRSIS. RMSIN incorpo-rates an Intra-scale Interaction Module (IIM) to effectively address the fine-grained detail required at multiple scales and a Cross-scale Interaction Module (CIM) for integrating these details coherently across the network. Furthermore, RMSIN employs an Adaptive Rotated Convolution (ARC) to account for the diverse orientations of objects, a novel contribution that significantly enhances segmentation accu-racy. To assess the efficacy of RMSIN, we have curated an expansive dataset comprising 17,402 image-caption-mask triplets, which is unparalleled in terms of scale and vari-ety. This dataset not only presents the model with a wide range of spatial and rotational scenarios but also estab-lishes a stringent benchmark for the RRSIS task, ensuring a rigorous evaluation of performance. Experimental eval-uations demonstrate the exceptional performance of RM-SIN, surpassing existing state-of-the-art models by a signif-icant margin. Datasets and code are available at https://***/Lsan2401/RMSIN.

关键词： image segmentation Computer vision Codes Navigation Convolution Benchmark testing Solids

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：