Md. Arafat Hussain, Emon Kumar Dey · International Journal of Engineering and Manufacturing · 2018
Remote sensing image scene classification has gained remarkable attention because of its versatile use in different applications like geospatial object detection, natural hazards detection, geographic image retrieval, environment monitoring and etc. We have used the strength of convolutional neural network in scene image classification and proposed a new CNN to classify the images. Pre-trained VGG16 and ResNet50 are used to reduce overfitting and the training time in this paper. We have experimented on a recently proposed NWPU-RESISC45 dataset which is the largest dataset of remote sensing scene images. This paper found a significant improvement of accuracy by applying the proposed CNN and also the approaches have applied.
Cited by 11Open access
nxebbcie · Zenodo (CERN European Organization for Nuclear Research) · 2024
<pre><code>\n<p><strong>image classification in remote sensing pdf</strong><br></p>\n<p>Rating: 4.4 / 5 (4837 votes)<br></p>\n<p>Downloads: 49286<br><br></p>\n <p>= = = = = \n<strong><a href="https://calendario2023.es/21Nr9y?keyword=image classification in remote sensing pdf" target="_blank">CLICK HERE TO DOWNLOAD</a></strong>\n = = = = = <br><br></p>\n<p><br><br><br><br></p>\n<p><br><br><br><br></p>\n<p><br><br>Conventional classification uses The classification of remote sensing images is a challenging task, as image contains bulk of information which is to be carefully extracted and used. classification is defined a s the process o f categorizing all pixels i n an image or raw remotely sensed satellite data. Previous literature demonstrates that deep learning gains the excellent performance in image classification of remote sensing. In remote sensing image analysis, the images captured through satellite and drones are used to observe surface of the Earth. The main aim of any image classification-based system is to assign semantic labels to captured images, and to obtain a given set of labels or land cover This paper reviewed major remote sensing image classification techniques, including pixel-wise, sub-pixel-wise, and object-based image classification methods, and highlighted the importance of incorporating spatio-contextual information in remote sensing image classification from remote-sensing satellites (Keuchel et al. This study extracted the depth features of high-resolution remote sensing images using a residual learning network (ResNet), and low-level features, including color moment features and gray level co-occurrence matrix features, and created a classification model with the training support vector machine (SVM) Abstract. Often thematic classification is done using single date image, however in many instances a single date image is not informative enough to distinguish between different land cover types Remote sensing is mainly used to investigate sites of dams, bridges, and pipelines to locate construction materials and provide detailed geographic information. Then, common data sets and typical models of deep In a broad sense, image. b) was previously utilized in a remote sensing context by Gualtieri and Cromp in and Pal and Mather, This classification algorithm had been shown to be effective for face recognition in photos, handwriting and object recognition be fore it was adopted for use in remote sensing TLDR. Support vector machine 1, · The review shows that deep learning is promised to be dominant method of image classification of remote sensing, including deep belief network, convolutional , · Supervised Classification •Better for case where validity of classification depends on a priori knowledge of the technique, already know what types you plan to 8, · Although many machine learning methods have been successfully applied for the object-based classification of high resolution (HR) remote sensing imagery, 1 day ago · RS-Mamba for Large Remote Sensing Image Dense Prediction Sijie Zhao, Hao Chen*, Xueliang Zhang*, Pengfeng Xiao, Lei Bai, and Wanli Ouyang An accurate classification approach for high resolution remote sensing imagery based on the improved FCN model is proposed, which improves the density of output class maps by introducing Atrous convolution, and designs a multi-scale network architecture by adding a skip-layer structure to make it capable for multi-resolution image classification Keywords: Remote Sensing, Image Classification, K-means Classifier, Support Vector MachineImage y of Remote Sensing Classification Techniques Deep learning is the state-of-the-art of machine learning. Multispectral remote sensing images have been widely used for automated land use and land cover classification tasks. To begin with, data sources of remote sensing and current classification methods are briefly introduced. This paper looks into the following components related to the image classification process and procedures and image classification techniques and explains two common Image classification is widely applied in image analysis to extract land-use and land-cover (LULC) information from remote-sensing images.</p></code></pre>
Cited by 0Open access
Yuying, Xu, Rouyi, Xu, Jinyang, Ye · ScienceDB · 2025
This dataset is a land use classification method that uses multidimensional feature index coupled decision tree correction. The classification results were applied in the silt coastal zone of the Hangzhou Bay coastal plain, covering land use classification information at five key time points (2000, 2007, 2015, 2020, 2024) from 2000 to 2024. The land in the study area was divided into eight categories: vegetation-covered areas, offshore waters, cultured waters, paddy fields, other water bodies, swamps, construction land and unused land.
Cited by 0Open access
Pablo Ruiz, Javier Mateos, Gustau Camps‐Valls et al. · IEEE Transactions on Geoscience and Remote Sensing · 2013
In recent years, kernel methods, in particular support vector machines (SVMs), have been successfully introduced to remote sensing image classification. Their properties make them appropriate for dealing with a high number of image features and a low number of available labeled spectra. The introduction of alternative approaches based on (parametric) Bayesian inference has been quite scarce in the more recent years. Assuming a particular prior data distribution may lead to poor results in remote sensing problems because of the specificities and complexity of the data. In this context, the emerging field of nonparametric Bayesian methods constitutes a proper theoretical framework to tackle the remote sensing image classification problem. This paper exploits the Bayesian modeling and inference paradigm to tackle the problem of kernel-based remote sensing image classification. This Bayesian methodology is appropriate for both finite- and infinite-dimensional feature spaces. The particular problem of active learning is addressed by proposing an incremental/active learning approach based on three different approaches: 1) the maximum differential of entropies; 2) the minimum distance to decision boundary; and 3) the minimum normalized distance. Parameters are estimated by using the evidence Bayesian approach, the kernel trick, and the marginal distribution of the observations instead of the posterior distribution of the adaptive parameters. This approach allows us to deal with infinite-dimensional feature spaces. The proposed approach is tested on the challenging problem of urban monitoring from multispectral and synthetic aperture radar data and in multiclass land cover classification of hyperspectral images, in both purely supervised and active learning settings. Similar results are obtained when compared to SVMs in the supervised mode, with the advantage of providing posterior estimates for classification and automatic parameter learning. Comparison with random sampling as well as standard active learning methods such as margin sampling and entropy-query-by-bagging reveals a systematic overall accuracy gain and faster convergence with the number of queries.
Cited by 50
Eihan SHIMIZU · Journal of the Japan society of photogrammetry and remote sensing · 1992
The conventional method for classification of remote sensing image is based on Bayes' theorem. The
Cited by 0Open access
C. Radhika, Pl. Prranamyaaw, R. Poojitha et al. · Cognitive science and technology · 2025
Cited by 0
Minhua Wang, Philip J. Howarth · Remote Sensing of Environment · 1993
Cited by 16
Kumar H, Ali T, Holder C, McGough S, Bhowmik D · MyImpact · 2024
Cited by 0Open access
Li, Jiaojiao, Du, Qian, Chanussot, Jocelyn et al. · 2024
With the rapid growth in remote sensing imaging technology, vast amounts of remote sensing data are generated, which is significant for land-monitoring systems, and agriculture, etc., for Earth, Mars, etc. In recent decades, deep learning techniques have had a significant effect on remote sensing data processing, especially in image classification and semantic segmentation. However, several challenges still exist due to the limited annotations, the complexity of large-scale areas, and other specific problems, which make it more difficult in real-world applications. Therefore, novel deep neural networks combined with meta-learning, attention mechanisms, or other new transformer technologies need to be given more attention in remote sensing. It is also necessary to develop lightweight, explainable, and robust networks. Moreover, this Special Issue aims to develop state-of-the-art deep networks for more accurate remote sensing image classification and semantic segmentation, which also aims to achieve an efficient cross-domain performance through a lightweight network design.
Cited by 1Open access
Shah Kehul, Sujeet More · 2014
The resolution of remote sensing images increase every day .Most of the existing methods is used the same method for years. The existing method does not provide satisfactory result. The aim is to develop an artificial neural network based on classification method consists of segmentation and classification .Segmentation followed by K-Means method and then classification performed with back propagation neural network which provide accuracy and satisfactory result compare to the other method. General Terms Artificial neural network, Image Classification
Cited by 0
I Gusti Ayu Agung Diatri Indradewi, Ni Luh Wiwik Sri Rahayu Ginantra, Made Suci Ariantini · Journal of Physics Conference Series · 2020
Abstract Hyperspectral images are able to provide more information because this kind of images have hundreds of spectral bands. In machine learning, the classification of hyperspectral data has several challenges, including high number of dimensions, number of output classes, and limited data references. The solution given to overcome the challenge is to use Ensemble Learning. The benefit of using Ensemble Learning is that we can improve the classification performance of hyperspectral data. One of the Ensemble Learning methods is RotBoost, which is a combination of the Rotation Forest and Adaboost methods. To find out the performance of the RotBoost method, this research used hyperspectral data of vegetation area in Indian pines, Indiana, USA that is provided by NASA’s airborne visible infra-red imaging spectrometer (AVIRIS). The RotBoost method then compared with Rotation Forest method to find a better performance. Confusion matrix used to evaluate the accuracy of each method in the classification. The performance measured is overall accuracy obtained by doing 5-fold cross validation. This experiment also conducted to find the most optimal S (number of base classifiers) and T (number of iteration in Adaboost) values. Experimental results showed that RotBoost produces better accuracy than the Rotation Forest. S and T parameter values are also not very influential on RotBoost accuracy.
Cited by 0Open access
Hrithik Kumar, Teymoor Ali, Chris Holder et al. · 2024
Acceleration of image segmentation using deep learning methods on satellite imagery has become ubiquitous in various applications areas such as land cover classification, disaster monitoring and vegetation detection. However, the increase in satellite image resolution and large data volume required for remote sensing applications has resulted in a substantial increase in computational resource usage and demand for real-time processing. This paper investigates quantum computing as a novel approach to meet these computational demands, exploiting its parallel processing strengths. We evaluate hybrid quantum models (COQCNN, MQCNN, FQCNN) against classical CNN and U-Net architectures in remote sensing classification. Although COQCNN and MQCNN underperformed, FQCNN reached 53.26% accuracy, outperforming the classical CNN by 8%. Despite quicker convergence, quantum models struggle with complex feature segmentation, a task where U-Net excels. This study highlights quantum convolutions as a potential path to enhance convergence while addressing challenges like noise from multiple quantum channels affecting accuracy.
Cited by 2
Yakoub Bazi, Laila Bashmal, Mohamad Mahmoud Al Rahhal et al. · Remote Sensing · 2021
In this paper, we propose a remote-sensing scene-classification method based on vision transformers. These types of networks, which are now recognized as state-of-the-art models in natural language processing, do not rely on convolution layers as in standard convolutional neural networks (CNNs). Instead, they use multihead attention mechanisms as the main building block to derive long-range contextual relation between pixels in images. In a first step, the images under analysis are divided into patches, then converted to sequence by flattening and embedding. To keep information about the position, embedding position is added to these patches. Then, the resulting sequence is fed to several multihead attention layers for generating the final representation. At the classification stage, the first token sequence is fed to a softmax classification layer. To boost the classification performance, we explore several data augmentation strategies to generate additional data for training. Moreover, we show experimentally that we can compress the network by pruning half of the layers while keeping competing classification accuracies. Experimental results conducted on different remote-sensing image datasets demonstrate the promising capability of the model compared to state-of-the-art methods. Specifically, Vision Transformer obtains an average classification accuracy of 98.49%, 95.86%, 95.56% and 93.83% on Merced, AID, Optimal31 and NWPU datasets, respectively. While the compressed version obtained by removing half of the multihead attention layers yields 97.90%, 94.27%, 95.30% and 93.05%, respectively.
Cited by 553Open access
Huan Li, Hong Yang, Chao Zeng · 2018
There is great value to extract artificial surface from remote sensing images to understand urban expansion dynamics. With crowdsourcing data like Open Street Map (OSM), a great amount of labeled training data can be used as input of many supervised classification methods like Neural Network. This study explores the potential application of combining crowdsourcing data and remote sensing images in artificial surface extraction. A 1000 km <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> area of a Landsat 8 image in Beijing, the capital city of China, is chosen as the case study. Comparing with a spectral method Normalized Differential Building Index (NDBI) and an unsupervised method ISODATA, the freely available labeled building foot scripts by OSM are used as training datasets for several supervised classification methods including Maximum Likelihood Classification (MLC), Supporting Vector Machine (SVM), and Neural Network (NN). The estimation by OSM point features with building-like attributes shows that the accuracies of the five classification methods NDBI, ISODATA, MLC, SVM, and NN are 8.51 %, 45.39 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup> , 75.18 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup> , 85.11 %, and 93.62% respectively. This means that the combination of crowdsourcing and remote sensing has a very potential value for satellites applications like artificial surface extraction.
Cited by 1
Shreya Gupta, Rakesh Dwivedi, Vivek Kumar et al. · 2021
Remote sensing is the technology used for extracting information about the earth surface with the help of sensors installed on the satellites. The remote sensing technology captures and analyzes the sensed data which also helps in planning and monitoring the use of regional data. In our work, we used deep learning to analyze remotely sensed data. This paper aims to identify buildings from the images and provide the result using one of the deep neural networks. Various models of Convolutional Neural Networks (CNNs) help in rapid and accurate analysis of remote sensing data. The significance of the work lies in training the model correctly without overfitting. The work achieves 72.97% accurate model.
Cited by 3
Peijun Du, Xia Junshi, Zhaohui Xue et al. · National Remote Sensing Bulletin · 2016
éç模å¼è¯å«ãæºå¨å¦ä¹ ãé¥æææ¯çç¸å ³å¦ç§é¢åçåå±,é«å è°±é¥æå½±ååç±»ç 究åå¾å¿«éè¿å±ãæ¬æç³»ç»æ»ç»åè¯è¿°äºå½åé«å è°±é¥æå½±ååç±»çç¸å ³ç 究è¿å±,å¨æ»ç»åç±»çç¥çåºç¡ä¸,éç¹ä»ä»¥æ ¸æ¹æ³ä¸ºä»£è¡¨çæ°ååç±»å¨è®¾è®¡ãç¹å¾ææã空é´-å è°±åç±»ãåºäºä¸»å¨å¦ä¹ ååçç£å¦ä¹ çåç±»ãåºäºç¨ç表达çåç±»ãå¤åç±»å¨éæå 个æ¹é¢å¯¹é«å 谱影ååç´ çº§åç±»ææ°ç 究è¿è¡äºç»¼è¿°ãé对ä»åçç 究æ¹å,æåºé«å è°±é¥æå½±ååç±»ä¸æ¹é¢è¦éåºå¤§æ°æ®ãæºè½åé«å 谱对å°è§æµçåå±å沿,继ç»å¼å ¥æºå¨å¦ä¹ é¢åçæ°ç论ãæ°æ¹æ³,综åå©ç¨å¤æºé¥ææ°æ®ãå¤ç»´ç¹å¾ç©ºé´äºè¡¥çä¼å¿,æé«å类精度ãåç±»å¨æ³åè½ååèªå¨åç¨åº¦;å¦ä¸æ¹é¢è¦å ³æ³¨é«å è°±é¥æåºç¨çéæ±,çªåºé«å è°±é¥æè®°å½ç²¾ç»å è°±ç¹å¾çä¼å¿,é对åºç¨éæ±åå±ææçåç±»æ¹æ³ã
Cited by 76Open access
Yuliya Tarabalka · HAL (Le Centre pour la Communication Scientifique Directe) · 2017
The latest generation of aerial- and satellite-based imaging sensors acquires huge volumesof Earth’s images with high spatial, spectral and temporal resolution, which open the doorto a large range of important applications, such as the monitoring of natural disasters, theplanning of urban environments and precision agriculture. In order to fully exploit thepotential offered by these sensors, there is a need to develop accurate and time-efficientmathematical models and algorithms for spectral-spatial analysis of the recorded high-resolution data.The main goal of my research is to develop learning approaches, which would helpto automatically interpret, or classify, remote sensing images. This manuscript presentsseveral strategies I have explored for this purpose, varying from the use of strong shapepriors to detect objects, regularization of classification probabilities on the image graphs,and up to the use of convolutional neural network models capable to learn deep hierar-chical contextual features.The experimental results on diverse benchmarks of images and image time series showthe competitiveness of the developed methods when compared to the state-of-the-art ap-proaches. In particular, we have recently created large-scale classification benchmarkof aerial images and have demonstrated that the modern deep learning-based methodssucceed in generalizing to the dissimilar urban settlements around the Earth. This opensnew exciting perspectives towards designing systems which would be able to automati-cally update world-scale maps from remote sensing data.
Cited by 0Open access
Zhang, Guangyun · UNSWorks (University of New South Wales, Sydney, Australia) · 2013
Spatial information is important for remote sensing image classification. How to extract spatial information and incorporate it into classification procedure is a challenging issue in order to improve the traditionally spectral based classification. New frameworks and models are developed in this thesis. A new method based on the Conditional Random Fields (CRF) model is constructed to incorporate both spatial and spectral neighbouring information into the classification simultaneously. We develop a simplified version to cope with the complex training procedure for CRF. The new model integrates the boundary constraint into the classification. Comparing to traditional Markov Random Fields (MRF) model, this method incorporates discriminative model instead of generative model and takes into account of the observed data dependency into the classification to improve the result. A new framework is also developed based on the super pixels which are spatially connected homogenous regions. We develop an irregular graphical model based on the super pixels to incorporate long distance dependency into classification. Computation complexity is reduced significantly because of the reduction of the nodes and the edges in the construction of this graphical model. New methods are built to calculate the node and edge potentials with pixel level samples. A new algorithm for boundary information is developed to avoid over-smoothing. The third part of this thesis is the investigation of incorporating the spatial features into hyperspectral remote sensing image classification. These generated extra features make the high dimensional problem even worse for the hyperspectral data. A Sparse Multiclass Logistic Regression model is applied in this thesis to combine the spectral features, spectral interacted features and textural features into one procedure. This model realizes the feature selection and classification simultaneously. It can identify an effective subset of features and cope with a small size of training sample problem, even for the situation where the number of training samples is smaller than the dimensionality of the features. Experiments were conducted using real remote sensing images and encouraging results are acquired comparing to traditional methods.
Cited by 1Open access
Dong Jie and Shen Guojie · 2012
Cited by 3
Zhipeng Li, Li Shen, Linmei Wu · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · 2016
The data from remote sensing images are widely used for characterizing land use and land cover at present. With the increasing availability of very high resolution (VHR) remote sensing images, the remote sensing image classification becomes more and more important for information extraction. The VHR remote sensing images are rich in details, but high within-class variance as well as low between-class variance make the classification of ground cover a difficult task. What’s more, some related studies show that the quality of VHR remote sensing images also has a great influence on the ability of the automatic image classification. Therefore, the research that how to select the appropriate VHR remote sensing images to meet the application of classification is of great significance. In this context, the factors of VHR remote sensing image classification ability are discussed and some indices are selected for describing the image quality and the image classification ability objectively. Then, we explore the relationship of the indices of image quality and image classification ability under a specific classification framework. The results of the experiments show that these image quality indices are not effective for indicating the image classification ability directly. However, according to the image quality metrics, we can still propose some suggestion for the application of classification.
Cited by 0Open access