Filters








539 Hits in 3.4 sec

Convolution Based Spectral Partitioning Architecture for Hyperspectral Image Classification [article]

Ringo S.W. Chu, Ho-Cheung Ng, Xiwei Wang, Wayne Luk
2019 arXiv   pre-print
To address these challenges, this paper proposes a deep learning architecture using three dimensional convolutional neural networks with spectral partitioning to perform effective feature extraction.  ...  Hyperspectral images (HSIs) can distinguish materials with high number of spectral bands, which is widely adopted in remote sensing applications and benefits in high accuracy land cover classifications  ...  The authors are grateful for the support by Intel, United Kingdom EPSRC (grant numbers EP/I012036/1, EP/L00058X/1, EP/L016796/1, EP/N031768/1), European Union Horizon 2020 Research and the Lee Family Scholarship  ... 
arXiv:1906.11981v1 fatcat:wrpr2jrt4vaijgpq342vi7ulo4

HİPERSPEKTRAL VERİLERİN SINIFLANDIRMASINDA DERİN ÖĞRENME VE BOYUT İNDİRGEME TEKNİKLERİNİN KARŞILAŞTIRILMASI

Gizem ORTAÇ, Gıyasettin ÖZCAN
2018 Uludağ University Journal of The Faculty of Engineering  
Recently, deep convolutional neural networks are proposed to classify hyperspectral images directly in the spectral domain.  ...  The obtained results on hyperspectral image data sets show that our proposed CNN architecture improves the accuracy rates for classification performance, when compared to traditional methods by increasing  ...  Unlike conventional hyperspectral classification approaches, we propose a 2D CNN architecture for efficient classification.  ... 
doi:10.17482/uumfd.435723 fatcat:vq7fmf7vgfhafltj3liiyhvnlu

Cross-domain CNN for Hyperspectral Image Classification [article]

Hyungtae Lee, Sungmin Eum, Heesung Kwon
2018 arXiv   pre-print
In this paper, we address the dataset scarcity issue with the hyperspectral image classification.  ...  As only a few thousands of pixels are available for training, it is difficult to effectively learn high-capacity Convolutional Neural Networks (CNNs).  ...  For each dataset-specific stream in the proposed architecture, we have used the modified version of the 9-layered hyperspectral image classification CNN introduced by Lee and Kwon [4, 5] .  ... 
arXiv:1802.00093v2 fatcat:f7wc6qz3p5hnzczl4u52p6qade

A Novel Classification Framework for Hyperspectral Image Data by Improved Multilayer Perceptron Combined with Residual Network

Aili Wang, Meixin Li, Haibin Wu
2022 Symmetry  
Convolutional neural networks (CNNs) have attracted extensive attention in the field of modern remote sensing image processing and show outstanding performance in hyperspectral image (HSI) classification  ...  Combined with the characteristics of hyperspectral data, we design IMLP based on three improvements.  ...  Acknowledgments: We thank Kaiyuan Jiang for his valuable comments and discussion. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/sym14030611 fatcat:s6dhg4uperhzzkz2cuuz4fgtvq

Multiscale Convolutional Transformer with Center Mask Pretraining for Hyperspectral Image Classification [article]

Sen Jia, Yifan Wang
2022 arXiv   pre-print
Hyperspectral images (HSI) not only have a broad macroscopic field of view but also contain rich spectral information, and the types of surface objects can be identified through spectral information, which  ...  is one of the main applications in hyperspectral image related research.In recent years, more and more deep learning methods have been proposed, among which convolutional neural networks (CNN) are the  ...  Architecture of the proposed multiscale convolutional transformer for hyperspectral image classification Fig. 4 .Fig. 5 . 45 Fig. 4.  ... 
arXiv:2203.04771v4 fatcat:v4f4yv5xkzhudeffk4zuvrjkjy

BASS Net: Band-Adaptive Spectral-Spatial Feature Learning Neural Network for Hyperspectral Image Classification

Anirban Santara, Kaustubh Mani, Pranoot Hatwar, Ankit Singh, Ankur Garg, Kirti Padia, Pabitra Mitra
2017 IEEE Transactions on Geoscience and Remote Sensing  
In hyperspectral images (HSI) they face the challenges of large dimensionality, spatial variability of spectral signatures and scarcity of labeled data.  ...  Deep learning based landcover classification algorithms have recently been proposed in literature.  ...  Experiments on benchmark hyperspectral image classification data sets show that the proposed network converges faster and gives superior classification performance than other deep learning based methods  ... 
doi:10.1109/tgrs.2017.2705073 fatcat:nkg5lzfly5gpxd33drr6jnspm4

Mapping Tree Species Composition Using OHS-1 Hyperspectral Data and Deep Learning Algorithms in Changbai Mountains, Northeast China

Yanbiao Xi, Chunying Ren, Zongming Wang, Shiqing Wei, Jialing Bai, Bai Zhang, Hengxing Xiang, Lin Chen
2019 Forests  
Especially for broadleaf species with similar spectral characteristics, such as Manchurian walnut and aspen, the accuracy of Conv1D-based classifier is significantly higher than RF classifier (87.15% and  ...  In this study, one-dimensional convolutional neural network (Conv1D), a popular deep learning algorithm, was proposed to automatically identify tree species using OHS-1 hyperspectral images.  ...  S.W. optimized the algorithm and gave suggestions for the whole study. J.B. processed hyperspectral data in addition to writing the paper. H.X. and B.Z. gave suggestions for the whole study.  ... 
doi:10.3390/f10090818 fatcat:s6ugsrglhrgyppfebeyegfpege

A Lightweight 1-D Convolution Augmented Transformer with Metric Learning for Hyperspectral Image Classification

Xiang Hu, Wenjing Yang, Hao Wen, Yu Liu, Yuanxi Peng
2021 Sensors  
However, most deep learning methods for hyperspectral image classification are based on convolutional neural networks (CNN). Those methods require heavy GPU memory resources and run time.  ...  In this paper, we propose a model for hyperspectral image classification based on the transformer, which is widely used in natural language processing.  ...  Conclusions In this article, we introduce the transformer architecture for hyperspectral image classification.  ... 
doi:10.3390/s21051751 pmid:33802533 fatcat:3d4vcipcxnhwpero6a3zgm4plq

A hyperspectral image classification algorithm based on atrous convolution

Xiaoqing Zhang, Yongguo Zheng, Weike Liu, Zhiyong Wang
2019 EURASIP Journal on Wireless Communications and Networking  
Hyperspectral images not only have high spectral dimension, but the spatial size of datasets containing such kind of images is also small.  ...  Aiming at this problem, we design the NG-APC (non-gridding multi-level concatenated Atrous Pyramid Convolution) module based on the combined atrous convolution.  ...  Acknowledgements Thanks for the support of the National Virtual Simulation Laboratory Center for Coal Mine Safety Mining, Shandong University of Science and Technology.  ... 
doi:10.1186/s13638-019-1594-y fatcat:fw66gl3p4nhh7kgp6n2ticyv3q

Conditional Random Field and Deep Feature Learning for Hyperspectral Image Segmentation [article]

Fahim Irfan Alam, Jun Zhou, Alan Wee-Chung Liew, Xiuping Jia, Jocelyn Chanussot, Yongsheng Gao
2017 arXiv   pre-print
Image segmentation is considered to be one of the critical tasks in hyperspectral remote sensing image processing.  ...  In this paper, we propose a method to segment hyperspectral images by considering both spectral and spatial information via a combined framework consisting of CNN and CRF.  ...  [20] for feature extraction and classification of hyperspectral images based on three-dimensional spectral cubes across all the bands that combines both spectral and spatial information.  ... 
arXiv:1711.04483v2 fatcat:vensfbnbjfgh3hnxdakobqb2l4

Conditional Random Field and Deep Feature Learning for Hyperspectral Image Classification

Fahim Irfan Alam, Jun Zhou, Alan Wee-Chung Liew, Xiuping Jia, Jocelyn Chanussot, Yongsheng Gao
2018 IEEE Transactions on Geoscience and Remote Sensing  
Image segmentation is considered to be one of the critical tasks in hyperspectral remote sensing image processing.  ...  In this paper, we propose a method to segment hyperspectral images by considering both spectral and spatial information via a combined framework consisting of CNN and CRF.  ...  [20] for feature extraction and classification of hyperspectral images based on three-dimensional spectral cubes across all the bands that combines both spectral and spatial information.  ... 
doi:10.1109/tgrs.2018.2867679 fatcat:6cyzgw7g7rfs7ertcsx72iwspa

Optimizing CNN-based Hyperspectral Image Classification on FPGAs [article]

Shuanglong Liu, Ringo S.W. Chu, Xiwei Wang, Wayne Luk
2019 arXiv   pre-print
Hyperspectral image (HSI) classification has been widely adopted in applications involving remote sensing imagery analysis which require high classification accuracy and real-time processing speed.  ...  This paper proposes a novel CNN-based algorithm for HSI classification which takes into account hardware efficiency.  ...  Hyperspectral image (HSI) classification is the task to assign a class label to every pixel in an image. Several approaches have been explored in literature for HSI classification.  ... 
arXiv:1906.11834v1 fatcat:arcbhexooja6hhmm4j5z4sgbei

Crop Classification for Agricultural Applications in Hyperspectral Remote Sensing Images

Loganathan Agilandeeswari, Manoharan Prabukumar, Vaddi Radhesyam, Kumar L. N. Boggavarapu Phaneendra, Alenizi Farhan
2022 Applied Sciences  
Band selection (BS) refers to the process of selecting the most relevant bands from a hyperspectral image, which is a necessary and important step for classification in HSI.  ...  Hyperspectral imaging (HSI), measuring the reflectance over visible (VIS), near-infrared (NIR), and shortwave infrared wavelengths (SWIR), has empowered the task of classification and can be useful in  ...  Acknowledgments: The authors thank the Vellore Institute of Technology, Vellore for providing a VIT seed grant for carrying out this research work.  ... 
doi:10.3390/app12031670 fatcat:zmcveoach5ghhj2wd5cxnb7cgi

Deep Convolutional Neural Networks for Hyperspectral Image Classification

Wei Hu, Yangyu Huang, Li Wei, Fan Zhang, Hengchao Li
2015 Journal of Sensors  
In this paper, deep convolutional neural networks are employed to classify hyperspectral images directly in spectral domain.  ...  Experimental results based on several hyperspectral image data sets demonstrate that the proposed method can achieve better classification performance than some traditional methods, such as support vector  ...  In this paper, we will explore what is the suitable architecture and strategy for CNN-based HSI classification. CNN-Based HSI Classification 3.1. Applying CNNs to HSI Classification.  ... 
doi:10.1155/2015/258619 fatcat:crlw4dhnyzh7dfaty2ukqd2lhq

Light Weight Residual Dense Attention Net for Spectral Reconstruction from RGB Images [article]

D.Sabari Nathan, K.Uma, D Synthiya Vinothini, B. Sathya Bama, S. M. Md Mansoor Roomi
2020 arXiv   pre-print
Hyperspectral Imaging is the acquisition of spectral and spatial information of a particular scene. Capturing such information from a specialized hyperspectral camera remains costly.  ...  Reconstructing such information from the RGB image achieves a better solution in both classification and object recognition tasks.  ...  To overcome the above problem, this work provides a cost effective solution for hyperspectral imaging that can reconstruct the spectral information from the RGB image.  ... 
arXiv:2004.06930v2 fatcat:57g5uhhvjjakjfp3c4udzulydy
« Previous Showing results 1 — 15 out of 539 results