HSI-CNN: A Novel Convolution Neural Network for Hyperspectral Image

Luo, Yanlin; Zou, Jie; Yao, Chengfei; Zhao, Xianfeng; Li, Tao; Bai, Gang

doi:10.1109/icalip.2018.8455251

Cited by 128 publications

(76 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In a similar idea, [64] suggests an alternative approach that performs spatial-spectral convolutions in the first layer to perform spectral dimension reduction, similarly to what could be expected from PCA, albeit supervised and including spatial knowledge. Deeper layers form a traditional 2D CNN that performs as usual.…”

Section: B Spectral Classificationmentioning

confidence: 99%

Deep Learning for Classification of Hyperspectral Data: A Comparative Review

Audebert

Saux

Lefèvre

2019

IEEE Geosci. Remote Sens. Mag.

502

194

View full text Add to dashboard Cite

In recent years, deep learning techniques revolutionized the way remote sensing data are processed. Classification of hyperspectral data is no exception to the rule, but has intrinsic specificities which make application of deep learning less straightforward than with other optical data. This article presents a state of the art of previous machine learning approaches, reviews the various deep learning approaches currently proposed for hyperspectral classification, and identifies the problems and difficulties which arise to implement deep neural networks for this task. In particular, the issues of spatial and spectral resolution, data volume, and transfer of models from multimedia images to hyperspectral data are addressed. Additionally, a comparative study of various families of network architectures is provided and a software toolbox is publicly released to allow experimenting with these methods. 1 This article is intended for both data scientists with interest in hyperspectral data and remote sensing experts eager to apply deep learning techniques to their own dataset.

show abstract

Section: B Spectral Classificationmentioning

confidence: 99%

Deep Learning for Classification of Hyperspectral Data: A Comparative Review

Audebert

Saux

Lefèvre

2019

IEEE Geosci. Remote Sens. Mag.

502

194

View full text Add to dashboard Cite

show abstract

“…Santara et al [17] presented an end-to-end deep learning architecture that extracts band specific spectral-spatial features to performs landcover classification. Luo et al [13] proposed a novel HSI classification model to reorganize data by using the correlation between convolution results and to splice the one-dimensional data into image-like two-dimensional data to deepen the network structure and enable the network to extract and distinguish the features better. Lee et al [5] built a fully convolutional neural network with a total of 9 layers, which is much deeper than other convolutional networks for HSI classification.…”

Section: Related Workmentioning

confidence: 99%

“…Among the approaches explored for HSI classification, convolutional neural network (CNN) based methods such as BASS Net [17] and HSI-CNN [13] are favourable over the others because of their greatly improved accuracy for some popular benchmark datasets, with the ability to use extensive parameters to learn spectral features of a HSI. However, these CNN-based algorithms have great computational complexity due to the large dimensionality of hyperspectral images.…”

Section: Introductionmentioning

confidence: 99%

Optimizing CNN-Based Hyperspectral Image Classification on FPGAs

Liu

Chu

Wang

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

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. Methods based on Convolutional neural networks (CNNs) have been proven to achieve state-of-the-art accuracy in classifying HSIs. However, CNN models are often too computationally intensive to achieve real-time response due to the high dimensional nature of HSI, compared to traditional methods such as Support Vector Machines (SVMs). Besides, previous CNN models used in HSI are not specially designed for efficient implementation on embedded devices such as FPGAs. This paper proposes a novel CNN-based algorithm for HSI classification which takes into account hardware efficiency. A customized architecture which enables the proposed algorithm to be mapped effectively onto FPGA resources is then proposed to support real-time on-board classification with low power consumption. Implementation results show that our proposed accelerator on a Xilinx Zynq 706 FPGA board achieves more than 70× faster than an Intel 8-core Xeon CPU and 3× faster than an NVIDIA GeForce 1080 GPU. Compared to previous SVM-based FPGA accelerators, we achieve comparable processing speed but provide a much higher classification accuracy.

show abstract

“…Nowadays, the major role of software on our lives is not negligible, such that it can affect critical areas of our lives. Accordingly, reliability as one of the important aspects of quality of system components and proper connections among those are of great importance and it can indicate the critical position of software reliability engineering [1]. The probability of failure-free software operation or getting its expected precision is called software reliability [2].…”

Section: Introductionmentioning

confidence: 99%

“…Here, we reviewed the most important works in the field of architecture-based system reliability analysis, which have been performed as the result of the mentioned advantages. The goal of [1] was to provide an architecture-based reliability model which can consider heterogeneity of software architecture to address various component interactions. Accordingly, the method used in this work is based on discrete-time Markov chains as the building blocks for modeling application and calculating its reliability.…”

Section: Introductionmentioning

confidence: 99%