Classification of hyperspectral imagery with a 3D convolutional neural network and J-M distance

Wang, Chunxing; Ma, Nan; Ming, Yanfang; Wang, Quan; Xia, Jinfeng

doi:10.1016/j.asr.2019.05.005

Cited by 31 publications

(17 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A conventional method is to fuse separately extracted spectral features and spatial features ( Zhao and Du, 2016 ; Wang et al, 2017a ). Another method is to use three-dimensional (3D) CNN, whose 3D convolution kernel directly combines local spectral-spatial features ( Wang et al, 2019a ). At present, there are various DL architectures that combine the spectral-spatial features of HSIs, such as Resnet and DenseNet ( Paoletti et al, 2019 ; Zhong et al, 2018 ).…”

Section: Introductionmentioning

confidence: 99%

Combining Multi-Dimensional Convolutional Neural Network (CNN) With Visualization Method for Detection of Aphis gossypii Glover Infection in Cotton Leaves Using Hyperspectral Imaging

Yan

Jiao

et al. 2021

Front. Plant Sci.

View full text Add to dashboard Cite

Cotton is a significant economic crop. It is vulnerable to aphids (Aphis gossypii Glovers) during the growth period. Rapid and early detection has become an important means to deal with aphids in cotton. In this study, the visible/near-infrared (Vis/NIR) hyperspectral imaging system (376–1044 nm) and machine learning methods were used to identify aphid infection in cotton leaves. Both tall and short cotton plants (Lumianyan 24) were inoculated with aphids, and the corresponding plants without aphids were used as control. The hyperspectral images (HSIs) were acquired five times at an interval of 5 days. The healthy and infected leaves were used to establish the datasets, with each leaf as a sample. The spectra and RGB images of each cotton leaf were extracted from the hyperspectral images for one-dimensional (1D) and two-dimensional (2D) analysis. The hyperspectral images of each leaf were used for three-dimensional (3D) analysis. Convolutional Neural Networks (CNNs) were used for identification and compared with conventional machine learning methods. For the extracted spectra, 1D CNN had a fine classification performance, and the classification accuracy could reach 98%. For RGB images, 2D CNN had a better classification performance. For HSIs, 3D CNN performed moderately and performed better than 2D CNN. On the whole, CNN performed relatively better than conventional machine learning methods. In the process of 1D, 2D, and 3D CNN visualization, the important wavelength ranges were analyzed in 1D and 3D CNN visualization, and the importance of wavelength ranges and spatial regions were analyzed in 2D and 3D CNN visualization. The overall results in this study illustrated the feasibility of using hyperspectral imaging combined with multi-dimensional CNN to detect aphid infection in cotton leaves, providing a new alternative for pest infection detection in plants.

show abstract

Section: Introductionmentioning

confidence: 99%

Combining Multi-Dimensional Convolutional Neural Network (CNN) With Visualization Method for Detection of Aphis gossypii Glover Infection in Cotton Leaves Using Hyperspectral Imaging

Yan

Jiao

et al. 2021

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…However, since the spectral and spatial features are extracted independently, the mutual excitation is generally ignored. Three-dimensional CNNs have allowed the extraction of deep spectral-spatial features by using a 3D convolution kernel [22][23][24]. In [24], a 3D CNN and the Jeffries-Matusita distance were introduced to select effective bands and reduce the redundancy of spectral information.…”

Section: Introductionmentioning

confidence: 99%

“…Three-dimensional CNNs have allowed the extraction of deep spectral-spatial features by using a 3D convolution kernel [22][23][24]. In [24], a 3D CNN and the Jeffries-Matusita distance were introduced to select effective bands and reduce the redundancy of spectral information. In [22], 3D convolution was combined with a traditional self-encoder and wavelet technology to maximize the extraction of spectral-spatial structure information.…”

Section: Introductionmentioning

confidence: 99%

Triple-Attention-Based Parallel Network for Hyperspectral Image Classification

Zhu

Zheng

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Convolutional neural networks have been highly successful in hyperspectral image classification owing to their unique feature expression ability. However, the traditional data partitioning strategy in tandem with patch-wise classification may lead to information leakage and result in overoptimistic experimental insights. In this paper, we propose a novel data partitioning scheme and a triple-attention parallel network (TAP-Net) to enhance the performance of HSI classification without information leakage. The dataset partitioning strategy is simple yet effective to avoid overfitting, and allows fair comparison of various algorithms, particularly in the case of limited annotated data. In contrast to classical encoder–decoder models, the proposed TAP-Net utilizes parallel subnetworks with the same spatial resolution and repeatedly reuses high-level feature maps of preceding subnetworks to refine the segmentation map. In addition, a channel–spectral–spatial-attention module is proposed to optimize the information transmission between different subnetworks. Experiments were conducted on three benchmark hyperspectral datasets, and the results demonstrate that the proposed method outperforms state-of-the-art methods with the overall accuracy of 90.31%, 91.64%, and 81.35% and the average accuracy of 93.18%, 87.45%, and 78.85% over Salinas Valley, Pavia University and Indian Pines dataset, respectively. It illustrates that the proposed TAP-Net is able to effectively exploit the spatial–spectral information to ensure high performance.

show abstract

“…Deep neural network (DNN) has become the focus of attention for their robust superior in remote sensing image classification [12]. End-to-end convolutional neural network (CNN) was the main feature extraction tool to interpret VHR remote sensing image [13]- [16]. Currently, more challenge deep models were proposed to further improve the classification performance.…”

Section: Introductionmentioning

confidence: 99%

Improved Metric Learning With the CNN for Very-High-Resolution Remote Sensing Image Classification

Cheng

Shen

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

The number of labeled samples has a great impact on the classification results of very high-resolution (VHR) remote sensing image. However, the acquisition of available labeled samples is difficult and time-consuming. Faced with the limited labeled samples on high-resolution remote sensing image, semisupervised method becomes an effective way. In semi-supervised learning, accurate similarity prediction between unlabeled and labeled samples is very important. However, reliable similarity prediction between high-dimensional features is difficult. For more reliable similarity prediction for high-dimensional feature, a novel semi-supervised classification framework via improved metric learning (IML) with convolutional neural network (CNN) is proposed. In the proposed method, a novel trainable metric learning network is designed to accurately evaluate the similarity between high-dimension features. The vector distance parameter solving problem is transformed into a neural network design problem, which can automatically calculate parameters by BP algorithm. Finally, the pixel constraint mechanism is introduced to select the unlabeled samples. Experimental results conducted on three VHR remote sensing images, including Aerial, Xi'an, and Pavia University, and the results present that the proposed method performs better than the compared state-of-the-art methods.

show abstract

Classification of hyperspectral imagery with a 3D convolutional neural network and J-M distance

Cited by 31 publications

References 23 publications

Combining Multi-Dimensional Convolutional Neural Network (CNN) With Visualization Method for Detection of Aphis gossypii Glover Infection in Cotton Leaves Using Hyperspectral Imaging

Combining Multi-Dimensional Convolutional Neural Network (CNN) With Visualization Method for Detection of Aphis gossypii Glover Infection in Cotton Leaves Using Hyperspectral Imaging

Triple-Attention-Based Parallel Network for Hyperspectral Image Classification

Improved Metric Learning With the CNN for Very-High-Resolution Remote Sensing Image Classification

Contact Info

Product

Resources

About