Hyperspectral Image Classification Via Double-Branch Multi-Scale Spectral-Spatial Convolution Network

Liang, Lianhui; Zhang, Shaoquan; Li, Jun; Cui, Zhi

doi:10.1109/igarss46834.2022.9884001

Cited by 2 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experimental results show that this method can make full use of the spectral and spatial information of images, and its performance in HSI classification is better than some advanced algorithms. In order to further improve the processing speed of HSI data and improve the calculation efficiency of the model, Liang, L [10] and others use the framework of multiscale spectral-spatial network, which combines 2D octave and 3D CNN, is called MOCNN. The extended experiments on four HSI data sets show that MOCNN method is superior to other HSI classification methods.…”

Section: Introductionmentioning

confidence: 99%

Identification of adulterated honey with different varieties and concentrations based on hyperspectral imaging technology combined with deep learning

Zhang

Wang

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Honey is an important agricultural and sideline product in China, which contains the high nutritional value and commercial value. An advanced honey adulteration identification model can help beekeepers and consumers better identify honey and avoid losses. Given the complex operation and high technical requirements of traditional honey identification experimental instruments, a new model for quickly and efficiently identifying honey adulteration with different kinds and concentrations was developed in this study. Based on the data of adulterated honey with different varieties and concentrations obtained by hyperspectral imaging technology, a large number of regions of interest were randomly selected as samples. Then, the classification model is established by adopting preprocessing methods such as standardization, centralization, multivariate scattering correction, standard variable transformation, first-order difference, and second-order difference, combining the advantages of convolutional neural network and support vector machine. Finally, the accuracy of the results is compared, and D1-CNN-SVM is determined as the best classification prediction model, with an accuracy rate of 100%. At the same time, through the analysis of the confusion matrix of experimental results, this study summarizes the difficulties in identifying adulterated honey of different varieties and concentrations.

show abstract

Section: Introductionmentioning

confidence: 99%

Identification of adulterated honey with different varieties and concentrations based on hyperspectral imaging technology combined with deep learning

Zhang

Wang

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

Multi-Scale Spectral-Spatial Attention Network for Hyperspectral Image Classification Combining 2D Octave and 3D Convolutional Neural Networks

Liang

Zhang

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Traditional convolutional neural networks (CNNs) can be applied to obtain the spectral-spatial feature information from hyperspectral images (HSIs). However, they often introduce significant redundant spatial feature information. The octave convolution network is frequently utilized instead of traditional CNN to decrease spatial redundant information of the network and extend its receptive field. However, the 3D octave convolution-based approaches may introduce extensive parameters and complicate the network. To solve these issues, we propose a new HSI classification approach with a multi-scale spectral-spatial network-based framework that combines 2D octave and 3D CNNs. Our method, called MOCNN, first utilizes 2D octave convolution and 3D DenseNet branch networks with various convolutional kernel sizes to obtain complex spatial contextual feature information and spectral characteristics, separately. Moreover, the channel and the spectral attention mechanisms are, respectively, applied to these two branch networks to emphasize significant feature regions and certain important spectral bands that comprise discriminative information for the categorization. Furthermore, a sample balancing strategy is applied to address the sample imbalance problem. Expansive experiments are undertaken on four HSI datasets, demonstrating that our MOCNN approach outperforms several other methods for HSI classification, especially in scenarios dominated by limited and imbalanced sample data.

show abstract

Hyperspectral Image Classification Via Double-Branch Multi-Scale Spectral-Spatial Convolution Network

Cited by 2 publications

References 11 publications

Identification of adulterated honey with different varieties and concentrations based on hyperspectral imaging technology combined with deep learning

Identification of adulterated honey with different varieties and concentrations based on hyperspectral imaging technology combined with deep learning

Multi-Scale Spectral-Spatial Attention Network for Hyperspectral Image Classification Combining 2D Octave and 3D Convolutional Neural Networks

Contact Info

Product

Resources

About