Hyperspectral unmixing using deep convolutional autoencoder

Elkholy, Menna M.; Mostafa, Mohammed; Ebied, Hala M.; Tolba, Mohamed F.

doi:10.1080/01431161.2020.1724346

Cited by 32 publications

(15 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2, which is composed of four main phases: preprocessing, training, testing, and evaluation. The proposed workflow was inspired by semantic segmentation due to their booming performance in several applications, such as scene comprehension, 32 processing satellite images, 15,33 and object detection in satellite images. 34 UNet model, 35 which is considered a famous and effective semantic segmentation architecture, is used in the training phase to identify the change regions.…”

Section: Proposed Workflowmentioning

confidence: 99%

“…The availability of satellite instruments, the enormous amount of data acquired, and the availability of computational power has enabled a deeper neural network to introduce a new challenges in the earth science domain. 15,16 Recent advances in DL have demonstrated state-of-the-art results in pattern recognition tasks, mainly in image processing and speech recognition. 17,18 Modern convolutional neural network (CNN) architectures [19][20][21] tend to contain enormous hidden layers and millions of neurons, allowing them to concurrently learn hierarchical features for a broad class of patterns from data and achieve well-tailored models for the targeted application.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hyperspectral change detection based on modification of UNet neural networks

Moustafa

Mohamed

Ahmed

et al. 2021

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

The Earth's surface changes continuously due to several natural and humanmade factors. Efficient change detection (CD) is useful in monitoring and managing different situations. The recent rise in launched hyperspectral platforms provides a diversity of spectrum in addition to the spatial resolution required to meet recent civil applications requirements. Traditional multispectral CD algorithms hardly cope with the complex nature of hyperspectral images and their high dimensionality. To overcome these limitations, a CD deep convolutional neural network (CNN) semantic segmentation-based workflow was proposed. The proposed workflow is composed of four main stages, namely preprocessing, training, testing, and evaluation. Initially, preprocessing is performed to overcome hyperspectral image noise and the high dimensionality problem. Random oversampling (ROS), deep learning, and bagging ensemble were incorporated to handle imbalanced dataset. Also, we evaluated the generality and performance of the original UNet model and four variants of UNet, namely residual UNet, residual recurrent UNet, attention UNet, and attention residual recurrent UNet. Three hyperspectral CD datasets were employed in performance assessment for binary and multiclass change cases; all datasets suffer from class imbalance and small region of interest size. Recurrent residual UNet presented the best performance in both accuracy and inference time. Overall, the obtained results imply that deep CNN segmentation models can be utilized to implement efficient CD for hyperspectral imageries. © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

show abstract

Section: Proposed Workflowmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Hyperspectral change detection based on modification of UNet neural networks

Moustafa

Mohamed

Ahmed

et al. 2021

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

show abstract

“…This problem is solved by applying a transformation MNF or also called cascading PCA [1]. Its most notable difference is that MNF considers noise within the data set, while PCA only considers the variations of each vector [25]. The noise value existing in the dataset is not always constant everywhere, but the variance of the noisy data is greater than the variance of the actual data, so the principal components obtained with MNF are better [1].…”

Section: Minimum Noise Fraction (Mnf)mentioning

confidence: 99%

Pixel Purity Index Applied to the Mapping of Degraded Soils by the Presence of Cangahuas in the Ilaló Volcano, Ecuador

Palacios¹,

Ushiña²,

Carrera³

2021

International Journal on Advanced Science, Engineering and Information Technology

View full text Add to dashboard Cite

“…The concept of auto-encoder was proposed earlier, and was originally applied to high-dimensional complex data processing, which promoted the development of neural networks [42][43][44] . The self-encoder is an unsupervised learning algorithm in the deep learning algorithm, to be more precise, a self-supervised learning algorithm whose label data is derived from the input samples.…”

Section: Automatic Encodermentioning

confidence: 99%

Image Target Recognition Model of Multi- Channel Structure Convolutional Neural Network Training Automatic Encoder

et al. 2020

View full text Add to dashboard Cite

The self-encoder is a typical unsupervised deep learning algorithm. In the field of unsupervised learning, it is very popular with researchers. Therefore, in view of the shortage of labeled training samples, the convolution kernel of a typical convolutional neural network is set by experience, and the network structure is fixed and it is difficult to re-learn later. This paper combines the convolutional neural network and the automatic encoder, and proposes a multi-based the method of integrated network structure to extract the features of the image for recognition. First, the SAE pre-trained CNN model convolution kernel is used to pre-train based on the classic CNN structure. Secondly, input and process image data of different scales to extract image space and spectral features respectively. Then, construct multiple channels, and use different scale filters and sampling intervals for different channels. Finally, after one layer of down sampling, the feature maps obtained from multiple channels are input into the fully connected layer, and after a hidden layer, the features finally used for classification are obtained. Experimental results show that the proposed method uses sparse automatic coding for pre-training time efficiency increased by 50%, and can further improve the recognition accuracy, the highest recognition rate reached 0.985. INDEX TERMS Convolutional neural network; multi-channel; training; automatic encoder; recognition.

show abstract

Hyperspectral unmixing using deep convolutional autoencoder

Cited by 32 publications

References 31 publications

Hyperspectral change detection based on modification of UNet neural networks

Hyperspectral change detection based on modification of UNet neural networks

Pixel Purity Index Applied to the Mapping of Degraded Soils by the Presence of Cangahuas in the Ilaló Volcano, Ecuador

Image Target Recognition Model of Multi- Channel Structure Convolutional Neural Network Training Automatic Encoder

Contact Info

Product

Resources

About