A Sparse Autoencoder Based Hyperspectral Anomaly Detection Algorihtm Using Residual of Reconstruction Error

Chang, Shizhen; Du, Bo; Zhang, Liangpei

doi:10.1109/igarss.2019.8898697

Cited by 31 publications

(18 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…θ = (W (1) , b (1) , W (2) , b (2) ) is the network parameters. The training process of an AE is to find the optimal θ to minimize the reconstruction error J(θ) [39].…”

Section: Stacked Autoencoder (Sae)-based Detectormentioning

confidence: 99%

Background Purification Framework With Extended Morphological Attribute Profile for Hyperspectral Anomaly Detection

Huang

Liu

et al. 2021

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

View full text Add to dashboard Cite

Hyperspectral anomaly detection has attracted extensive interests for its wide use in military and civilian fields, and three main categories of detection methods have been developed successively over past decades, including statistical model-based, representation-based and deep learning-based methods. Most of these algorithms are essentially trying to construct proper background profiles which describe the characteristics of background, then identify the pixels that do not conform to the profiles as anomalies. Apparently, the crucial issue is how to build accurate background profile, however the background profiles constructed by existing methods are not accurate enough. In this paper, a novel and universal background purification framework with extended morphological attribute profiles is proposed. It explore the spatial characteristic of image, and remove suspect anomaly pixels from image to obtain purified background. Moreover, three detectors with this framework covering different categories are also developed. The experiments implemented on four real hyperspectral image demonstrate the background purification framework is effective, universal and suitable. Furthermore, compared with other popular algorithms, the detectors with the framework perform well in terms of accuracy and efficiency.

show abstract

“…θ = (W (1) , b (1) , W (2) , b (2) ) is the network parameters. The training process of an AE is to find the optimal θ to minimize the reconstruction error J(θ) [39].…”

Section: Stacked Autoencoder (Sae)-based Detectormentioning

confidence: 99%

Background Purification Framework With Extended Morphological Attribute Profile for Hyperspectral Anomaly Detection

Huang

Liu

et al. 2021

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

View full text Add to dashboard Cite

show abstract

“…Therefore, some researchers have employed AEs to solve critical image processing challenges such as image classification [24][25][26], clustering [23,27,28], spectral unmixing [29] and image segmentation [30,31]. AEs have also been applied to deal with other important problems such as image fusion [32], change detection [33][34][35], pansharpening [36,37], anomaly detection [38,39], and image retrieval [40]. In recent years, the application of AE for clustering purposes has gained much attention in the RS community.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Deep Learning for Landslide Detection from Multispectral Sentinel-2 Imagery

et al. 2021

View full text Add to dashboard Cite

This paper proposes a new approach based on an unsupervised deep learning (DL) model for landslide detection. Recently, supervised DL models using convolutional neural networks (CNN) have been widely studied for landslide detection. Even though these models provide robust performance and reliable results, they depend highly on a large labeled dataset for their training step. As an alternative, in this paper, we developed an unsupervised learning model by employing a convolutional auto-encoder (CAE) to deal with the problem of limited labeled data for training. The CAE was used to learn and extract the abstract and high-level features without using training data. To assess the performance of the proposed approach, we used Sentinel-2 imagery and a digital elevation model (DEM) to map landslides in three different case studies in India, China, and Taiwan. Using minimum noise fraction (MNF) transformation, we reduced the multispectral dimension to three features containing more than 80% of scene information. Next, these features were stacked with slope data and NDVI as inputs to the CAE model. The Huber reconstruction loss was used to evaluate the inputs. We achieved reconstruction losses ranging from 0.10 to 0.147 for the MNF features, slope, and NDVI stack for all three study areas. The mini-batch K-means clustering method was used to cluster the features into two to five classes. To evaluate the impact of deep features on landslide detection, we first clustered a stack of MNF features, slope, and NDVI, then the same ones plus with the deep features. For all cases, clustering based on deep features provided the highest precision, recall, F1-score, and mean intersection over the union in landslide detection.

show abstract

“…• A reconstruction error is calculated for the training and test data for understanding the gap between normal and abnormal data samples. A base threshold is pivotal for this mapping function [10].…”

Section: Introductionmentioning

confidence: 99%

Anomaly Detection on Medical Images using Autoencoder and Convolutional Neural Network

Siddalingappa¹,

Sekar²

2021

IJACSA

View full text Add to dashboard Cite

Detection of anomalies from the medical image dataset improves prognosis by discovering new facts hidden in the data. The present study aims to discuss anomaly detection using autoencoders and convolutional neural networks. The autoencoder identifies the imbalance between normal and abnormal samples. They create learning models flexible and accurate on training data. The problem is addressed in four stages: 1) training: an autoencoder is initialized with the hyperparameters and trained on the lung cancer CT scan images, 2) test: the autoencoder reconstructs the input from the latent space representation with a slight variation from the original data, indicated by a reconstruction error as Mean Squared Error (MSE), 3) evaluate: the MSE value of the training and test dataset are compared. The MSE values of anomalous data are higher than a base threshold, detecting those as anomalies, 4) validate: the efficiency metrics such as accuracy and MSE scores are used at both training and validation phases. The dataset was further classified as benign and malignant. The accuracy reported for outlier detection and the classification task is 98% and 97.2%. Thus, the proposed autoencoder-based anomaly detection could positively isolate anomalies from the CT scan images of lung cancer.

show abstract

A Sparse Autoencoder Based Hyperspectral Anomaly Detection Algorihtm Using Residual of Reconstruction Error

Cited by 31 publications

References 11 publications

Background Purification Framework With Extended Morphological Attribute Profile for Hyperspectral Anomaly Detection

Background Purification Framework With Extended Morphological Attribute Profile for Hyperspectral Anomaly Detection

Unsupervised Deep Learning for Landslide Detection from Multispectral Sentinel-2 Imagery

Anomaly Detection on Medical Images using Autoencoder and Convolutional Neural Network

Contact Info

Product

Resources

About