Distance Transform-Based Spectral-Spatial Feature Vector for Hyperspectral Image Classification with Stacked Autoencoder

Pixel-wise classification of hyperspectral images (HSIs) from remote sensing data is a common approach for extracting information about scenes. In recent years, approaches based on deep learning techniques have gained wide applicability. An HSI dataset can be viewed either as a collection of images, each one captured at a different wavelength, or as a collection of spectra, each one associated with a specific point (pixel). Enhanced classification accuracy is enabled if the spectral and spatial information are combined in the input vector. This allows simultaneous classification according to spectral type but also according to geometric relationships. In this study, we proposed a novel spatial feature vector which improves accuracies in pixel-wise classification. Our proposed feature vector is based on the distance transform of the pixels with respect to the dominant edges in the input HSI. In other words, we allow the location of pixels within geometric subdivisions of the dataset to modify the contribution of each pixel to the spatial feature vector. Moreover, we used the extended multi attribute profile (EMAP) features to add more geometric features to the proposed spatial feature vector. We have performed experiments with three hyperspectral datasets. In addition to the Salinas and University of Pavia datasets, which are commonly used in HSI research, we include samples from our Surrey BC dataset. Our proposed method results compares favorably to traditional algorithms as well as to some recently published deep learning-based algorithms.

Download Full-text

Spectral–Spatial Feature Extraction for Hyperspectral Image Classification: A Dimension Reduction and Deep Learning Approach

IEEE Transactions on Geoscience and Remote Sensing ◽

10.1109/tgrs.2016.2543748 ◽

2016 ◽

Vol 54 (8) ◽

pp. 4544-4554 ◽

Cited By ~ 404

Author(s):

Wenzhi Zhao ◽

Shihong Du

Keyword(s):

Feature Extraction ◽

Deep Learning ◽

Dimension Reduction ◽

Image Classification ◽

Hyperspectral Image ◽

Learning Approach ◽

Hyperspectral Image Classification ◽

Spatial Feature

Download Full-text

SUPPORT VECTOR CLASSIFICATION OF LAND COVER AND BENTHIC HABITAT FROM HYPERSPECTRAL IMAGES

International Journal of High Speed Electronics and Systems ◽

10.1142/s0129156408005382 ◽

2008 ◽

Vol 18 (02) ◽

pp. 337-348 ◽

Cited By ~ 1

Author(s):

VIDYA MANIAN ◽

MIGUEL VELEZ-REYES

Keyword(s):

Land Cover ◽

Hyperspectral Image ◽

Feature Vector ◽

Hyperspectral Images ◽

Support Vector ◽

Svm Classifier ◽

Benthic Habitat ◽

Hyperspectral Image Classification ◽

Habitat Classification

This paper presents a novel wavelet and support vector machine (SVM) based method for hyperspectral image classification. A 1-D wavelet transform is applied to the pixel spectra, followed by feature extraction and SVM classification. Contrary to the traditional method of using pixel spectra with SVM classifier, our approach not only reduces the dimension of the input pixel feature vector but also improves the classification accuracy. Texture energy features computed in the spectral dimension are mapped using polynomial kernels and used for training the SVM classifier. Results with AVIRIS and other hyperspectral images for land cover and benthic habitat classification are presented. The accuracy of the method with limited training sets and computational burden is assessed.

Download Full-text

Inference in Supervised Spectral Classifiers for On-Board Hyperspectral Imaging: An Overview

Remote Sensing ◽

10.3390/rs12030534 ◽

2020 ◽

Vol 12 (3) ◽

pp. 534 ◽

Cited By ~ 3

Author(s):

Adrián Alcolea ◽

Mercedes E. Paoletti ◽

Juan M. Haut ◽

Javier Resano ◽

Antonio Plaza

Keyword(s):

Energy Consumption ◽

Hyperspectral Image ◽

Machine Learning Techniques ◽

Hyperspectral Image Classification ◽

Comprehensive Overview ◽

Trade Offs ◽

Learning Techniques ◽

Model Size ◽

Computationally Intensive

Machine learning techniques are widely used for pixel-wise classification of hyperspectral images. These methods can achieve high accuracy, but most of them are computationally intensive models. This poses a problem for their implementation in low-power and embedded systems intended for on-board processing, in which energy consumption and model size are as important as accuracy. With a focus on embedded and on-board systems (in which only the inference step is performed after an off-line training process), in this paper we provide a comprehensive overview of the inference properties of the most relevant techniques for hyperspectral image classification. For this purpose, we compare the size of the trained models and the operations required during the inference step (which are directly related to the hardware and energy requirements). Our goal is to search for appropriate trade-offs between on-board implementation (such as model size and energy consumption) and classification accuracy.

Download Full-text

EMAP-DCNN: A NOVEL MATHEMATICAL MORPHOLOGY AND DEEP LEARNING COMBINED FRAMEWORK FOR HYPERSPECTRAL IMAGE CLASSIFICATION

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xliii-b3-2020-479-2020 ◽

2020 ◽

Vol XLIII-B3-2020 ◽

pp. 479-486

Author(s):

H. Teffahi ◽

N. Teffahi

Keyword(s):

Remote Sensing ◽

Feature Extraction ◽

Deep Learning ◽

Image Classification ◽

Mathematical Morphology ◽

Hyperspectral Image ◽

Hyperspectral Image Classification ◽

Remote Sensing Images ◽

Spatial Classification

Abstract. The classification of hyperspectral image (HSI) with high spectral and spatial resolution represents an important and challenging task in image processing and remote sensing (RS) domains due to the problem of computational complexity and big dimensionality of the remote sensing images. The spatial and spectral pixel characteristics have crucial significance for hyperspectral image classification and to take into account these two types of characteristics, various classification and feature extraction methods have been developed to improve spectral-spatial classification of remote sensing images for thematic mapping purposes such as agricultural mapping, urban mapping, emergency mapping in case of natural disasters... In recent years, mathematical morphology and deep learning (DL) have been recognized as prominent feature extraction techniques that led to remarkable spectral-spatial classification performances. Among them, Extended Multi-Attribute Profiles (EMAP) and Dense Convolutional Neural Network (DCNN) are considered as robust and powerful approaches such as the work in this paper is based on these two techniques for the feature extraction stage and used in two combined manners and constructing the EMAP-DCNN frame. The experiments were conducted on two popular datasets: “Indian Pines” and “Huston” hyperspectral datasets. Experimental results demonstrate that the two proposed approaches of the EMAP-DCNN frame denoted EMAP-DCNN 1, EMAP-DCNN 2 provide competitive performances compared with some state-of-the-art spectral-spatial classification methods based on deep learning.

Download Full-text

Hyperspectral Image Classification Using Spatial and Edge Features Based on Deep Learning

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s0218001419540272 ◽

2019 ◽

Vol 33 (09) ◽

pp. 1954027 ◽

Cited By ~ 1

Author(s):

Dexiang Zhang ◽

Jingzhong Kang ◽

Lina Xun ◽

Yu Huang

Keyword(s):

Neural Network ◽

Deep Learning ◽

Spatial Information ◽

Hyperspectral Image ◽

Bilateral Filter ◽

Convolution Neural Network ◽

Hyperspectral Images ◽

Data Sets ◽

Edge Information

In recent years, deep learning has been widely used in the classification of hyperspectral images and good results have been achieved. But it is easy to ignore the edge information of the image when using the spatial features of hyperspectral images to carry out the classification experiments. In order to make full use of the advantages of convolution neural network (CNN), we extract the spatial information with the method of minimum noise fraction (MNF) and the edge information by bilateral filter. The combination of the two kinds of information not only increases the useful information but also effectively removes part of the noise. The convolution neural network is used to extract features and classify for hyperspectral images on the basis of this fused information. In addition, this paper also uses another kind of edge-filtering method to amend the final classification results for a better accuracy. The proposed method was tested on three public available data sets: the University of Pavia, the Salinas, and the Indian Pines. The competitive results indicate that our approach can realize a classification of different ground targets with a very high accuracy.

Download Full-text

I3D: An Improved Three-Dimensional CNN Model on Hyperspectral Remote Sensing Image Classification

Security and Communication Networks ◽

10.1155/2021/5217578 ◽

2021 ◽

Vol 2021 ◽

pp. 1-12

Author(s):

Qian Haizhong

Keyword(s):

Deep Learning ◽

Image Classification ◽

Spatial Information ◽

Hyperspectral Image ◽

Three Dimensional ◽

Spectral Feature ◽

Real Life ◽

Hyperspectral Image Classification ◽

Accuracy Rate ◽

Spatial Coupling

Hyperspectral image data are widely used in real life because it contains rich spectral and spatial information. Hyperspectral image classification is to distinguish different functions based on different features. The computer performs quantitative analysis through the captured image and classifies each pixel in the image. However, the traditional deep learning-based hyperspectral image classification technology, due to insufficient spatial-spectral feature extraction, too many network layers, and complex calculations, leads to large parameters and optimizes hyperspectral images. For this reason, I proposed the I3D-CNN model. The number of classification parameters is large, and the network is complex. This method uses hyperspectral image cubes to directly extract spectral-spatial coupling features, adds depth separable convolution to 3D convolution to reextract spatial features, and extracts the parameter amount and calculation time at the same time. In addition, the model removes the pooling layer to achieve fewer parameters, smaller model scale, and easier training effects. The performance of the I3D-CNN model on the test datasets is better than other deep learning-based methods after comparison. The results show that the model still exhibits strong classification performance, reduces a large number of learning parameters, and reduces complexity. The accuracy rate, average classification accuracy rate, and kappa coefficient are all stable above 95%.

Download Full-text

Double-Branch Multi-Attention Mechanism Network for Hyperspectral Image Classification

Remote Sensing ◽

10.3390/rs11111307 ◽

2019 ◽

Vol 11 (11) ◽

pp. 1307 ◽

Cited By ~ 11

Author(s):

Wenping Ma ◽

Qifan Yang ◽

Yue Wu ◽

Wei Zhao ◽

Xiangrong Zhang

Keyword(s):

Image Classification ◽

Spatial Information ◽

Hyperspectral Image ◽

State Of The Art ◽

Attention Mechanism ◽

Hyperspectral Image Classification ◽

Spatial Feature ◽

Types Of Information ◽

Different Characteristics ◽

Better Than

Recently, Hyperspectral Image (HSI) classification has gradually been getting attention from more and more researchers. HSI has abundant spectral and spatial information; thus, how to fuse these two types of information is still a problem worth studying. In this paper, to extract spectral and spatial feature, we propose a Double-Branch Multi-Attention mechanism network (DBMA) for HSI classification. This network has two branches to extract spectral and spatial feature respectively which can reduce the interference between the two types of feature. Furthermore, with respect to the different characteristics of these two branches, two types of attention mechanism are applied in the two branches respectively, which ensures to extract more discriminative spectral and spatial feature. The extracted features are then fused for classification. A lot of experiment results on three hyperspectral datasets shows that the proposed method performs better than the state-of-the-art method.

Download Full-text

Deep Belief Network for Spectral–Spatial Classification of Hyperspectral Remote Sensor Data

Sensors ◽

10.3390/s19010204 ◽

2019 ◽

Vol 19 (1) ◽

pp. 204 ◽

Cited By ~ 10

Author(s):

Chenming Li ◽

Yongchang Wang ◽

Xiaoke Zhang ◽

Hongmin Gao ◽

Yao Yang ◽

...

Keyword(s):

Feature Extraction ◽

Deep Learning ◽

Optical Sensors ◽

Spatial Information ◽

Hyperspectral Image ◽

Deep Belief Network ◽

Fine Tuning ◽

Sensor Data ◽

Belief Network

With the development of high-resolution optical sensors, the classification of ground objects combined with multivariate optical sensors is a hot topic at present. Deep learning methods, such as convolutional neural networks, are applied to feature extraction and classification. In this work, a novel deep belief network (DBN) hyperspectral image classification method based on multivariate optical sensors and stacked by restricted Boltzmann machines is proposed. We introduced the DBN framework to classify spatial hyperspectral sensor data on the basis of DBN. Then, the improved method (combination of spectral and spatial information) was verified. After unsupervised pretraining and supervised fine-tuning, the DBN model could successfully learn features. Additionally, we added a logistic regression layer that could classify the hyperspectral images. Moreover, the proposed training method, which fuses spectral and spatial information, was tested over the Indian Pines and Pavia University datasets. The advantages of this method over traditional methods are as follows: (1) the network has deep structure and the ability of feature extraction is stronger than traditional classifiers; (2) experimental results indicate that our method outperforms traditional classification and other deep learning approaches.

Download Full-text