Joint Alternate Small Convolution and Feature Reuse for Hyperspectral Image Classification

A hyperspectral image (HSI) contains fine and rich spectral information and spatial information of ground objects, which has great potential in applications. It is also widely used in precision agriculture, marine monitoring, military reconnaissance and many other fields. In recent years, a convolutional neural network (CNN) has been successfully used in HSI classification and has provided it with outstanding capacity for improving classification effects. To get rid of the bondage of strong correlation among bands for HSI classification, an effective CNN architecture is proposed for HSI classification in this work. The proposed CNN architecture has several distinct advantages. First, each 1D spectral vector that corresponds to a pixel in an HSI is transformed into a 2D spectral feature matrix, thereby emphasizing the difference among samples. In addition, this architecture can not only weaken the influence of strong correlation among bands on classification, but can also fully utilize the spectral information of hyperspectral data. Furthermore, a 1 × 1 convolutional layer is adopted to better deal with HSI information. All the convolutional layers in the proposed CNN architecture are composed of small convolutional kernels. Moreover, cascaded composite layers of the architecture consist of 1 × 1 and 3 × 3 convolutional layers. The inputs and outputs of each composite layer are stitched as the inputs of the next composite layer, thereby accomplishing feature reuse. This special module with joint alternate small convolution and feature reuse can extract high-level features from hyperspectral data meticulously and comprehensively solve the overfitting problem to an extent, in order to obtain a considerable classification effect. Finally, global average pooling is used to replace the traditional fully connected layer to reduce the model parameters and extract high-dimensional features from the hyperspectral data at the end of the architecture. Experimental results on three benchmark HSI datasets show the high classification accuracy and effectiveness of the proposed method.

Download Full-text

Wavelet-based extended morphological profile and deep autoencoder for hyperspectral image classification

International Journal of Wavelets Multiresolution and Information Processing ◽

10.1142/s0219691318500169 ◽

2018 ◽

Vol 16 (03) ◽

pp. 1850016 ◽

Cited By ~ 2

Author(s):

Huiwu Luo ◽

Yuan Yan Tang ◽

Robert P. Biuk-Aghai ◽

Xu Yang ◽

Lina Yang ◽

...

Keyword(s):

Spatial Information ◽

Hyperspectral Image ◽

State Of The Art ◽

Classification Performance ◽

Fine Tuning ◽

Spectral Information ◽

Data Sets ◽

Spatial Description ◽

Hyperspectral Image Classification ◽

High Level

In this paper, we propose a novel scheme to learn high-level representative features and conduct classification for hyperspectral image (HSI) data in an automatic fashion. The proposed method is a collaboration of a wavelet-based extended morphological profile (WTEMP) and a deep autoencoder (DAE) (“WTEMP-DAE”), with the aim of exploiting the discriminative capability of DAE when using WTEMP features as the input. Each part of WTEMP-DAE is ingenious and contributes to the final classification performance. Specifically, in WTEMP-DAE, the spatial information is extracted from the WTEMP, which is then joined with the wavelet denoised spectral information to form the spectral-spatial description of HSI data. The obtained features are fed into DAE as the original input, where the good weights and bias of the network are initialized through unsupervised pre-training. Once the pre-training is completed, the reconstruction layers are discarded and a logistic regression (LR) layer is added to the top of the network to perform supervised fine-tuning and classification. Experimental results on two real HSI data sets demonstrate that the proposed strategy improves classification performance in comparison with other state-of-the-art hand-crafted feature extractors and their combinations.

Download Full-text

Cluster-Wise Weighted NMF for Hyperspectral Images Unmixing with Imbalanced Data

Remote Sensing ◽

10.3390/rs13020268 ◽

2021 ◽

Vol 13 (2) ◽

pp. 268

Author(s):

Xiaochen Lv ◽

Wenhong Wang ◽

Hongfu Liu

Keyword(s):

Spatial Information ◽

Hyperspectral Image ◽

Imbalanced Data ◽

Reconstruction Error ◽

Hyperspectral Data ◽

Weight Matrix ◽

Hyperspectral Images ◽

Mixed Data ◽

Sparsity Constraints ◽

Additional Constraints

Hyperspectral unmixing is an important technique for analyzing remote sensing images which aims to obtain a collection of endmembers and their corresponding abundances. In recent years, non-negative matrix factorization (NMF) has received extensive attention due to its good adaptability for mixed data with different degrees. The majority of existing NMF-based unmixing methods are developed by incorporating additional constraints into the standard NMF based on the spectral and spatial information of hyperspectral images. However, they neglect to exploit the nature of imbalanced pixels included in the data, which may cause the pixels mixed with imbalanced endmembers to be ignored, and thus the imbalanced endmembers generally cannot be accurately estimated due to the statistical property of NMF. To exploit the information of imbalanced samples in hyperspectral data during the unmixing procedure, in this paper, a cluster-wise weighted NMF (CW-NMF) method for the unmixing of hyperspectral images with imbalanced data is proposed. Specifically, based on the result of clustering conducted on the hyperspectral image, we construct a weight matrix and introduce it into the model of standard NMF. The proposed weight matrix can provide an appropriate weight value to the reconstruction error between each original pixel and the reconstructed pixel in the unmixing procedure. In this way, the adverse effect of imbalanced samples on the statistical accuracy of NMF is expected to be reduced by assigning larger weight values to the pixels concerning imbalanced endmembers and giving smaller weight values to the pixels mixed by majority endmembers. Besides, we extend the proposed CW-NMF by introducing the sparsity constraints of abundance and graph-based regularization, respectively. The experimental results on both synthetic and real hyperspectral data have been reported, and the effectiveness of our proposed methods has been demonstrated by comparing them with several state-of-the-art methods.

Download Full-text

Spectral-Spatial Anomaly Detection of Hyperspectral Data Based on Improved Isolation Forest

10.36227/techrxiv.14428880.v3 ◽

2021 ◽

Author(s):

Xiangyu Song ◽

Sunil Aryal ◽

Kai Ming Ting ◽

zhen Liu ◽

Bin He

Keyword(s):

Anomaly Detection ◽

Spatial Information ◽

Hyperspectral Image ◽

Gabor Filter ◽

Poor Performance ◽

Hyperspectral Data ◽

Relative Mass ◽

Anomaly Score ◽

Spectral Anomaly ◽

Isolation Forest

Anomaly detection in hyperspectral image is affected by redundant bands and the limited utilization capacity of spectral-spatial information. In this article, we propose a novel Improved Isolation Forest (IIF) algorithm based on the assumption that anomaly pixels are more susceptible to isolation than the background pixels. The proposed IIF is a modified version of the Isolation Forest (iForest) algorithm, which addresses the poor performance of iForest in detecting local anomalies and anomaly detection in high-dimensional data. Further, we propose a spectral-spatial anomaly detector based on IIF (SSIIFD) to make full use of global and local information, as well as spectral and spatial information. To be specific, first, we apply the Gabor filter to extract spatial features, which are then employed as input to the Relative Mass Isolation Forest (ReMass-iForest) detector to obtain the spatial anomaly score. Next, original images are divided into several homogeneous regions via the Entropy Rate Segmentation (ERS) algorithm, and the preprocessed images are then employed as input to the proposed IIF detector to obtain the spectral anomaly score. Finally, we fuse the spatial and spectral anomaly scores by combining them linearly to predict anomaly pixels. The experimental results on four real hyperspectral data sets demonstrate that the proposed detector outperforms other state-of-the-art methods.

Download Full-text

Mixed 2D/3D Convolutional Network for Hyperspectral Image Super-Resolution

Remote Sensing ◽

10.3390/rs12101660 ◽

2020 ◽

Vol 12 (10) ◽

pp. 1660 ◽

Cited By ~ 2

Author(s):

Qiang Li ◽

Qi Wang ◽

Xuelong Li

Keyword(s):

Spatial Information ◽

Hyperspectral Image ◽

Feature Fusion ◽

Super Resolution ◽

Superior Performance ◽

Spectral Information ◽

Great Success ◽

Convolutional Network ◽

Training Time ◽

Image Super Resolution

Deep learning-based hyperspectral image super-resolution (SR) methods have achieved great success recently. However, there are two main problems in the previous works. One is to use the typical three-dimensional convolution analysis, resulting in more parameters of the network. The other is not to pay more attention to the mining of hyperspectral image spatial information, when the spectral information can be extracted. To address these issues, in this paper, we propose a mixed convolutional network (MCNet) for hyperspectral image super-resolution. We design a novel mixed convolutional module (MCM) to extract the potential features by 2D/3D convolution instead of one convolution, which enables the network to more mine spatial features of hyperspectral image. To explore the effective features from 2D unit, we design the local feature fusion to adaptively analyze from all the hierarchical features in 2D units. In 3D unit, we employ spatial and spectral separable 3D convolution to extract spatial and spectral information, which reduces unaffordable memory usage and training time. Extensive evaluations and comparisons on three benchmark datasets demonstrate that the proposed approach achieves superior performance in comparison to existing state-of-the-art methods.

Download Full-text

An effective hyperspectral image retrieval method using integrated spectral and textural features

Sensor Review ◽

10.1108/sr-10-2014-0716 ◽

2015 ◽

Vol 35 (3) ◽

pp. 274-281 ◽

Cited By ~ 10

Author(s):

Zhenfeng Shao ◽

Weixun Zhou ◽

Qimin Cheng ◽

Chunyuan Diao ◽

Lei Zhang

Keyword(s):

Design Methodology ◽

Spatial Information ◽

Hyperspectral Image ◽

Hyperspectral Data ◽

Textural Features ◽

Washington Dc ◽

Query Image ◽

Retrieval Method ◽

Content Type ◽

Similar Images

Purpose – The purpose of this paper is to improve the retrieval results of hyperspectral image by integrating both spectral and textural features. For this purpose, an improved multiscale opponent representation for hyperspectral texture is proposed to represent the spatial information of the hyperspectral scene. Design/methodology/approach – In the presented approach, end-member signatures are extracted as spectral features by means of the widely used end-member induction algorithm N-FINDR, and the improved multiscale opponent representation is extracted from the first three principal components of the hyperspectral data based on Gabor filters. Then, the combination similarity between query image and other images in the database is calculated, and the first k more similar images are returned in descending order of the combination similarity. Findings – Some experiments are calculated using the airborne hyperspectral data of Washington DC Mall. According to the experimental results, the proposed method improves the retrieval results, especially for image categories that have regular textural structures. Originality/value – The paper presents an effective retrieval method for hyperspectral images.

Download Full-text

New evaluation method to detect physiological stress in fruit trees by airborne hyperspectral image spectroscopy

International Journal of Horticultural Science ◽

10.31421/ijhs/16/1/860 ◽

2010 ◽

Vol 16 (1) ◽

Author(s):

J. Tamás

Keyword(s):

Precision Agriculture ◽

Near Infrared ◽

Evaluation Method ◽

Hyperspectral Image ◽

Physiological Stress ◽

Incident Light ◽

Hyperspectral Data ◽

Data Cube ◽

Infrared Range ◽

Image Spectroscopy

Nowadays airborne remote sensing data are increasingly used in precision agriculture. The fast space-time dependent localization of stresses in orchards, which allows for a more efficient application of horticultural technologies, could lead to improved sustainable precise management. The disadvantage of the near field multi and hyper spectroscopy is the spot sample taking, which can apply independently only for experimental survey in plantations. The traditional satellite images is optionally suitable for precision investigation because of the low spectral and ground resolution on field condition. The presented airborne hyperspectral image spectroscopy reduces above mentioned disadvantages and at the same time provides newer analyzing possibility to the user. In this paper we demonstrate the conditions of data base collection and some informative examination possibility. The estimating of the board band vegetation indices calculated from reflectance is well known in practice of the biomass stress examinations. In this method the N-dimension spectral data cube enables to calculate numerous special narrow band indexes and to evaluate maps. This paper aims at investigating the applied hyperspectral analysis for fruit tree stress detection. In our study, hyperspectral data were collected by an AISADUAL hyperspectral image spectroscopy system, with high (0,5-1,5 m) ground resolution. The research focused on determining of leaves condition in different fruit plantations in the peach orchard near Siófok. Moreover the spectral reflectance analyses could provide more information about plant condition due to changes in the absorption of incident light in the visible and near infrared range of the spectrum.

Download Full-text

Hyperspectral Image Classification Based on Sparse Superpixel Graph

Remote Sensing ◽

10.3390/rs13183592 ◽

2021 ◽

Vol 13 (18) ◽

pp. 3592

Author(s):

Yifei Zhao ◽

Fengqin Yan

Keyword(s):

Classification Accuracy ◽

Spatial Information ◽

Hyperspectral Image ◽

Hyperspectral Images ◽

Spectral Information ◽

Hyperspectral Image Classification ◽

Computational Burden ◽

Large Size ◽

High Classification Accuracy ◽

Good Classification

Hyperspectral image (HSI) classification is one of the major problems in the field of remote sensing. Particularly, graph-based HSI classification is a promising topic and has received increasing attention in recent years. However, graphs with pixels as nodes generate large size graphs, thus increasing the computational burden. Moreover, satisfactory classification results are often not obtained without considering spatial information in constructing graph. To address these issues, this study proposes an efficient and effective semi-supervised spectral-spatial HSI classification method based on sparse superpixel graph (SSG). In the constructed sparse superpixels graph, each vertex represents a superpixel instead of a pixel, which greatly reduces the size of graph. Meanwhile, both spectral information and spatial structure are considered by using superpixel, local spatial connection and global spectral connection. To verify the effectiveness of the proposed method, three real hyperspectral images, Indian Pines, Pavia University and Salinas, are chosen to test the performance of our proposal. Experimental results show that the proposed method has good classification completion on the three benchmarks. Compared with several competitive superpixel-based HSI classification approaches, the method has the advantages of high classification accuracy (>97.85%) and rapid implementation (<10 s). This clearly favors the application of the proposed method in practice.

Download Full-text

Multiple Classifiers and Graph Cut Methods for Spectral Spatial Classification of Hyperspectral Image

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

10.5194/isprsarchives-xl-8-683-2014 ◽

2014 ◽

Vol XL-8 ◽

pp. 683-688

Author(s):

D. B. Bhushan ◽

R. R. Nidamanuri

Keyword(s):

Land Cover ◽

Supervised Classification ◽

Spatial Information ◽

Hyperspectral Image ◽

Contextual Information ◽

Graph Cut ◽

Spectral Information ◽

Cut Method ◽

Multiple Classifier ◽

The One

Hyperspectral image contains fine spectral and spatial resolutions for generating accurate land use and land cover maps. Supervised classification is the one of method used to exploit the information from the hyperspectral image. The traditional supervised classification methods could not be able to overcome the limitations of the hyperspectral image. The multiple classifier system (MCS) has the potential to increase the classification accuracy and reliability of the hyperspectral image. However, the MCS extracts only the spectral information from the hyperspectral image and neglects the spatial contextual information. Incorporating spatial contextual information along with spectral information is necessary to obtain smooth classification maps. Our objective of this paper is to design a methodology to fully exploit the spectral and spatial information from the hyperspectral image for land cover classification using MCS and Graph cut (GC) method. The problem is modelled as the energy minimization problem and solved using &alpha;-expansion based graph cut method. Experiments are conducted with two hyperspectral images and the result shows that the proposed MCS based graph cut method produces good quality classification map.

Download Full-text

A Dual-Path Small Convolution Network for Hyperspectral Image Classification

Remote Sensing ◽

10.3390/rs13173411 ◽

2021 ◽

Vol 13 (17) ◽

pp. 3411

Author(s):

Lanxue Dang ◽

Peidong Pang ◽

Xianyu Zuo ◽

Yang Liu ◽

Jay Lee

Keyword(s):

Hyperspectral Image ◽

Middle Layer ◽

Hyperspectral Data ◽

Model Parameters ◽

Data Sets ◽

Testing Time ◽

Spatial Features ◽

Current State ◽

Proposed Model ◽

Fully Connected

Convolutional neural network (CNN) has shown excellent performance in hyperspectral image (HSI) classification. However, the structure of the CNN models is complex, requiring many training parameters and floating-point operations (FLOPs). This is often inefficient and results in longer training and testing time. In addition, the label samples of hyperspectral data are limited, and a deep network often causes the over-fitting phenomenon. Hence, a dual-path small convolution (DPSC) module is proposed. It is composed of two 1 × 1 small convolutions with a residual path and a density path. It can effectively extract abstract features from HSI. A dual-path small convolution network (DPSCN) is constructed by stacking DPSC modules. Specifically, the proposed model uses a DPSC module to complete the extraction of spectral and spectral–spatial features successively. It then uses a global average pooling layer at the end of the model to replace the conventional fully connected layer to complete the final classification. In the implemented study, all convolutional layers of the proposed network, except the middle layer, use 1 × 1 small convolution, effectively reduced model parameters and increased the speed of feature extraction processes. DPSCN was compared with several current state-of-the-art models. The results on three benchmark HSI data sets demonstrated that the proposed model is of lower complexity, has stronger generalization ability, and has higher classification efficiency.

Download Full-text

Sparse Unmixing for Hyperspectral Image with Nonlocal Low-Rank Prior

Remote Sensing ◽

10.3390/rs11242897 ◽

2019 ◽

Vol 11 (24) ◽

pp. 2897 ◽

Cited By ~ 3

Author(s):

Yuhui Zheng ◽

Feiyang Wu ◽

Hiuk Jae Shim ◽

Le Sun

Keyword(s):

Mixed Model ◽

Linear Mixed Model ◽

Spatial Information ◽

Hyperspectral Image ◽

Simulated Data ◽

Hyperspectral Data ◽

Low Rank ◽

Data Sets ◽

Self Similarity ◽

Model Framework

Hyperspectral unmixing is a key preprocessing technique for hyperspectral image analysis. To further improve the unmixing performance, in this paper, a nonlocal low-rank prior associated with spatial smoothness and spectral collaborative sparsity are integrated together for unmixing the hyperspectral data. The proposed method is based on a fact that hyperspectral images have self-similarity in nonlocal sense and smoothness in local sense. To explore the spatial self-similarity, nonlocal cubic patches are grouped together to compose a low-rank matrix. Then, based on the linear mixed model framework, the nuclear norm is constrained to the abundance matrix of these similar patches to enforce low-rank property. In addition, the local spatial information and spectral characteristic are also taken into account by introducing TV regularization and collaborative sparse terms, respectively. Finally, the results of the experiments on two simulated data sets and two real data sets show that the proposed algorithm produces better performance than other state-of-the-art algorithms.

Download Full-text