Hyperspectral and LiDAR Data Fusion Using Extinction Profiles and Deep Convolutional Neural Network

Ghamisi, Pedram; Höfle, Bernhard; Zhu, Xiao Xiang

doi:10.1109/jstars.2016.2634863

Cited by 191 publications

(138 citation statements)

References 53 publications

Supporting

Mentioning

138

Contrasting

Order By: Relevance

“…Finally, the averaged spectral vector which actually includes the spatial contextual information was processed by the following deep network. Furthermore, instead of directly exploiting the spatial information within a neighboring window, some different filtering methods (e.g., Gobar filtering [78], [79], attribute filtering [80], extinction filtering [81], and rolling guidance filtering [82]) were introduced to process the original hyperspectral data aiming to extract more effective spatial features. These filter-based works combine the deep learning techniques with other spatial-feature extraction methods and deliver more accurate classification results.…”

Section: Spectral-spatial-feature Networkmentioning

confidence: 99%

Deep Learning for Hyperspectral Image Classification: An Overview

Li¹,

Song²,

Fang³

et al. 2019

IEEE Trans. Geosci. Remote Sensing

Self Cite

1,340

452

View full text Add to dashboard Cite

Hyperspectral image (HSI) classification has become a hot topic in the field of remote sensing. In general, the complex characteristics of hyperspectral data make the accurate classification of such data challenging for traditional machine learning methods. In addition, hyperspectral imaging often deals with an inherently nonlinear relation between the captured spectral information and the corresponding materials. In recent years, deep learning has been recognized as a powerful feature-extraction tool to effectively address nonlinear problems and widely used in a number of image processing tasks. Motivated by those successful applications, deep learning has also been introduced to classify HSIs and demonstrated good performance. This survey paper presents a systematic review of deep learning-based HSI classification literatures and compares several strategies for this topic. Specifically, we first summarize the main challenges of HSI classification which cannot be effectively overcome by traditional machine learning methods, and also introduce the advantages of deep learning to handle these problems. Then, we build a framework which divides the corresponding works into spectralfeature networks, spatial-feature networks, and spectral-spatialfeature networks to systematically review the recent achievements in deep learning-based HSI classification. In addition, considering the fact that available training samples in the remote sensing field are usually very limited and training deep networks require a large number of samples, we include some strategies to improve classification performance, which can provide some guidelines for future studies on this topic. Finally, several representative deep learning-based classification methods are conducted on real HSIs in our experiments.

show abstract

Section: Spectral-spatial-feature Networkmentioning

confidence: 99%

Deep Learning for Hyperspectral Image Classification: An Overview

Li¹,

Song²,

Fang³

et al. 2019

IEEE Trans. Geosci. Remote Sensing

Self Cite

1,340

452

View full text Add to dashboard Cite

show abstract

“…SVM classifiers with radial basis functions using extended multi-attribute profiles [13] and extended multi-extinction profiles [14], which were called EMAP-SVMs and EMEP-SVMs for short, were used for comparison. We used same parameters as [12] to ensure the effectiveness of EMAPs.…”

Section: A Data Description and Experimental Settingsmentioning

confidence: 99%

“…Besides we also conducted experiments on standard training and test samples of Houston data set. Detailed information about the number of standard training and test samples can be found in [14]. In this case, basic structures of the model remained the same except that a smaller neighborhood window (11×11) was adopted for both spectral and LiDAR networks.…”

Section: ) Classification Performances After Data Fusionmentioning

confidence: 99%

Deep Fusion of Remote Sensing Data for Accurate Classification

Chen

Ghamisi

et al. 2017

IEEE Geosci. Remote Sensing Lett.

Self Cite

200

118

View full text Add to dashboard Cite

The multisensory fusion of remote sensing data has obtained a great attention in recent years. In this letter, we propose a new feature fusion framework based on deep neural networks (DNNs). The proposed framework employs deep convolutional neural networks (CNNs) to effectively extract features of multi-/hyper-spectral and light detection and ranging (LiDAR) data. Then, a fully connected DNN is designed to fuse the heterogeneous features obtained by the previous CNNs. Through the aforementioned deep networks, one can extract the discriminant and invariant features of remote sensing data, which are useful for further processing. At last, logistic regression is used to produce the final classification results. Dropout and batch normalization strategies are adopted in the deep fusion framework to further improve classification accuracy. The obtained results reveal that the proposed deep fusion model provides competitive results in terms of classification accuracy. Furthermore, the proposed deep learning idea opens a new window for future remote sensing data fusion. Index Terms-Convolutional neural network (CNN), data fusion, deep neural network (DNN), feature extraction (FE), multispectral image (MSI), hyperspectral image (HSI), light detection and ranging (LiDAR).

show abstract

“…For example, Guan et al [34] used a segmentation technique to isolate tree crowns, and then used a neural network to classify species based on point distribution. In another study, Ghamisi et al [35] applied a 2D CNN to estimate forest attributes from rasterized LiDAR and hyperspectral data. A 2D CNN is designed to scan two-dimensional images, and is only capable of identifying spatial features along two axes.…”

Section: Introductionmentioning

confidence: 99%

The Use of Three-Dimensional Convolutional Neural Networks to Interpret LiDAR for Forest Inventory

Ayrey

Hayes

2018

Remote Sensing

View full text Add to dashboard Cite

Abstract:As light detection and ranging (LiDAR) technology becomes more available, it has become common to use these datasets to generate remotely sensed forest inventories across landscapes. Traditional methods for generating these inventories employ the use of height and proportion metrics to measure LiDAR returns and relate these back to field data using predictive models. Here, we employ a three-dimensional convolutional neural network (CNN), a deep learning technique that scans the LiDAR data and automatically generates useful features for predicting forest attributes. We test the accuracy in estimating forest attributes using the three-dimensional implementations of different CNN models commonly used in the field of image recognition. Using the best performing model architecture, we compared CNN performance to models developed using traditional height metrics. The results of this comparison show that CNNs produced 12% less prediction error when estimating biomass, 6% less in estimating tree count, and 2% less when estimating the percentage of needleleaf trees. We conclude that using CNNs can be a more accurate means of interpreting LiDAR data for forest inventories compared to standard approaches.

show abstract

Hyperspectral and LiDAR Data Fusion Using Extinction Profiles and Deep Convolutional Neural Network

Cited by 191 publications

References 53 publications

Deep Learning for Hyperspectral Image Classification: An Overview

Deep Learning for Hyperspectral Image Classification: An Overview

Deep Fusion of Remote Sensing Data for Accurate Classification

The Use of Three-Dimensional Convolutional Neural Networks to Interpret LiDAR for Forest Inventory

Contact Info

Product

Resources

About