Hyperspectral and LiDAR Data Classification Using Kernel Collaborative Representation Based Residual Fusion

Ge, Chiru; Du, Qian; Li, Wei; Li, Yunsong; Sun, Weiwei

doi:10.1109/jstars.2019.2913206

Cited by 37 publications

(19 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the literature, many techniques for HSIs and LiDAR data fusion have been developed for the purpose of classification [22]- [27]. Concretely, HSIs and LiDAR data fusion methods can be categorized into pixel-based, feature-based, and decision-based.…”

Section: Introductionmentioning

confidence: 99%

Multiple Feature-Based Superpixel-Level Decision Fusion for Hyperspectral and LiDAR Data Classification

Jia

Zhan

Zhang

et al. 2021

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Multiple Feature-Based Superpixel-Level Decision Fusion for Hyperspectral and LiDAR Data Classification

Jia

Zhan

Zhang

et al. 2021

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…In the decision level fusion, the traditional fusion method is max voting fusion strategy [25], but voting can result in rough results. Recently, the residual fusion strategy of the collaborative representationbased classifier is proposed [30], with two sensitive parameters be adjusted during the fusion process.…”

Section: Introductionmentioning

confidence: 99%

“…For LiDAR images, shape and texture information are extracted by spatial feature extraction algorithms. Here, extinction profile (EP) and local binary pattern (LBP) are extracted as spatial features due to their effectiveness [30]. Recently, the spectral-spatial residual network (SSRN) is proposed for HSI classification [38].…”

Section: Introductionmentioning

confidence: 99%

Deep Residual Network-Based Fusion Framework for Hyperspectral and LiDAR Data

Sun

et al. 2021

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

Self Cite

View full text Add to dashboard Cite

This paper presents a deep residual network-based fusion framework for hyperspectral and LiDAR data. In this framework, three new fusion methods are proposed, which are the residual network-based deep feature fusion (RNDFF), the residual network-based probability reconstruction fusion (RNPRF) and the residual network-based probability multiplication fusion (RNPMF). The three methods use extinction profile (EP), local binary pattern (LBP), and deep residual network. Specifically, EP and LBP features are extracted from two sources and stacked as spatial features. For RNDFF, the deep features of each source are extracted by a deep residual network, and then the deep features are stacked to create the fusion features which are classified by softmax classifier. For RNPRF, the deep features of each source are input to the softmax classifier to obtain the probability matrices, and then the probability matrices are fused by weighted addition to producing the final label assignment. For RNPMF, the probability matrices are fused by array multiplication. Experimental results demonstrate that the classification performance of the proposed methods significantly outperform existing methods in hyperspectral and LiDAR data fusion.

show abstract

“…Xia et al combined hyperspectral image (HSI) and DSM by using integrated classifiers to process morphological features and classify them [19]. In 2019, Ge et al proposed a new framework for fusion of HSI and LiDAR data based on the extinction profiles, local binary pattern (LBP), and kernel collaborative representation classification [20]. Wang et al used spatial transformation network(STN) and densely connected convolutional network (DenseNet) are combined to form STN-DenseNet, which makes the input data adaptively deform according to the network needs, making full use of all information from the front layers of the network [21].…”

Section: Introductionmentioning

confidence: 99%

A Novel LiDAR Data Classification Algorithm Combined CapsNet with ResNet

Wang

et al. 2020

Sensors

View full text Add to dashboard Cite

LiDAR data contain feature information such as the height and shape of the ground target and play an important role for land classification. The effect of convolutional neural network (CNN) for feature extraction on LiDAR data is very significant, however CNN cannot resolve the spatial relationship of features adequately. The capsule network (CapsNet) can identify the spatial variations of features and is widely used in supervised learning. In this article, the CapsNet is combined with the residual network (ResNet) to design a deep network-ResCapNet for improving the accuracy of LiDAR classification. The capsule network represents the features by vectors, which can account for the direction of the features and the relative position between the features. Therefore, more detailed feature information can be extracted. ResNet protects the integrity of information by passing input information to the output directly, which can solve the problem of network degradation caused by information loss in the traditional CNN propagation process to a certain extent. Two different LiDAR data sets and several classic machine learning algorithms are used for comparative experiments. The experimental results show that ResCapNet proposed in this article `improve the performance of LiDAR classification.

show abstract

Hyperspectral and LiDAR Data Classification Using Kernel Collaborative Representation Based Residual Fusion

Cited by 37 publications

References 39 publications

Multiple Feature-Based Superpixel-Level Decision Fusion for Hyperspectral and LiDAR Data Classification

Multiple Feature-Based Superpixel-Level Decision Fusion for Hyperspectral and LiDAR Data Classification

Deep Residual Network-Based Fusion Framework for Hyperspectral and LiDAR Data

A Novel LiDAR Data Classification Algorithm Combined CapsNet with ResNet

Contact Info

Product

Resources

About