Dimensionality Reduction and Classification of Hyperspectral Image via Multistructure Unified Discriminative Embedding

Luo, Fulin; Zou, Zehua; Liu, Jiamin; Lin, Zhiping

doi:10.1109/tgrs.2021.3128764

Cited by 132 publications

(42 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The theoretical value displayed in Table 4 has been calculated using Equation ( 2) where the distance from the camera fore-optics, h, has been measured with a meter band, giving the value 920 mm. The error shown in the table between the theoretical and the empirical value have been calculated as the percentage absolute difference between both values using Equation (7), where, Th refers to the theoretical value and Emp to the empirical (calculated) value. The deviation between the empirical and theoretical values increases as the distance from the camera to the object gets shorter.…”

Section: Morphological Analysismentioning

confidence: 99%

“…This has led to its use in remote sensing applications in fields such as as defense [ 1 ], security [ 2 ] or mineral identification [ 3 ] just to name a few, as well as in controlled environments such as in laboratories to conduct experiments and studies of particular materials and products [ 4 , 5 ] or in industrial processes, contributing to the screening of the quality of goods in production [ 6 ]. Hyperspectral image processing has been a topic of deep research over the last few decades, as numerous new techniques emerge, from simple spectral index calculations to complex deep learning algorithms, with the purpose of finding a trade-off between results improvements and operations and data simplification [ 7 , 8 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Laboratory Hyperspectral Image Acquisition System Setup and Validation

Morales

Horstrand

Guerra

et al. 2022

Sensors

View full text Add to dashboard Cite

Hyperspectral Imaging (HSI) techniques have demonstrated potential to provide useful information in a broad set of applications in different domains, from precision agriculture to environmental science. A first step in the preparation of the algorithms to be employed outdoors starts at a laboratory level, capturing a high amount of samples to be analysed and processed in order to extract the necessary information about the spectral characteristics of the studied samples in the most precise way. In this article, a custom-made scanning system for hyperspectral image acquisition is described. Commercially available components have been carefully selected in order to be integrated into a flexible infrastructure able to obtain data from any Generic Interface for Cameras (GenICam) compliant devices using the gigabyte Ethernet interface. The entire setup has been tested using the Specim FX hyperspectral series (FX10 and FX17) and a Graphical User Interface (GUI) has been developed in order to control the individual components and visualise data. Morphological analysis, spectral response and optical aberration of these pushbroom-type hyperspectral cameras have been evaluated prior to the validation of the whole system with different plastic samples for which spectral signatures are extracted and compared with well-known spectral libraries.

show abstract

Section: Morphological Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Laboratory Hyperspectral Image Acquisition System Setup and Validation

Morales

Horstrand

Guerra

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…], the result of X 2 after hybrid attention is shown in formula (7). In formula (7), φ(p m,n i )x m,n i represents the enhanced result of each feature x m,n i in X 2 in the spatial and channel dimensions, respectively.…”

Section: Group-wise Hybrid Attentionmentioning

confidence: 99%

“…In recent years, convolutional neural networks (CNNs) have achieved excellent performance in many fields [1][2][3][4][5][6][7]. In particular, in the field of image classification [8][9][10][11], convolutional neural networks have become the most commonly used method.…”

Section: Introductionmentioning

confidence: 99%

A Lightweight Convolutional Neural Network Based on Group-Wise Hybrid Attention for Remote Sensing Scene Classification

et al. 2021

View full text Add to dashboard Cite

With the development of computer vision, attention mechanisms have been widely studied. Although the introduction of an attention module into a network model can help to improve e classification performance on remote sensing scene images, the direct introduction of an attention module can increase the number of model parameters and amount of calculation, resulting in slower model operations. To solve this problem, we carried out the following work. First, a channel attention module and spatial attention module were constructed. The input features were enhanced through channel attention and spatial attention separately, and the features recalibrated by the attention modules were fused to obtain the features with hybrid attention. Then, to reduce the increase in parameters caused by the attention module, a group-wise hybrid attention module was constructed. The group-wise hybrid attention module divided the input features into four groups along the channel dimension, then used the hybrid attention mechanism to enhance the features in the channel and spatial dimensions for each group, then fused the features of the four groups along the channel dimension. Through the use of the group-wise hybrid attention module, the number of parameters and computational burden of the network were greatly reduced, and the running time of the network was shortened. Finally, a lightweight convolutional neural network was constructed based on the group-wise hybrid attention (LCNN-GWHA) for remote sensing scene image classification. Experiments on four open and challenging remote sensing scene datasets demonstrated that the proposed method has great advantages, in terms of classification accuracy, even with a very low number of parameters.

show abstract

“…These methods can provide dense point clouds of the rooftops and facades of the building. Aerial photogrammetry obtains detailed textural patterns of building planar features [10][11][12][13][14][15], and depth cameras acquire the distances from objects to the camera [16][17][18][19]. The LiDAR scanner provides high-density and high-precision geometric structure information of objects from different positions and provides high-quality point cloud data to reconstruct three-dimensional building models [20][21][22].…”

Section: Introductionmentioning

confidence: 99%

Building Plane Segmentation Based on Point Clouds

Gao

Zhou

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Planes are essential features to describe the shapes of buildings. The segmentation of a plane is significant when reconstructing a building in three dimensions. However, there is a concern about the accuracy in segmenting plane from point cloud data. The objective of this paper was to develop an effective segmentation algorithm for building planes that combines the region growing algorithm with the distance algorithm based on boundary points. The method was tested on point cloud data from a cottage and pantry as scanned using a Faro Focus 3D laser range scanner and Matterport Camera, respectively. A coarse extraction of the building plane was obtained from the region growing algorithm. The coplanar points where two planes intersect were obtained from the distance algorithm. The building plane’s optimal segmentation was then obtained by combining the coarse extraction plane points and the corresponding coplanar points. The results show that the proposed method successfully segmented the plane points of the cottage and pantry. The optimal distance thresholds using the proposed method from the uncoarse extraction plane points to each plane boundary point of cottage and pantry were 0.025 m and 0.030 m, respectively. The highest correct rate and the highest error rate of the cottage’s (pantry’s) plane segmentations using the proposed method under the optimal distance threshold were 99.93% and 2.30% (98.55% and 2.44%), respectively. The F1 score value of the cottage’s and pantry’s plane segmentations using the proposed method under the optimal distance threshold reached 97.56% and 95.75%, respectively. This method can segment different objects on the same plane, while the random sample consensus (RANSAC) algorithm causes the plane to become over-segmented. The proposed method can also extract the coplanar points at the intersection of two planes, which cannot be separated using the region growing algorithm. Although the RANSAC-RG method combining the RANSAC algorithm and the region growing algorithm can optimize the segmentation results of the RANSAC (region growing) algorithm and has little difference in segmentation effect (especially for cottage data) with the proposed method, the method still loses coplanar points at some intersection of the two planes.

show abstract

Dimensionality Reduction and Classification of Hyperspectral Image via Multistructure Unified Discriminative Embedding

Cited by 132 publications

References 49 publications

Laboratory Hyperspectral Image Acquisition System Setup and Validation

Laboratory Hyperspectral Image Acquisition System Setup and Validation

A Lightweight Convolutional Neural Network Based on Group-Wise Hybrid Attention for Remote Sensing Scene Classification

Building Plane Segmentation Based on Point Clouds

Contact Info

Product

Resources

About