Assessment of spectral variation between rice canopy components using spectral feature analysis of near-ground hyperspectral imaging data

Zhou, Kai; Cheng, Tao; Deng, Xinqiang; Yao, Xia; Tian, Yongchao; Zhu, Yan; Cao, Weixing

doi:10.1109/whispers.2016.8071699

Cited by 9 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In frequency domain (as described in (2)), the Gabor filter denotes a single valued Gaussian distribution centered at f . Hence, the spatial (or time) and frequency domain Gabor filter representations as described in (1) and 2respectively, provide a streamlined rendition of the general 2D structure devised by Daugman from the Gabor's original 1D elementary function [19]. This implied function enforces a set of selfsimilar filters, i.e.…”

Section: A Gabor Filteringmentioning

confidence: 99%

“…Technological advancements in the hyperspectral remote sensing domain in conjunction with the ease at which data is acquired utilizing various platforms such as drones, has motivated the inception of various hyperspectral remote sensing applications in the area of earth monitoring and observation such as land cover classification for agriculture [1], city planning [2], airborne surveillance [3], weather monitoring [4], climate change observations [5], etc. With the advancements in hyperspectral sensors technology pacing ahead in the direction of light-weight, and portable sensors with significant increase in their spectral, spatial, and temporal resolutions capabilities, there is a crucial necessity for smart Big Data Analysis techniques that can stay abreast of sensor technology advancements.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Study of Spatial–Spectral Feature Extraction Frameworks With 3-D Convolutional Neural Network for Robust Hyperspectral Imagery Classification

Praveen

Menon

2021

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

View full text Add to dashboard Cite

Section: A Gabor Filteringmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Study of Spatial–Spectral Feature Extraction Frameworks With 3-D Convolutional Neural Network for Robust Hyperspectral Imagery Classification

Praveen

Menon

2021

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

View full text Add to dashboard Cite

“…rich spectral signature [1]. Therefore, HSI data containing a large amount of information have been successfully applied in environment monitoring [2], [3], medical treatment [4], [5], agricultural evaluation [6], and geological exploration [7]. These applications are premised on the precise classification of each pixel in the HSI.…”

Section: Introductionmentioning

confidence: 99%

Multiscale Adaptive Convolution for Hyperspectral Image Classification

Ren

et al. 2022

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

View full text Add to dashboard Cite

Convolutional neural network (CNN) is widely used in HSI classification owing to their advantages of spatial-spectral features capture capability, learning depth features as well as their structural flexibility. Nevertheless, the shape of the convolution kernel is fixed, a limitation that leads to shape fixation when modeling different feature in CNN, especially in the edge regions between classes. A multiscale adaptive convolution (MSAC) model is proposed in this paper to overcome this shortcoming. Combining superpixels with the traditional convolutional kernels to form adaptive kernels automatically adjusts the receptive field, suppresses edge noise, and enhances feature learning for different classes. On the basis of adaptive convolution, adaptive convolution units (AConvUs) are constructed. The hierarchical residual structure is constructed by superimposing multiple AConvUs to learn the spatial spectral features of different receptive fields of the HSI, reduce the gradient disappearance and enhance the robustness. The proposed multiscale convolution adjusts the shape of the convolution kernel according to the spatial distribution of different superpixels in HSI. Finally, the MSAC classification framework is constructed by the decision fusion of multiscale adaptive convolution at different superpixel scales, which helps to extract the complementary information of the HSI. The MSAC method's experimental performance on several HSI datasets, including the Gaofen-5 (GF-5), to verify the validity and practicality.

show abstract

“…The number of spectral bands in an HSI depends on the imaging system but usually there are hundreds of bands in an HSI providing a useful source of information. HSIs provide rich datasets that are useful in many areas such as remote sensing [1][2][3][4], agriculture [5], food processing [6][7][8], face recognition [9], etc. In some of these applications such as in most of the remote sensing related areas, the goal is to perform pixel-wise segmentation.…”

Section: Introductionmentioning

confidence: 99%

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

Madani

McIsaac

2021

Remote Sensing

View full text Add to dashboard Cite

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.

show abstract

Assessment of spectral variation between rice canopy components using spectral feature analysis of near-ground hyperspectral imaging data

Cited by 9 publications

References 9 publications

Study of Spatial–Spectral Feature Extraction Frameworks With 3-D Convolutional Neural Network for Robust Hyperspectral Imagery Classification

Study of Spatial–Spectral Feature Extraction Frameworks With 3-D Convolutional Neural Network for Robust Hyperspectral Imagery Classification

Multiscale Adaptive Convolution for Hyperspectral Image Classification

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

Contact Info

Product

Resources

About