Hyperspectral Image Classification in the Presence of Noisy Labels

Jiang, Junjun; Ma, Jiayi; Wang, Zheng; Chen, Chen; Liu, Xianming

doi:10.1109/tgrs.2018.2861992

Cited by 138 publications

(62 citation statements)

References 52 publications

(68 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the resulting images look realistic, the compensated high-frequency details such as image edges may cause inconsistency with the high-resolution ground truth [22]. Some works show that this issue negatively impacts land cover classification results [23,24]. Edge information is an important feature for object detection [25], and therefore, this information is needed to be preserved in the enhanced images to get good detection accuracy.…”

Section: Problem Description and Motivationmentioning

confidence: 99%

Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network

Rabbi

Ray

Schubert³

et al. 2020

Preprint

View full text Add to dashboard Cite

The detection performance of small objects in remote sensing images is not satisfactory compared to large objects, especially in low-resolution and noisy images. A generative adversarial network (GAN)-based model called enhanced super-resolution GAN (ESRGAN) shows remarkable image enhancement performance, but reconstructed images miss high-frequency edge information. Therefore, object detection performance degrades for small objects on recovered noisy and low-resolution remote sensing images. Inspired by the success of edge enhanced GAN (EEGAN) and ESRGAN, we apply a new edge-enhanced super-resolution GAN (EESRGAN) to improve the image quality of remote sensing images and use different detector networks in an end-to-end manner where detector loss is backpropagated into the EESRGAN to improve the detection performance. We propose an architecture with three components: ESRGAN, Edge Enhancement Network (EEN), and Detection network. We use residual-in-residual dense blocks (RRDB) for both the ESRGAN and EEN, and for the detector network, we use the faster region-based convolutional network (FRCNN) (two-stage detector) and single-shot multi-box detector (SSD) (one stage detector). Extensive experiments on a public (car overhead with context) and a self-assembled (oil and gas storage tank) satellite dataset show superior performance of our method compared to the standalone state-of-the-art object detectors.

show abstract

Section: Problem Description and Motivationmentioning

confidence: 99%

Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network

Rabbi

Ray

Schubert³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…In the last few decades, Hyperspectral image (HSI) has received considerable attention in the field of earth observation and geoinformation science. With the wealth of spatial and spectral information, HSI has been successfully applied in many applications, such as spectral unmixing, environment monitoring, matching and object classification [1][2][3][4][5][6][7][8]. However, due to the low spatial resolution of current HSI sensors and the mixed effects of the ground surface, these factors will seriously affect the accurate interpretation of the image content.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Unmixing with Gaussian Mixture Model and Low-Rank Representation

Jin

Mei

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

Gaussian mixture model (GMM) has been one of the most representative models for hyperspectral unmixing while considering endmember variability. However, the GMM unmixing models only have proper smoothness and sparsity prior constraints on the abundances and thus do not take into account the possible local spatial correlation. When the pixels that lie on the boundaries of different materials or the inhomogeneous region, the abundances of the neighboring pixels do not have those prior constraints. Thus, we propose a novel GMM unmixing method based on superpixel segmentation (SS) and low-rank representation (LRR), which is called GMM-SS-LRR. we adopt the SS in the first principal component of HSI to get the homogeneous regions. Moreover, the HSI to be unmixed is partitioned into regions where the statistical property of the abundance coefficients have the underlying low-rank property. Then, to further exploit the spatial data structure, under the Bayesian framework, we use GMM to formulate the unmixing problem, and put the low-rank property into the objective function as a prior knowledge, using generalized expectation maximization to solve the objection function. Experiments on synthetic datasets and real HSIs demonstrated that the proposed GMM-SS-LRR is efficient compared with other current popular methods.

show abstract

“…In [29], superpixel-level principal component analysis (SuperPCA) is presented as a spectral-spatial dimensionality reduction approach to extract the reduced features for HSIs, in which the spatial information are taken into consideration by superpixel segmentation. The approach of Jiang et al [30] incorporates the superpixel based spatial information to remove the samples with noisy labels. The above-mentioned approaches demonstrate that superpixel segmentation is a useful method to refine the spatial information for HSI analysis.…”

Section: Introductionmentioning

confidence: 99%

Spectral-Spatial Hyperspectral Image Classification with Superpixel Pattern and Extreme Learning Machine

et al. 2019

View full text Add to dashboard Cite

Spectral-spatial classification of hyperspectral images (HSIs) has recently attracted great attention in the research domain of remote sensing. It is well-known that, in remote sensing applications, spectral features are the fundamental information and spatial patterns provide the complementary information. With both spectral features and spatial patterns, hyperspectral image (HSI) applications can be fully explored and the classification performance can be greatly improved. In reality, spatial patterns can be extracted to represent a line, a clustering of points or image texture, which denote the local or global spatial characteristic of HSIs. In this paper, we propose a spectral-spatial HSI classification model based on superpixel pattern (SP) and kernel based extreme learning machine (KELM), called SP-KELM, to identify the land covers of pixels in HSIs. In the proposed SP-KELM model, superpixel pattern features are extracted by an advanced principal component analysis (PCA), which is based on superpixel segmentation in HSIs and used to denote spatial information. The KELM method is then employed to be a classifier in the proposed spectral-spatial model with both the original spectral features and the extracted spatial pattern features. Experimental results on three publicly available HSI datasets verify the effectiveness of the proposed SP-KELM model, with the performance improvement of 10% over the spectral approaches.

show abstract

Hyperspectral Image Classification in the Presence of Noisy Labels

Cited by 138 publications

References 52 publications

Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network

Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network

Hyperspectral Unmixing with Gaussian Mixture Model and Low-Rank Representation

Spectral-Spatial Hyperspectral Image Classification with Superpixel Pattern and Extreme Learning Machine

Contact Info

Product

Resources

About