Robust support vector method for hyperspectral data classification and knowledge discovery

Camps‐Valls, Gustau; Gómez-Chova, L.; Calpe‐Maravilla, Javier; Martín-Guerrero, José D.; Soria-Olivas, Emilio; Alonso, Luis; Moreno, José

doi:10.1109/tgrs.2004.827262

Cited by 241 publications

(104 citation statements)

References 35 publications

Supporting

Mentioning

104

Contrasting

Order By: Relevance

“…Support vector machines (SVMs) are nonparametric discriminative classifiers which typically perform well in classification of hyperspectral data and do not require reduction in dimensionality [35]. A radial basis function (RBF) kernel-based SVM [34] was used as the base learner.…”

Section: B Experimental Designmentioning

confidence: 99%

“…Further, in order to concentrate on the most informative samples within this pool, we explore sample consistency by the clustering assumption [20], [21] Querying those samples could help refine the classification hyperplane, especially for discriminative classifiers such as SVM [35], whose performance heavily relies on the quality of the support vectors around the decision boundary. Also, by avoiding queries of samples from high-density regions where labels are more likely to be consistent, we can avoid inclusion of non-informative/redundant samples into the training pool, thereby reducing the overall sample size required to train a good learner.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Active Learning via Multi-View and Local Proximity Co-Regularization for Hyperspectral Image Classification

Wei

Crawford

2011

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

Abstract-A novel co-regularization framework for active learning is proposed for hyperspectral image classification. The first regularizer explores the intrinsic multi-view information embedded in the hyperspectral data. By adaptively and quantitatively measuring the disagreement level, it focuses only on samples with high uncertainty and builds a contention pool which is a small subset of the overall unlabeled data pool, thereby mitigating the computational cost. The second regularizer is based on the "consistency assumption" and designed on a spatial or the spectral based manifold space. It serves to further focus on the most informative samples within the contention pool by penalizing rapid changes in the classification function evaluated on proximally close samples in a local region. Such changes may be due to the lack of capability of the current learner to describe the unlabeled data. Incorporating manifold learning into the active learning process enforces the clustering assumption and avoids the degradation of the distance measure associated with the original high-dimensional spectral features. One spatial and two local spectral embedding methods are considered in this study, in conjunction with the support vector machine (SVM) classifier implemented with a radial basis function (RBF) kernel. Experiments show excellent performance on AVIRIS and Hyperion hyperspectral data as compared to random sampling and the state-of-the-art SVM SIMPLE .

show abstract

Section: B Experimental Designmentioning

confidence: 99%

mentioning

confidence: 99%

Active Learning via Multi-View and Local Proximity Co-Regularization for Hyperspectral Image Classification

Wei

Crawford

2011

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

show abstract

“…SVM has demonstrated its robustness to outliers and is an excellent classifier when the number of input features is high [12]. The original binary version of SVM aims to find the optimal plane that separates the available data into two classes by maximizing the distance (margins) between the so-called support vectors (i.e., the closest training samples to the optimal hyperplane).…”

Section: Vegetation Index (Vi) Formulamentioning

confidence: 99%

“…Remote sensing image classification is a convenient approach for producing these maps due to advantages in terms of cost, revisit time, and spatial coverage [10]. Indeed, remotely sensed image classification has been successfully applied to produce crop maps in homogeneous areas [11][12][13][14].…”

Section: Introductionmentioning

confidence: 99%

A Cloud-Based Multi-Temporal Ensemble Classifier to Map Smallholder Farming Systems

et al. 2018

View full text Add to dashboard Cite

Smallholder farmers cultivate more than 80% of the cropland area available in Africa. The intrinsic characteristics of such farms include complex crop-planting patterns, and small fields that are vaguely delineated. These characteristics pose challenges to mapping crops and fields from space. In this study, we evaluate the use of a cloud-based multi-temporal ensemble classifier to map smallholder farming systems in a case study for southern Mali. The ensemble combines a selection of spatial and spectral features derived from multi-spectral Worldview-2 images, field data, and five machine learning classifiers to produce a map of the most prevalent crops in our study area. Different ensemble sizes were evaluated using two combination rules, namely majority voting and weighted majority voting. Both strategies outperform any of the tested single classifiers. The ensemble based on the weighted majority voting strategy obtained the higher overall accuracy (75.9%). This means an accuracy improvement of 4.65% in comparison with the average overall accuracy of the best individual classifier tested in this study. The maximum ensemble accuracy is reached with 75 classifiers in the ensemble. This indicates that the addition of more classifiers does not help to continuously improve classification results. Our results demonstrate the potential of ensemble classifiers to map crops grown by West African smallholders. The use of ensembles demands high computational capability, but the increasing availability of cloud computing solutions allows their efficient implementation and even opens the door to the data processing needs of local organizations.

show abstract

“…With the successful application of SVMs to a wide variety of different pattern recognition areas, such as 3D object recognition, image classification, character recognition, etc, SVMs have recently attracted increasing attention in remote-sensed multi/hyper-spectral communities [7,8,9,10,11,12,13,14]. Previous literature applying SVMs to hyperspectral data classification [10,11,12] has shown competitive performance with the best available classification algorithms.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral image fusion using spectrally weighted kernels

Guo

Gunn

Damper

et al. 2005

2005 7th International Conference on Information Fusion

View full text Add to dashboard Cite

show abstract

Robust support vector method for hyperspectral data classification and knowledge discovery

Cited by 241 publications

References 35 publications

Active Learning via Multi-View and Local Proximity Co-Regularization for Hyperspectral Image Classification

Active Learning via Multi-View and Local Proximity Co-Regularization for Hyperspectral Image Classification

A Cloud-Based Multi-Temporal Ensemble Classifier to Map Smallholder Farming Systems

Hyperspectral image fusion using spectrally weighted kernels

Contact Info

Product

Resources

About