Assessment of the impact of dimensionality reduction methods on information classes and classifiers for hyperspectral image classification by multiple classifier system

Damodaran, Bharath Bhushan; Nidamanuri, ‪Rama Rao

doi:10.1016/j.asr.2013.11.027

Cited by 24 publications

(10 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, we discuss how to select the best set of combinations of spectral bands and acquisition dates from the 36 possible combinations (6 bands and 6 dates). Dimensionality reduction is a common preprocessing step in supervised classification, since it prevents possible redundancy in the datasets and overfitting [20]. Moreover, dimensionality reduction may permit reducing the amount of data (fewer acquisition dates) and computational effort.…”

Section: Variable Selectionmentioning

confidence: 99%

Reliable Crop Identification with Satellite Imagery in the Context of Common Agriculture Policy Subsidy Control

Schmedtmann

Campagnolo

2015

Remote Sensing

View full text Add to dashboard Cite

Agricultural subsidies in the context of the Common Agricultural Policy (CAP) represent over 40% of the EU's yearly budget. To ensure that funds are properly spent, farmers are controlled by National Control and Paying Agencies (NCPA) using tools, such as computer-assisted photo interpretation (CAPI), which aims at identifying crops via remotely-sensed imagery. CAPI is time consuming and requires a large team of skilled photo interpreters. The objective of this study was to develop a reliable control system to partially replace CAPI for crop identification, with the overreaching goal of reducing control costs and completion time. Validated control data provided by the Portuguese Control and Paying Agency and an atmospherically-corrected Landsat ETM+ time series were used to perform parcel-based crop classification, leading to an accuracy of only 68% due to high similarity between crops' spectral signatures. To address this problem, we propose an automatic control system (ACS) that couples crop classification to a reliability requirement. This allows the decision-maker to set a reliability level, which restricts automatic crop identification to parcels that are classified with high certainty. While higher reliability levels reduce the risk of misclassifications, lower levels increase the proportion of automatic control decisions (ACP). With a reliability level of 80%, more than half of the parcels in our study area are automatically identified with an overall accuracy of 84%. In particular, this allows automatically controlling over 85% of all parcels classified as maize, rice, wheat or vineyard.Remote Sens. 2015, 7 9326

show abstract

Section: Variable Selectionmentioning

confidence: 99%

Reliable Crop Identification with Satellite Imagery in the Context of Common Agriculture Policy Subsidy Control

Schmedtmann

Campagnolo

2015

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…, β R ] t is the output weight between the hidden layer nodes and the output nodes, and C (ψ l , v j ) is competence value of the jth validation sample of the classifier ψ l obtained from (9). For all the validation samples j, (14) can represented as…”

Section: Proposed Dcs/des-elm Methods and Spectral-spatial Des Apprmentioning

confidence: 99%

“…Explicitly, the diversity in the MCS is created by defining a diversity measure and optimizing it. Implicitly, diversity can be introduced by selecting a subset of features [10]- [12], training samples manipulation, selecting classifiers from different categories, and different feature extraction methods [13], [14]. However, the diversity constraint alone does not guarantee that the MCS always performs better.…”

mentioning

confidence: 99%

Dynamic Ensemble Selection Approach for Hyperspectral Image Classification With Joint Spectral and Spatial Information

Damodaran

Nidamanuri

Tarabalka

2015

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

Self Cite

View full text Add to dashboard Cite

Accurate generation of a land cover map using hyperspectral data is an important application of remote sensing. Multiple classifier system (MCS) is an effective tool for hyperspectral image classification. However, most of the research in MCS addressed the problem of classifier combination, while the potential of selecting classifiers dynamically is least explored for hyperspectral image classification. The goal of this paper is to assess the potential of dynamic classifier selection/dynamic ensemble selection (DCS/DES) for classification of hyperspectral images, which consists in selecting the best (subset of) optimal classifier(s) relative to each input pixel by exploiting the local information content of the image pixel. In order to have an accurate as well as computationally fast DCS/DES, we proposed a new DCS/DES framework based on extreme learning machine (ELM) regression and a new spectral-spatial classification model, which incorporates the spatial contextual information by using the Markov random field (MRF) with the proposed DES method. The proposed classification framework can be considered as a unified model to exploit the full spectral and spatial information. Classification experiments carried out on two different airborne hyperspectral images demonstrate that the proposed method yields a significant increase in the accuracy when compared to the state-of-the-art approaches.Index Terms-Dynamic classifier selection, dynamic ensemble selection, hyperspectral image classification, markov random field model, multiple classifier system, spectral-spatial classification.

show abstract

“…Remote sensing can quickly obtain surface information, achieve understanding, and study surface characteristics of the spatial distribution through transferring, processing, and analyzing the data. The advantage of high spectral resolution remote sensing is that it can obtain many continuous band spectral images therefore, it achieves a fine description of ground targets and reaches the purpose of identifying features, especially suitable for plant fine classification compared with the conventional remote sensing methods [1][2][3][4][5].…”

Section: Introductionmentioning

confidence: 99%

Improving Hyperspectral Image Classification Method for Fine Land Use Assessment Application Using Semisupervised Machine Learning

Wang¹,

Guo²,

Wang³

et al. 2015

Journal of Spectroscopy

View full text Add to dashboard Cite

Study on land use/cover can reflect changing rules of population, economy, agricultural structure adjustment, policy, and traffic and provide better service for the regional economic development and urban evolution. The study on fine land use/cover assessment using hyperspectral image classification is a focal growing area in many fields. Semisupervised learning method which takes a large number of unlabeled samples and minority labeled samples, improving classification and predicting the accuracy effectively, has been a new research direction. In this paper, we proposed improving fine land use/cover assessment based on semisupervised hyperspectral classification method. The test analysis of study area showed that the advantages of semisupervised classification method could improve the high precision overall classification and objective assessment of land use/cover results.

show abstract

Assessment of the impact of dimensionality reduction methods on information classes and classifiers for hyperspectral image classification by multiple classifier system

Cited by 24 publications

References 33 publications

Reliable Crop Identification with Satellite Imagery in the Context of Common Agriculture Policy Subsidy Control

Reliable Crop Identification with Satellite Imagery in the Context of Common Agriculture Policy Subsidy Control

Dynamic Ensemble Selection Approach for Hyperspectral Image Classification With Joint Spectral and Spatial Information

Improving Hyperspectral Image Classification Method for Fine Land Use Assessment Application Using Semisupervised Machine Learning

Contact Info

Product

Resources

About