A Fixed-Threshold Approach to Generate High-Resolution Vegetation Maps for IKONOS Imagery

Cheng, Wen-Chun; Chang, Jyh-Chian; Chang, Chien-Ping; Su, Yu Xiang; Tu, Te-Ming

doi:10.3390/s8074308

Cited by 29 publications

(20 citation statements)

References 10 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, a threshold of NDVI < 0.4 and <0.5 was used to mask all non-tree features for winter (2012) and summer image (2011) respectively. The method was chosen because it is basic and easy to implement (Cheng et al, 2008).…”

Section: Discussionmentioning

confidence: 99%

Potential to monitor plant stress using remote sensing tools

Ramoelo

Dzikiti

Deventer

et al. 2015

Journal of Arid Environments

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Potential to monitor plant stress using remote sensing tools

Ramoelo

Dzikiti

Deventer

et al. 2015

Journal of Arid Environments

View full text Add to dashboard Cite

“…It indicates that it is easier to discriminate class i from class j. This measure can be extended from two classes to M (M > 2) classes by averaging the separability value of each pair of classes, as seen in Equation (6).…”

Section: Scatter-matrix-based Feature Selectionmentioning

confidence: 99%

“…In practical applications, the first step required is to discriminate the crop of interest from the other objects and determine its planting area. Usually, it is easy to distinguish vegetated areas from other surface types by setting a threshold of normalized difference vegetation index (NDVI) [6,7]. As to the discrimination of different vegetation types using hyperspectral images, this is a typical hyperspectral image classification problem.…”

Section: Introductionmentioning

confidence: 99%

An Improved Combination of Spectral and Spatial Features for Vegetation Classification in Hyperspectral Images

Zhao

Wang

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

Due to the advances in hyperspectral sensor technology, hyperspectral images have gained great attention in precision agriculture. In practical applications, vegetation classification is usually required to be conducted first and then the vegetation of interest is discriminated from the others. This study proposes an integrated scheme (SpeSpaVS_ClassPair_ScatterMatrix) for vegetation classification by simultaneously exploiting image spectral and spatial information to improve vegetation classification accuracy. In the scheme, spectral features are selected by the proposed scatter-matrix-based feature selection method (ClassPair_ScatterMatrix). In this method, the scatter-matrix-based class separability measure is calculated for each pair of classes and then averaged as final selection criterion to alleviate the problem of mutual redundancy among the selected features, based on the conventional scatter-matrix-based class separability measure (AllClass_ScatterMatrix). The feature subset search is performed by the sequential floating forward search method. Considering the high spectral similarity among different green vegetation types, Gabor features are extracted from the top two principal components to provide complementary spatial features for spectral features. The spectral features and Gabor features are stacked into a feature vector and then the ClassPair_ScatterMatrix method is used on the formed vector to overcome the over-dimensionality problem and select discriminative features for vegetation classification. The final features are fed into support vector machine classifier for classification. To verify whether the ClassPair_ScatterMatrix method could well avoid selecting mutually redundant features, the mean square correlation coefficients were calculated for the ClassPair_ScatterMatrix method and AllClass_ScatterMatrix method. The experiments were conducted on a widely used agricultural hyperspectral image. The experimental results showed that (1) the The proposed ClassPair_ScatterMatrix method could better alleviate the problem of selecting mutually redundant features, compared to the AllClass_ScatterMatrix method; (2) compared with the representative mutual information-based feature selection methods, the scatter-matrix-based feature selection methods generally achieved higher classification accuracies, and the ClassPair_ScatterMatrix method especially, produced the highest classification accuracies with respect to both data sets (87.2% and 90.1%); and (3) the proposed integrated scheme produced higher classification accuracy, compared with the decision fusion of spectral and spatial features and the methods only involving spectral

show abstract

“…In [7], a fixed threshold approach generating highresolution vegetation maps for IKONOS imagery was proposed. In this technique an extended Tasseled Cap Transformation (TCT) is used to produce a vegetation map, and then a highresolution version of this map is obtained after an Intensity-Hue-Saturation (IHS) based fusion method [9].…”

Section: Vegetation Extraction For Ikonos Imagerymentioning

confidence: 99%

“…In recent studies vegetation indices and extraction applications are proposed. In [7], the authors presented a fixed-threshold vegetation index (VTCmap) based on the extended Tasseled Cap transformation (TCT). Then it is applied to extract vegetation from the fused images.…”

Section: Introductionmentioning

confidence: 99%

A high-resolution index for vegetation extraction in IKONOS images

El-Mezouar

Taleb

Kpalma

et al. 2010

Remote Sensing for Agriculture, Ecosystems, and Hydrology XII

View full text Add to dashboard Cite

Abstract. In monitoring vegetation change and urban planning, the measure and the mapping of the green vegetation over the Earth play an important role. The normalized difference vegetation index (NDVI) is the most popular approach to generate vegetation maps for remote sensing imagery. Unfortunately, the NDVI generates low-resolution vegetation maps. Highresolution imagery, such as IKONOS imagery, can be used to overcome this weakness leading to better classification accuracy. Hence, it is important to derive a vegetation index providing the high-resolution data. Various scientific researchers have proposed methods based on high-resolution vegetation indices. These methods use image fusion to generate high-resolution vegetation maps. IKONOS produces high-resolution panchromatic (Pan) images and low-resolution multispectral (MS) images. Generally, for the image fusion purpose, the conventional linear interpolation bicubic scheme is used to resize the lowresolution images. This scheme fails around edges and consequently produces blurred edges and annoying artefacts in interpolated images. This study presents a new index that provides high-resolution vegetation maps for IKONOS imagery. This vegetation index (HRNDVI: High Resolution NDVI) is based on a new derived formula including the high-resolution information. We use an artefact free image interpolation method to up sample the MS images so that they have the same size as that of the Pan images. The HRNDVI is then computed by using the resampled MS and the Pan images. The proposed vegetation index takes the advantage of the high spatial resolution information of Pan images to generate artefact free vegetation maps. Visual analysis demonstrates that this index is promising and performs well in vegetation extraction and visualization.

show abstract

A Fixed-Threshold Approach to Generate High-Resolution Vegetation Maps for IKONOS Imagery

Cited by 29 publications

References 10 publications

Potential to monitor plant stress using remote sensing tools

Potential to monitor plant stress using remote sensing tools

An Improved Combination of Spectral and Spatial Features for Vegetation Classification in Hyperspectral Images

A high-resolution index for vegetation extraction in IKONOS images

Contact Info

Product

Resources

About