Simplified Classification of Multispectral Image Fragments

A simplified approach to classification of multispectral image fragments by their specific spectral features is presented. Application of this approach to discrimination of vegetation areas occupied by the Giant Hogweed species is described and compared with an approach based on calculation of the Consolidated Covariance Image. The proposed method is based on calculation of mean and standard deviation and successive thresholding within certain spectral bands that are found to be informative for the specific task by analysing the ground truth data. It is shown that the method provides close to perfect discrimination of Giant Hogweed from other vegetation areas represented in ground truth data (absence of commission errors together with clear identification of Giant Hogweed fragments in corresponding ground truth regions). Simplicity of the method provides for fast processing of multispectral images from large areas. The proposed approach is perspective for analysis of multispectral images in different application fields where it is possible to choose several informative spectral bands, e.g. in biomedical imaging. DOI: http://dx.doi.org/10.5755/j01.eee.20.6.7286

[1]  Lorenzo Bruzzone,et al.  Fusion of Hyperspectral and LIDAR Remote Sensing Data for Classification of Complex Forest Areas , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[2]  Lorenzo Bruzzone,et al.  Tree species classification in the Southern Alps with very high geometrical resolution multispectral and hyperspectral data , 2011, 2011 3rd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS).

[3]  Atam P. Dhawan,et al.  Transillumination Imaging for Blood Oxygen Saturation Estimation of Skin Lesions , 2012, IEEE Transactions on Biomedical Engineering.

[4]  Aivars Lorencs,et al.  Tree Species Identification in Mixed Baltic Forest Using LiDAR and Multispectral Data , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[5]  Charles A DiMarzio,et al.  Multispectral method for skin imaging: development and validation. , 2007, Applied optics.

[6]  Jana Müllerová,et al.  Remote sensing as a tool for monitoring plant invasions: Testing the effects of data resolution and image classification approach on the detection of a model plant species Heracleum mantegazzianum (giant hogweed) , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[7]  H. Peter White,et al.  Monitoring environmental remediation: Hyperspectral mapping of re-vegetated areas affected by smelting operations in sudbury, Canada , 2010, 2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing.

[8]  R. Jackson,et al.  Interpreting vegetation indices , 1991 .

[9]  I. Mednieks,et al.  Using Consolidated Covariance Image for Discrimination of Habitats , 2012, 2012 13th Biennial Baltic Electronics Conference.

[10]  James H. Everitt,et al.  Using Satellite Data to Map False Broomweed (Ericameria austrotexana) Infestations on South Texas Rangelands , 1993, Weed Technology.