Wilt

Donated on 3/12/2014

High-resolution Remote Sensing data set (Quickbird). Small number of training samples of diseased trees, large number for other land cover. Testing data set from stratified random sample of image.

Dataset Characteristics

Multivariate

Subject Area

Biology

Associated Tasks

Classification

Feature Type

-

# Instances

4889

# Features

-

Dataset Information

Additional Information

This data set contains some training and testing data from a remote sensing study by Johnson et al. (2013) that involved detecting diseased trees in Quickbird imagery. There are few training samples for the 'diseased trees' class (74) and many for 'other land cover' class (4265). The data set consists of image segments, generated by segmenting the pansharpened image. The segments contain spectral information from the Quickbird multispectral image bands and texture information from the panchromatic (Pan) image band. The testing data set is for the row with “Segmentation scale 15” segments and “original multi-spectral image” Spectral information in Table 2 of the reference (i.e. row 5). Please see the reference below for more information on the data set, and please cite the reference if you use this data set. Enjoy! Files training.csv: training data set (4339 image segments) testing.csv: testing data set (500 image segments)

Has Missing Values?

No

Variables Table

Variable NameRoleTypeDescriptionUnitsMissing Values
no
no
no
no
no
no

0 to 6 of 6

Additional Variable Information

class: 'w' (diseased trees), 'n' (all other land cover) GLCM_Pan: GLCM mean texture (Pan band) Mean_G: Mean green value Mean_R: Mean red value Mean_NIR: Mean NIR value SD_Pan: Standard deviation (Pan band)

Reviews

There are no reviews for this dataset yet.

Login to Write a Review
Download
0 citations
3854 views

Creators

Brian Johnson

License

By using the UCI Machine Learning Repository, you acknowledge and accept the cookies and privacy practices used by the UCI Machine Learning Repository.

Read Policy