2017 IEEE GRSS Data Fusion Contest
# Nickname Score [%]
1 WXYZ 74.94
2 WXYZ 74.45
3 WXYZ 73.38
4 AGTDA 72.63
5 AGTDA 72.63
6 camilasa 72.38
7 Fabricia 72.21
8 Fabricia 71.88
9 AGTDA 71.54
10 Fabricia 71.36
2015 IEEE GRSS Data Fusion Contest Dataset: Zeebruges
# Nickname Score [%]
1 rit1 87.93
2 rit1 87.91
3 RIT_YS 87.85
4 RIT_YS 85.50
5 rit1 85.22
6 RIT_YS 85.22
7 rit1 84.82
8 rit1 83.63
9 rit1 83.51
10 blesaux 76.56
San Francisco
# Nickname Score [%]
1 Adil 92.50
2 Adil 91.52
3 Adil 91.52
4 Adil 58.02
Flevoland
# Nickname Score [%]
no data
Avon12
# Nickname Score [%]
1 Nirmalan 95.19
2 EonRehman 95.08
3 EonRehman 95.08
4 EonRehman 95.08
5 pete 94.86
6 Tania 94.74
7 Nirmalan 94.70
8 pete 94.59
9 Tania 94.55
10 Nirmalan 94.51
Pavia
# Nickname Score [%]
1 rmkemker 75.69
2 eoguslu 73.06
3 eoguslu 72.97
4 rmkemker 72.41
5 rmkemker 71.08
6 rmkemker 70.68
7 eoguslu 70.53
8 rmkemker 69.63
9 eoguslu 69.50
10 ionur 66.99
Indian Pines
# Nickname Score [%]
1 hakyurek 90.73
2 hakyurek 90.73
3 hakyurek 90.71
4 hakyurek 90.41
5 eoguslu 90.17
6 hakyurek 89.50
7 eoguslu 89.28
8 eoguslu 89.09
9 eoguslu 89.06
10 eoguslu 89.01

GRSS Data and Algorithm Standard Evaluation website

Overview

The Standardized Remote Sensing Data Website of the IEEE Geoscience and Remote Sensing Society (GRSS) provides a set of community data sets and algorithm evaluation standards for use by the Earth observation community to support research, development, and testing of algorithms for remote sensing data products.

The website is aimed at remote sensing scientists, students, and professionals, who wish to evaluate the performances of their image analysis methods on freely available data against undisclosed test samples.

Currently, automated online evaluation of classification results from sample hyperspectral datasets is supported. The system is envisioned to grow to encompass more remote sensing modalities and types of processing results.

The website has been developed within the Standardized Algorithm and Data Evaluation Working Group of the GRSS Image Analysis and Data Fusion Technical Committee.

How to get the data and submit results

  • Register for an account and log in with your username and password.
  • Download the remotely sensed dataset you wish to classify along with the associated training data.
  • Apply your processing methods to generate a classification map and upload it to the website.
  • The website will automatically compute a set of classification accuracy parameters with respect to undisclosed test samples.
  • The top-10 results for each data set are reported on the website. You can also check your personal stats by logging in with your username and password.

Further information and useful hints from other users of this web site can be obtained through the LinkedIn Group of the IADF TC

Best displayed using Mozilla Firefox or Google Chrome. To navigate through the website, it is recommended to use the buttons on the right panel and not the back key.