Crowdsourcing-based application to solve the problem of insufficient training data in deep learning-based classification of satellite images

Abstract

In order to solve insufficient training data problem in remote sensing, a web platform was created so that registered users can generate labeled data for various classes in a dynamic structure. Users were asked to select representative pixel groups for the forest, hazelnut, shadow, soil, tea, and building classes with the polygon tool, and then assign a class label corresponding to each created polygon thanks to the help document displaying descriptive information regarding the locations, colors, textures and distributions of the classes in the image. Crowdsourcing was again used to test the accuracy of the tagged data produced by crowdsourcing. The created data set was overlaid with the original WV-2 image, and the correctness of the labels ​​of the polygons was once visually verified. Finally, the WV-2 image, consisting of 40 patches, was classified with CNN and an average of over 95% accuracy was achieved.

Keywords:

• Training data
• crowdsourcing
• multispectral image classification
• deep learning
• CNN

Acknowledgment

The WorldView-2 Data used in this study was taken from the TUBITAK 1001 project numbered 111Y296.

Disclosure statement

No potential conflict of interest was reported by the authors.