TY - JOUR

T1 - A label noise tolerant random forest for the classification of remote sensing data based on outdated maps for training

AU - Maas, Alina E.

AU - Rottensteiner, Franz

AU - Heipke, Christian

N1 - Funding information: This work was supported by the German Science Foundation (DFG) under grant HE 1822/35-1. The Graduiertenakademie of Leibniz University Hannover has supported a research stay of the first author, this support is gratefully acknowledged. The Hameln data were provided by the state surveying authorities (Landesamt für Geoinformation und Landesvermessung Niedersachsen, LGLN), Hannover. The Vaihingen dataset was provided by the German Society for Photogrammetry, Remote Sensing and Geoinformation.

PY - 2019/11

Y1 - 2019/11

N2 - Supervised classification of remotely sensed images is a classical method for change detection. The task requires training data containing images with known class labels. If these labels are acquired from an outdated map, the classifier must cope with errors in the training labels. Several papers state that the random forest classifier is robust with respect to these errors (label noise) by design, but for a large amount of label noise or for noise affecting different classes differently this assumption does not necessarily hold. In this paper we suggest an adaptation of the random forest classifier by integrating a model for label noise based on the idea that a training sample should not be assigned to one class only, but to all classes, each with a certain probability. The adapted random forest is embedded in an iterative scheme for the context-based classification of remote sensing data using the outdated map not only to provide the labels of the training samples, but also to support the classification process in unchanged areas. Our experiments are based on five test areas and the results show a higher accuracy using the suggested new method than using the standard random forest.

AB - Supervised classification of remotely sensed images is a classical method for change detection. The task requires training data containing images with known class labels. If these labels are acquired from an outdated map, the classifier must cope with errors in the training labels. Several papers state that the random forest classifier is robust with respect to these errors (label noise) by design, but for a large amount of label noise or for noise affecting different classes differently this assumption does not necessarily hold. In this paper we suggest an adaptation of the random forest classifier by integrating a model for label noise based on the idea that a training sample should not be assigned to one class only, but to all classes, each with a certain probability. The adapted random forest is embedded in an iterative scheme for the context-based classification of remote sensing data using the outdated map not only to provide the labels of the training samples, but also to support the classification process in unchanged areas. Our experiments are based on five test areas and the results show a higher accuracy using the suggested new method than using the standard random forest.

KW - Change detection

KW - Label noise

KW - Random forest

KW - Supervised classification

UR - http://www.scopus.com/inward/record.url?scp=85071309709&partnerID=8YFLogxK

U2 - 10.1016/j.cviu.2019.07.002

DO - 10.1016/j.cviu.2019.07.002

M3 - Article

AN - SCOPUS:85071309709

VL - 188

JO - Computer Vision and Image Understanding

JF - Computer Vision and Image Understanding

SN - 1077-3142

M1 - 102782

ER -