Automatic Labelling and Selection of Training Samples for High-Resolution Remote Sensing Image Classification over Urban Areas

Remote Sensing

Xin Huang²  Chunlei Weng³  Qikai Lu³  Tiantian Feng⁴  Liangpei Zhang³  Giles M. Foody¹  Norman Kerle¹ 

[1] id="af1-remotesensing-07-15819">1School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, Chi;School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, ChinaThe State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China;College of Surveying and Geo-Informatics, Tongji University, Shanghai 200092, China;

关键词: image classification;    training samples;    maximum likelihood classification;    support vector machine;    active learning;   

DOI  :  10.3390/rs71215819

来源: mdpi

【 摘 要 】

Supervised classification is the commonly used method for extracting ground information from images. However, for supervised classification, the selection and labelling of training samples is an expensive and time-consuming task. Recently, automatic information indexes have achieved satisfactory results for indicating different land-cover classes, which makes it possible to develop an automatic method for labelling the training samples instead of manual interpretation. In this paper, we propose a method for the automatic selection and labelling of training samples for high-resolution image classification. In this way, the initial candidate training samples can be provided by the information indexes and open-source geographical information system (GIS) data, referring to the representative land-cover classes: buildings, roads, soil, water, shadow, and vegetation. Several operations are then applied to refine the initial samples, including removing overlaps, removing borders, and semantic constraints. The proposed sampling method is evaluated on a series of high-resolution remote sensing images over urban areas, and is compared to classification with manually labeled training samples. It is found that the proposed method is able to provide and label a large number of reliable samples, and can achieve satisfactory results for different classifiers. In addition, our experiments show that active learning can further enhance the classification performance, as active learning is used to choose the most informative samples from the automatically labeled samples.

【 授权许可】

CC BY   
© 2015 by the authors; licensee MDPI, Basel, Switzerland.