The interacting effects of image acquisition date, number of images, classifier, and number of training samples on accuracy of binary classification of impervious cover

摘要

Selecting an appropriate time to acquire imagery for land-cover classification can have a substantial effect on classification accuracy. In this research, multi-temporal analysis of six Landsat images for binary impervious surface classification was conducted to investigate whether specific image dates (beyond simply leaf on/off) have a significant effect on impervious surface classification. We further examined the image date effects across training data sample sizes and classification algorithms. In terms of single time classification, the selection of an appropriate image time had the largest effect on the accuracy with a range of 7% to 10% between the most and least accurate classifications. The greenness transitional time between leaf off and leaf on (May images for our site) offered the highest performance. With multi-temporal images, an additional improvement in classification accuracy, up to 2.4%, was achieved when compared to the best single-time classification, when an advanced classifier (Support Vector Machine) was used. In addition, using all six available images with a reference data sample size as small as 150 pixels, classification accuracy was higher than that of many single-time classifications with substantially larger calibration data sample size. Our study suggests that there is considerable variability in classification accuracy of multi-temporal imagery and image dates should be carefully considered, beyond a general leaf on/off rule. Further testing should be conducted in other sites to identify optimal image dates.