Real-time terrain classification using ICESat/GLAS data over Beijing area

For providing a feasible solution for real-time terrain classification using ICESat-2 data, a supervised machine-learning-based real-time terrain classification method using ICESat data is proposed, which is composed of two procedures: offline classifier training and online terrain classification. The first procedure is accomplished by true label generation and feature selection. We advanced a new method of true label generation that uses laser-footprint-scale slopes and waveform characteristics as input data. The laser-footprint-scale slopes are estimated by an improved slope estimation method using elevations of repeat tracks. For feature selection, several waveform characteristics are extracted and the best ones are selected based on experiments. Using the generated true labels and selected features, we train a support vector machine classifier for the second procedure and the performance of online terrain classification is tested using ICESat/GLAS data collected from Beijing area during 2003-2009. The results show that by carefully selecting the features, high classification accuracy (around 92.36%) can be achieved even if the feature dimension is significantly reduced. Furthermore, the classification time of one laser footprint, which is approximately equal to 0.006 s, is less than one laser shot time; thus, the proposed method can be used for real-time terrain classification.