| 摘要： | Vegetation classi?cation is a fundamental task in several applica-tions such as forest management, remote sensing-based crop monitoring, and mitigation of plant diseases, digital prototyping of plants, and plant phenotyping, among others. We propose a novel supervoxel-based methodology to accurately detect vegeta-tion from small-footprint full-waveform airborne laser scanning data in urban and mountainous scenes. Mathematically, the full-waveform decomposition and ?tting model based on multiple kernels is presented to generate high-density 3D point clouds and their relevant attributes. The homogeneous supervoxels are then generated by using an enhanced probability density cluster- ing (PDC) algorithm. For each supervoxel, we employ latent Dirichlet allocation to obtain supervoxels features through gener- alisation of geometric and full-waveform features of point clouds. The Support Vector Machine (SVM) and ensemble classi?er ran-dom forest (RF) are used to classify these supervoxels into vegeta- tion and non-vegetation. Our experiments on urban and mountainous scenes demonstrate that our approach achieves an overall accuracy of 98.27% and 96.47% respectively by RF classi?er and achieves an overall accuracy of 98.16% and 97.67% on the same data sets by SVM classi?er. By integrating full-waveform information and more meaningful generalised features, our method outperforms state-of-the-art methods at preserving a trade-o? between missing alarm rate and false alarm rate. |
