Deep-Learning-Based Classification for DTM Extraction from ALS Point Cloud
Tóm tắt
Airborne laser scanning (ALS) point cloud data are suitable for digital terrain model (DTM) extraction given its high accuracy in elevation. Existing filtering algorithms that eliminate non-ground points mostly depend on terrain feature assumptions or representations; these assumptions result in errors when the scene is complex. This paper proposes a new method for ground point extraction based on deep learning using deep convolutional neural networks (CNN). For every point with spatial context, the neighboring points within a window are extracted and transformed into an image. Then, the classification of a point can be treated as the classification of an image; the point-to-image transformation is carefully crafted by considering the height information in the neighborhood area. After being trained on approximately 17 million labeled ALS points, the deep CNN model can learn how a human operator recognizes a point as a ground point or not. The model performs better than typical existing algorithms in terms of error rate, indicating the significant potential of deep-learning-based methods in feature extraction from a point cloud.
Từ khóa
Tài liệu tham khảo
Mongus, 2012, Parameter-free ground filtering of LiDAR data for automatic DTM generation, ISPRS J. Photogramm. Remote Sens., 67, 1, 10.1016/j.isprsjprs.2011.10.002
Vosselman, 2000, Slope based filtering of laser altimetry data, Int. Arch. Photogram. Remote Sens., 33, 935
Brzank, 2006, Classification of Lidar Data into water and land points in coastal areas, Int. Arch. Photogram. Remote Sens. Spat. Inform. Sci., 36, 197
Zhang, 2003, A progressive morphological filter for removing non-ground measurements from airborne LiDAR data, IEEE Trans. Geosci. Remote Sens., 41, 872, 10.1109/TGRS.2003.810682
Axelsson, 2000, DEM generation from laser scanner data using adaptive TIN models, Proc. Int. Arch. Photogramm. Remote Sens., 33, 110
Kraus, 1998, Determination of terrain models in wooded areas with airborne laser scanner data, ISPRS J. Photogramm. Remote Sens., 53, 193, 10.1016/S0924-2716(98)00009-4
Kamiński, W. (2012). GIS FOR GEOSCIENTISTS, University of Silesia.
Janowski, 2015, Application of the Msplit method for filtering airborne laser scanning datasets to estimate digital terrain models, Int. J. Remote Sens., 36, 2421, 10.1080/01431161.2015.1041617
Janowski, 2011, ALS Data Filtration with Fuzzy Logic, J. Indian Soc. Remote Sens., 39, 591, 10.1007/s12524-011-0130-2
Hu, 2015, Semi-Global Filtering of Airborne LiDAR Data for Fast Extraction of Digital Terrain Models, Remote Sens., 7, 10996, 10.3390/rs70810996
Kubik, T., Paluszynski, W., and Netzel, P. (2008). Classification of Raster Images Using Neural Networks and Statistical Classification Methods, University of Wroclaw.
Meng, L. (1993, January 3–9). Application of neural network in cartographic pattern recognition. Proceedings of the 16th International Cartographic Conference, Cologne, Germnay.
LeCun, 1989, Backpropagation applied to handwritten zip code recognition, Neural Comput., 1, 541, 10.1162/neco.1989.1.4.541
Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 24–27). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA.
Tompson, J., Goroshin, R., Jain, A., LeCun, Y., and Bregler, C. (2015, January 7–12). Efficient object localization using convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.
Taigman, Y., Yang, M., Ranzato, M., and Wolf, L. (2014, January 24–27). Deepface: Closing the gap to human-level performance in face verification. Proceedings of the Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.
He, K., Zhang, X., Ren, S., and Sun, J. (arXiv Preprint, 2015). Deep residual learning for image recognition, arXiv Preprint.
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., and Lecun, Y. (2014, January 14–16). Overfeat: Integrated recognition, localization and detection using convolutional networks. Proceedings of the International Conference on Learning Representations, Banff, AB, Canada.
Waibel, 1989, Phoneme recognition using time-delay neural networks, IEEE Trans. Acoust. Speech Signal Process., 37, 328, 10.1109/29.21701
Collobert, 2011, Natural language processing (almost) from scratch, J. Mach. Learn. Res., 12, 2493
Krizhevsky, A., Sutskever, I., and Hinton, G. (2012, January 3–8). ImageNet classification with deep convolutional neural networks. Proceedings of the Advances in Neural Information Processing Systems 2012, Lake Tahoe, NV, USA.
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2014, January 24–27). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.
Simonyan, K., and Zisserman, A. (2014, January 16). Very deep convolutional networks for large-scale image recognition. Proceedings of the International Conference on Learning Representations, Banff, Canada.
Ian, G., Yoshua, B., and Aaron, C. (2016). Deep Learning, MIT Press.
Ioffe, S., and Szegedy, C. (2015, January 6–11). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the International Conference on Machine Learning (ICML), Lille, France.
Nair, V., and Hinton, G.E. (2010, January 21–24). Rectified linear units improve restricted boltzmann machines. Proceedings of the 27th International Conference on Machine Learning, Haifa, Israel.
WG III/2: Point Cloud Processing. Available online: http://www.commission3.isprs.org/wg2/.
Mongus, 2014, Computationally efficient method for the generation of a digital terrain model from airborne LiDAR data using connected operators, IEEE J. Sel. Top. Appl. Remote Sens., 7, 340