ABSTRACT
Large-scale 3D Point cloud classification is a basic topic for various applications. Traditional geometries features are usually independent of each other and difficult to adapt to a fixed classification model. With the rise of the neural network, deep learning is considered in 3D point cloud application. 3D points are difficult to feed the neural network directly based on deep learning, as they cannot be arranged in a fixed order as image pixels. In this paper, we combine traditional feature-based methods with the Convolutional neural network(CNN) to finish the classification task. The core idea is to construct a feasible structure called Feature Description Matrix(FDM) which encapsulates the local feature of the point to feed CNN for training and testing. By extracting geometry features and designed Feature Description Vectors(FDV) for FDM, a simple mechanism for point cloud classification is given, and experiments validate the effectiveness of our method, with higher classification accuracy compared to state-of-art works.
- A. S. Antonarakis, K. S. Richards, J. Brasington, and E. Muller. 2010. Determining leaf area index and leafy tree roughness using terrestrial laser scanning. Water Resources Research 46, 6 (2010), 346--360.Google ScholarCross Ref
- Alexandre Boulch, Bertrand Le Saux, and Nicolas Audebert. 2017. Unstructured Point Cloud Semantic Labeling Using Deep Segmentation Networks. In Eurographics Workshop on 3D Object Retrieval, Ioannis Pratikakis, Florent Dupont, and Maks Ovsjanikov (Eds.).Google Scholar
- Leo Breiman. 2001. Random Forests. Mach. Learn. 45, 1 (Oct. 2001), 5--32. Google ScholarDigital Library
- N. Brodu and D. Lague. 2012. 3D terrestrial lidar data classification of complex natural scenes using a multi-scale dimensionality criterion: Applications in geomorphology. ISPRS Journal of Photogrammetry and Remote Sensing 68 (2012), 121--134.Google ScholarCross Ref
- Corinna Cortes and Vladimir Vapnik. 1995. Support-Vector Networks. Machine Learning 20, 3 (1995), 273--297. Google ScholarDigital Library
- Thomas M Cover and Peter E Hart. 1967. Nearest neighbor pattern classification. IEEE Transactions on Information Theory 13, 1 (1967), 21--27. Google ScholarDigital Library
- M. Engelcke, D. Rao, D. Zeng Wang, C. Hay Tong, and I. Posner. 2016. Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networks. ArXiv e-prints (2016).Google Scholar
- R. A. Fisher. 1936. The Use of Multiple Measurements in Taxonomic Problems. Annals of Eugenics 7, 7 (1936), 179--188.Google ScholarCross Ref
- Yoav Freund and Robert E Schapire. 1997. A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting. symposium on the theory of computing 55, 1 (1997), 119--139. Google ScholarDigital Library
- Sam Friedman and Ioannis Stamos. 2013. Online Detection of Repeated Structures in Point Clouds of Urban Scenes for Compression and Registration. International Journal of Computer Vision 102, 1--3 (2013), 112--128. Google ScholarDigital Library
- Paul Guerrero, Yanir aKleiman, Maks Ovsjanikov, and Niloy J. Mitra. 2018. PCP-NET: Learning Local Shape Properties from Raw Point Clouds. Computer Graphics Forum (2018).Google Scholar
- Kan Guo, Dongqing Zou, and Xiaowu Chen. 2015. 3D Mesh Labeling via Deep Convolutional Neural Networks. ACM Trans. Graph. 35, 1 (2015), 3:1--3:12. Google ScholarDigital Library
- Timo Hackel, N. Savinov, L. Ladicky, Jan D. Wegner, K. Schindler, and M. Pollefeys. 2017. SEMANTIC3D.NET: A new large-scale point cloud classification benchmark. In ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. IV-1-W1. 91--98.Google Scholar
- Wen Hao and Yinghui Wang. 2014. Classification-based scene modeling for urban point clouds. Optical Engineering 53, 3 (2014), 033110.Google ScholarCross Ref
- George L. Heritage and David J. Milan. 2009. Terrestrial Laser Scanning of grain roughness in a gravel-bed river. Geomorphology 113, 1 (2009), 4--11. Understanding earth surface processes from remotely sensed digital terrain models.Google ScholarCross Ref
- Jing Huang and Suya You. 2016. Point cloud labeling using 3D Convolutional Neural Network. In 2016 23rd International Conference on Pattern Recognition (ICPR). 2670--2675.Google ScholarCross Ref
- George H John and Pat Langley. 1995. Estimating continuous distributions in Bayesian classifiers. uncertainty in artificial intelligence (1995), 338--345. Google ScholarDigital Library
- Hema Swetha Koppula, Abhishek Anand, Thorsten Joachims, and Ashutosh Saxena. 2011. Semantic Labeling of 3D Point Clouds for Indoor Scenes. In NIPS. Google ScholarDigital Library
- Richard Labourdette and Richard R. Jones. 2007. Characterization of fluvial architectural elements using a three-dimensional outcrop data set: Escanilla braided system, South-Central Pyrenees, Spain. Geosphere 3, 6 (2007), 422--434.Google ScholarCross Ref
- Ee Hui Lim and David Suter. 2009. 3D terrestrial LIDAR classifications with super-voxels and multi-scale Conditional Random Fields. Computer-Aided Design 41, 10 (2009), 701--710. Google ScholarDigital Library
- F. Liu, S. Li, L. Zhang, C. Zhou, R. Ye, Y. Wang, and J. Lu. 2017. 3DCNN-DQN-RNN: A Deep Reinforcement Learning Framework for Semantic Parsing of Large-scale 3D Point Clouds. ICCV (2017).Google Scholar
- Lorenzo Luciano and A. Ben Hamza. 2017. Deep learning with geodesic moments for 3D shape classification. Pattern Recognition Letters (2017). Google ScholarDigital Library
- A. Martinovic, J. Knopp, H. Riemenschneider, and L. Van Gool. 2015. 3D all the way: Semantic segmentation of urban scenes from start to end in 3D. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 4456--4465.Google Scholar
- David J. Milan, George L. Heritage, and David Hetherington. 2007. Application of a 3D laser scanner in the assessment of erosion and deposition volumes and channel change in a proglacial river. Earth Surface Processes & Landforms 32, 11 (2007), 1657--1674.Google ScholarCross Ref
- Joanna M Nield, Giles F. S Wiggs, and Robert S Squirrell. 2015. Aeolian sand strip mobility and protodune development on a drying beach: examining surface moisture and surface roughness patterns measured by terrestrial laser scanning. Earth Surface Processes & Landforms 36, 4 (2015), 513--522.Google ScholarCross Ref
- Mustafa Ozuysal, Pascal Fua, and Vincent Lepetit. 2007. Fast Keypoint Recognition in Ten Lines of Code. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2007), 1--8.Google ScholarCross Ref
- Danil Prokhorov. 2010. A Convolutional Learning System for Object Classification in 3-D Lidar Data. Trans. Neur. Netw. 21, 5 (May 2010), 858--863. Google ScholarDigital Library
- Charles Ruizhongtai Qi, Hao Su, Kaichun Mo, and Leonidas J. Guibas. 2017. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. CVPR (2017).Google Scholar
- Charles Ruizhongtai Qi, Li Yi, Hao Su, and Leonidas J. Guibas. 2017. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. NIPS (2017).Google Scholar
- J R Quinlan. 1986. Induction of Decision Trees. Machine Learning 1, 1 (1986), 81--106. Google ScholarCross Ref
- Martin A Riedmiller and H Braun. 1993. A direct adaptive method for faster backpropagation learning: the RPROP algorithm. 1 (1993), 586--591.Google Scholar
- F. Rottensteiner, G. Sohn, J. Jung, M. Gerke, C. Baillard, S. Benitez, and U. Breitkopf. 2012. THE ISPRS BENCHMARK ON URBAN OBJECT CLASSIFICATION AND 3D BUILDING RECONSTRUCTION. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences I-3 (2012), 293--298.Google Scholar
- J. Su, A. Srivastava, and F.W. Huffer. 2013. Detection, classification and estimation of individual shapes in 2D and 3D point clouds. Computational Statistics & Data Analysis 58 (2013), 227--241. Google ScholarDigital Library
- Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, Chun-Yu Sun, and Xin Tong. 2017. O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis. ACM Transactions on Graphics 36, 4 (2017). Google ScholarDigital Library
- Z. Wang, L. Zhang, T. Fang, P. T. Mathiopoulos, X. Tong, H. Qu, Z. Xiao, F. Li, and D. Chen. 2015. A Multiscale and Hierarchical Feature Extraction Method for Terrestrial Laser Scanning Point Cloud Classification. IEEE Transactions on Geoscience and Remote Sensing 53, 5 (May 2015), 2409--2425.Google ScholarCross Ref
- Martin Weinmann, Boris Jutzi, Stefan Hinz, and Clment Mallet. 2015. Semantic point cloud interpretation based on optimal neighborhoods, relevant features and efficient classifiers. ISPRS Journal of Photogrammetry and Remote Sensing 105 (2015), 286--304.Google ScholarCross Ref
- Martin Weinmann, Boris Jutzi, and Clément Mallet. 2014. Semantic 3D scene interpretation: A framework combining optimal neighborhood size selection with relevant features. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences II-3 (2014), 181--188.Google Scholar
- Zhirong Wu, S. Song, A. Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and J. Xiao. 2015. 3D ShapeNets: A deep representation for volumetric shapes. In CVPR. 1912--1920.Google Scholar
- Bisheng Yang, Zhen Dong, Yuan Liu, Fuxun Liang, and Yongjun Wang. 2017. Computing multiple aggregation levels and contextual features for road facilities recognition using mobile laser scanning data. ISPRS Journal of Photogrammetry and Remote Sensing 126, Supplement C (2017), 180--194.Google ScholarCross Ref
- Liangpei Zhang, Xin Huang, Bo Huang, and Pingxiang Li. 2006. A pixel shape index coupled with spectral information for classification of high spatial resolution remotely sensed imagery. IEEE Transactions on Geoscience and Remote Sensing 44, 10 (Oct 2006), 2950--2961.Google Scholar
- Z. Zhang, L. Zhang, X. Tong, P. T. Mathiopoulos, B. Guo, X. Huang, Z. Wang, and Y. Wang. 2016. A Multilevel Point-Cluster-Based Discriminative Feature for ALS Point Cloud Classification. IEEE Transactions on Geoscience and Remote Sensing 54, 6 (June 2016), 3309--3321.Google Scholar
- Large-scale 3D Point Cloud Classification Based On Feature Description Matrix By CNN
Recommendations
Large Scale Image Classification Based on CNN and Parallel SVM
Neural Information ProcessingAbstractImage classification is one of the most important problems for computer vision and machine learning. Many image classification methods have been proposed and applied to many application areas. But how to improve the performance of image ...
Fruit type classification using deep learning and feature fusion
Highlights- Proposed used deep learning applications to classify the fruits based on optimal features.
- CNN employed to extract the optimal features.
- RNN employed to label the optimal features.
- LSTM employed to classify the fruits based on ...
AbstractMachine and deep learning applications play a dominant role in the current scenario in the agriculture sector. To date, the classification of fruits using image features has attained the researcher’s attraction very much from the last few years. ...
Point cloud classification by dynamic graph CNN with adaptive feature fusion
AbstractThe deep neural network has made the most advanced breakthrough in almost all 2D image tasks, so we consider the application of deep learning in 3D images. Point cloud data, as the most basic and important form of representation of 3D images, can ...
Comments