도시 구조물 분류를 위한 3차원 점 군의 구형 특징 표현과심층 신뢰 신경망 기반의 환경 형상 학습
Spherical Signature Description of 3D Point Cloud and Environmental Feature Learning based on Deep Belief Nets for Urban Structure Classification
1
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
This paper suggests the method of the spherical signature description of 3D point clouds taken from the laser range scanner on the ground vehicle. Based on the spherical signature description of each point, the extractor of significant environmental features is learned by the Deep Belief Nets for the urban structure classification. Arbitrary point among the 3D point cloud can represents its signature in its sky surface by using several neighborhood points. The unit spherical surface centered on that point can be considered to accumulate the evidence of each angular tessellation. According to a kind of point area such as wall, ground, tree, car, and so on, the results of spherical signature description look so different each other. These data can be applied into the Deep Belief Nets, which is one of the Deep Neural Networks, for learning the environmental feature extractor. With this learned feature extractor, 3D points can be classified due to its urban structures well. Experimental results prove that the proposed method based on the spherical signature description and the Deep Belief Nets is suitable for the mobile robots in terms of the classification accuracy.
Abstract
This paper suggests the method of the spherical signature description of 3D point clouds taken from the laser range scanner on the ground vehicle. Based on the spherical signature description of each point, the extractor of significant environmental features is learned by the Deep Belief Nets for the urban structure classification. Arbitrary point among the 3D point cloud can represents its signature in its sky surface by using several neighborhood points. The unit spherical surface centered on that point can be considered to accumulate the evidence of each angular tessellation. According to a kind of point area such as wall, ground, tree, car, and so on, the results of spherical signature description look so different each other. These data can be applied into the Deep Belief Nets, which is one of the Deep Neural Networks, for learning the environmental feature extractor. With this learned feature extractor, 3D points can be classified due to its urban structures well. Experimental results prove that the proposed method based on the spherical signature description and the Deep Belief Nets is suitable for the mobile robots in terms of the classification accuracy.
참고문헌 (17)
- A. Krizhevsky, "ImageNet Classification with Deep Convolutional Neural Networks", NIPS, ~ (2012)
- D. Silver, "Mastering the game of Go with deep neural networks and tree search", Nature, 529, pp.484~489 (2016)
- Sejin Lee, "Novel Sonar Salient Feature Structure for Extended Kalman Filter-Based Simultaneous Localization and Mapping of Mobile Robots", Advanced Robotics, 26(8-9), pp.1055~1074 (2012)
- S. Thrun, "Stanley : The robot that won the DARPA Grand Challenge", Journal of Field Robotics, 23(9), pp.661~692 (2006)
- 안승욱, "무인 자동차의 2차원 레이저 거리 센서를 이용한 도시 환경에서의 빠른 주변 환경 인식 방법", 로봇학회 논문지, 7(2), pp.92~100 (2012), 한국로봇학회[DOI]
- 이세진, "초음파 데이터의 형상 인지 지수를 이용한 확률 격자 지도의 작성", 로봇학회 논문지, 2(3), pp.227~233 (2007), 한국로봇학회
- Geoffrey E. Hinton, "A Fast Learning Algorithm for Deep Belief Nets", Neural Computation, 18(7), pp.1527~1554 (2006)
- J.F. Lalonde, "Natural Terrain Classification using Three-Dimensional Ladar Data for Ground Robot Mobility", Journal of Field Robotics, 23(10), pp.839~861 (2006)
- A. Golovinskiy, "Shapebased Recognition of 3D Point Clouds in Urban Environments", IEEE 12th International Conference on Computer Vision, pp.2154~2161 (2009)
- X. Zhu, "Segmentation and Classification of Range Image from an Intelligent Vehicle in Urban Environment", IEEE, 2010, 1457~1462
- H. Zhao, "Scene Understanding in a Larhge Dynamic Environment through a Laser-based Sensing", IEEE International Conference on Robotics and Automation, pp.128~133 (2010)
- Yungeun Choe, "Urban structure classification using the 3D normal distribution transform for practical robot applications", Advanced Robotics, 27(5), pp.351~371 (2013)
- Yong-Ju Lee, "Three-dimensional iterative closest point-based outdoor SLAM using terrain classification", Intelligent Service Robotics, 4(2), pp.147~158 (2011)
- Martin Magnusson, "The Three-Dimensional Normal-Distributions Transform – an Efficient Representation for Registration, Surface Analysis, and Loop Detection", Doctor, pp.2009
- R. Socher, "Convolutional-recursive deep learning for 3D object classification", NIPS, ~ (2012)
- Y. Bengio, "Greedy Layer-Wise Training of Deep Networks", Advances in neural information processing systems, 19, pp.153~160 (2007)
- D.H. Ackley, "A learning algorithm for Boltzmann machines", Cognitive Science, 9(1), pp.147~169 (1985)