More Web Proxy on the site http://driver.im/

research-article

CNN-based 3D object classification using Hough space of LiDAR point clouds

Authors:

Lingfeng Zhang,

Amanda GozhoAuthors Info & Claims

Human-centric Computing and Information Sciences, Volume 10, Issue 1

https://doi.org/10.1186/s13673-020-00228-8

Published: 07 May 2020 Publication History

Abstract

With the wide application of Light Detection and Ranging (LiDAR) in the collection of high-precision environmental point cloud information, three-dimensional (3D) object classification from point clouds has become an important research topic. However, the characteristics of LiDAR point clouds, such as unstructured distribution, disordered arrangement, and large amounts of data, typically result in high computational complexity and make it very difficult to classify 3D objects. Thus, this paper proposes a Convolutional Neural Network (CNN)-based 3D object classification method using the Hough space of LiDAR point clouds to overcome these problems. First, object point clouds are transformed into Hough space using a Hough transform algorithm, and then the Hough space is rasterized into a series of uniformly sized grids. The accumulator count in each grid is then computed and input to a CNN model to classify 3D objects. In addition, a semi-automatic 3D object labeling tool is developed to build a LiDAR point clouds object labeling library for four types of objects (wall, bush, pedestrian, and tree). After initializing the CNN model, we apply a dataset from the above object labeling library to train the neural network model offline through a large number of iterations. Experimental results demonstrate that the proposed method achieves object classification accuracy of up to 93.3% on average.

References

[1]

Aamir M, Yi-Fei P, Rahman Ziaur, et al. A hybrid proposed framework for object detection and classification J Inform Processing Syst 2018 14 5 1176-1194

[2]

Seo YS and Huh JH Automatic emotion-based music classification for supporting intelligent IoT applications Electronics 2019 8 2 164

[3]

Zhang J, Wang W, Lu C, Wang J, and Sangaiah AK Lightweight deep network for traffic sign classification Annals Telecommun 2019

[4]

Chu PM, Cho S, Park J, Fong S, and Cho K Enhanced ground segmentation method for Lidar point clouds in human-centric autonomous robot systems Human-centric Comput Inform Sci 2019 9 1 1-4

[5]

Wu J, Tian Y, Xu H, Yue R, Wang A, and Song X Automatic ground points filtering of roadside LiDAR data using a channel-based filtering algorithm Optics Laser Technol 2019 1 115 374-383

[6]

Guo Y, Bennamoun M, Sohel F, et al. 3D object recognition in cluttered scenes with local surface features: a survey IEEE Trans Pattern Anal Mach Intell 2014 36 11 2270-2287

[7]

Ghrabat MJ, Ma G, Maolood IY, Alresheedi SS, and Abduljabbar ZA An effective image retrieval based on optimized genetic algorithm utilized a novel SVM-based convolutional neural network classifier Human-centric Comput Inform Sci 2019 9 1 31

[8]

Hao W and Wang Y Structure-based object detection from scene point clouds Neurocomputing 2016 191 148-160

[9]

Zeng H, Liu Y, Li Siqi, et al. Convolutional neural network based multi-feature fusion for non-rigid 3D model retrieval J Inform Processing Syst 2018 14 1 176-190

[10]

Zhang J, Chaoquan L, Li X, et al. A full convolutional network based on DenseNet for remote sensing scene classification Mathemat Biosci Eng 2019 16 5 3345-3367

[11]

Meng R, Rice SG, Wang J, and Sun X A fusion steganographic algorithm based on faster R-CNN Comput Materials Continua 2018 55 1 1-6

[12]

Rangel JC, Martínez-Gómez J, Romero-González C, García-Varea I, and Cazorla M Semi-supervised 3D object recognition through CNN labeling Appl Soft Comput 2018 1 65 603-613

[13]

Xiao L, Wang R, Dai B, et al.Hybrid conditional random field based camera-LIDAR fusion for road detectionInf Sci2018432543-5583758198

[14]

Rusu RB, Bradski G, Thibaux R, Hsu J et al (2010) Fast 3D recognition and pose using the viewpoint feature histogram. IEEE/RSJ International Conference on Intelligent. p 2155–2162

[15]

Wohlkinger W, Vincze M (2011) Ensemble of shape functions for 3D object classification. IEEE International Conference on Robotics & Biomimetics. p 2987–2992

[16]

Chen T, Dai B, Liu D, Song J et al (2014) Performance of global descriptors for velodyne-based urban object recognition. IEEE Intelligent Vehicles Symposium Proceedings. p 667–673

[17]

Zhu S, Zhang L, Luo Y, et al. Characteristics positioning of facial point cloud based on spin image Comput Engin Design 2017 8 2209-2212

[18]

Dong Z, Yang B, Liu Y, et al. A novel binary shape context for 3D local surface description ISPRS J Photogrammetry Remote Sensing 2017 130 431-452

[19]

Salti S, Tombari F, and Di Stefano L SHOT: unique signatures of histograms for surface and texture description Comput Vis Image Underst 2014 125 251-264

[20]

Guo Y, Sohel F, Bennamoun M, et al. A novel local surface feature for 3D object recognition under clutter and occlusion Inf Sci 2015 293 196-213

[21]

Prakhya SM, Liu B, Lin W (2015) B-SHOT: a binary feature descriptor for fast and efficient key point matching on 3D point clouds. IEEE/RSJ International Conference on Intelligent Robots and Systems. p 1929–1934

[22]

Serna A and Marcotegui B Detection, segmentation and classification of 3D urban objects using mathematical morphology and supervised learning ISPRS J Photogrammetry Remote Sens 2014 93 243-255

[23]

Wang H, Wang C, Luo H, et al. Object detection in terrestrial laser scanning point clouds based on hough forest IEEE Geosci Remote Sens Lett 2014 11 10 1807-1811

[24]

Becker C, Häni N, Rosinskaya E, et al. Classification of aerial photogrammetric 3D point clouds Photogrammetric Eng Remote Sens 2017 84 5 287-295

[25]

Jin L, Yihe Y, Shiqi L, et al. Attention-based BiGRU-CNN for Chinese question classification J Ambient Intell Humanized Comput 2019

[26]

Su H, Maji S, Kalogerakis E et al (2015) Multi-view convolutional neural networks for 3D shape recognition. IEEE International Conference on Computer Vision. p 945–953.

[27]

Zhi S, Liu Y, Li X, et al. Toward real-time 3D object recognition: a lightweight volumetric CNN framework using multitask learning Comput Graph 2018 71 199-207

[28]

Qi CR, Su H, Mo K, Guibas LJ (2017) PointNet: deep learning on point sets for 3D classification and segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. p 652–660

[29]

Li Y, Bu R, Sun M, Wu W, Di X, Chen B (2018) PointCNN: Convolution on X-transformed points. Advances in Neural Information Processing Systems. p 820–830

[30]

Xu Y, Fan T, Xu M et al (2018) SpiderCNN: Deep learning on point sets with parameterized convolutional filters. Proceedings of the European Conference on Computer Vision. p 87–102

[31]

De Deuge M, Quadros A (2013) Unsupervised feature learning for classification of outdoor 3D scans. In Australasian Conference on Robotics and Automation. (2).

Cited By

Surajkanta YPal S(2023)Recognition of spherical segments using number theoretic properties of isothetic coversMultimedia Tools and Applications10.1007/s11042-022-14182-382:13(19393-19416)Online publication date: 1-May-2023
https://dl.acm.org/doi/10.1007/s11042-022-14182-3
Shi MWang RRen J(2023)Hierarchical capsule network for hyperspectral image classificationNeural Computing and Applications10.1007/s00521-023-08664-035:25(18417-18443)Online publication date: 1-Sep-2023
https://dl.acm.org/doi/10.1007/s00521-023-08664-0

Recommendations

Real-Time Object Recognition from Streaming LiDAR Point Cloud Data
DEBS '19: Proceedings of the 13th ACM International Conference on Distributed and Event-based Systems

In many robotic applications, LiDAR (Light Detection and Ranging) scanner is used to gather data about the environment. Applications like autonomous vehicles require real-time processing of LiDAR point cloud data with high accuracy.

We describe in this ...
3D object classification based on deep belief networks and point clouds

Since the discovery of 3D sensors such as Kinect camera, 3D object models, and point clouds become frequently used in many areas. The most important one is the 3D object recognition and classification in robotic applications. This type of sensors, like ...
Classification of Airborne LIDAR Intensity Data Using Statistical Analysis and Hough Transform with Application to Power Line Corridors
DICTA '09: Proceedings of the 2009 Digital Image Computing: Techniques and Applications

Light Detection and Ranging (LIDAR) has great potential to assist vegetation management in power line corridors by providing more accurate geometric information of the power line assets and vegetation along the corridors. However, the development of ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Human-centric Computing and Information Sciences

Human-centric Computing and Information Sciences Volume 10, Issue 1

Dec 2020

952 pages

ISSN:2192-1962

EISSN:2192-1962

Issue’s Table of Contents

© The Author(s) 2020.

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 07 May 2020

Accepted: 24 April 2020

Received: 28 September 2019

Author Tags

Qualifiers

Research-article

Funding Sources

National Natural Science Foundation of China

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 09 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Surajkanta YPal S(2023)Recognition of spherical segments using number theoretic properties of isothetic coversMultimedia Tools and Applications10.1007/s11042-022-14182-382:13(19393-19416)Online publication date: 1-May-2023
https://dl.acm.org/doi/10.1007/s11042-022-14182-3
Shi MWang RRen J(2023)Hierarchical capsule network for hyperspectral image classificationNeural Computing and Applications10.1007/s00521-023-08664-035:25(18417-18443)Online publication date: 1-Sep-2023
https://dl.acm.org/doi/10.1007/s00521-023-08664-0

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents