Abstract
Object recognition is a significant research area within computer vision. While traditional approaches have primarily focused on 2D image-based methods, these approaches often lack range information necessary for accurate surface recognition. To address this limitation, this paper proposes a point cloud-based object recognition approach. The method involves slicing the point cloud of an object into multiple point images, which are then merged into a single composite image for recognition. The classification task is performed using a convolutional neural network. In our simulation utilizing the KITTI dataset, objects are classified into three distinct categories: vehicles, pedestrians, and street clutter. The experimental results demonstrate the effectiveness of the proposed method, with impressive accuracy rates achieved. Specifically, the accuracy for vehicle recognition reaches 93.75%, while pedestrian recognition achieves 82.35%. These findings highlight the strong performance of the proposed approach in object recognition tasks, validating its potential for practical applications.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Salmane, P.H., et al.: 3D object detection for self-driving cars using video and LiDAR: an ablation study. Sensors 23(6), 3223 (2023)
Zhang, Y., Rabbat, M.: A graph-CNN for 3d point cloud classification. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6279–6283 (2018)
Huilin, Y., Xia, P., Chang, Q.: A method of objects classification for intelligent vehicles based on number of projected points. In: 2017 2nd IEEE International Conference on Intelligent Transportation Engineering (ICITE) (2017)
Sun, P., Zhao, X., Xu, Z., Wang, R., Min, H.: A 3D LiDAR data-based dedicated road boundary detection algorithm for autonomous vehicles. IEEE Access 7, 29623–29638 (2019)
Zhou, Y., Tuzel, O.: Voxelnet: End-to-end learning for point cloud based 3d object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4490–4499 (2017)
Asvadi, A., Garrote, L., Premebiad, C., et al.: DepthCN: Vehicle detection using 3D-LIDAR and ConvNet. In: ITSC 2017. IEEE International Conference on Intelligent Transportation Systems (2017)
Chen, X., Kundu, K., Zhu, Y., Ma, H., Fidler, S., Urtasun, R.: 3D object proposals using stereo imagery for accurate object class detection. IEEE Trans. Pattern Anal. Mach. Intell. 40(5), 1259–1272 (2018). https://doi.org/10.1109/TPAMI.2017.2706685
Barea, R., Pérez, C., Bergasa, L.M., et al.: Vehicle detection and localization using 3D LIDAR point cloud and image semantic segmentation. In: ITSC 2018. IEEE International Conference on Intelligent Transportation Systems (2018)
Maalej, Y., Sorour, S., Abdel-Rahim, A., et al.: Tracking 3D LIDAR point clouds using extended kalman filters in KITTI driving sequences. In: GLOBECOM 2018. IEEE Global Communications Conference (2018)
Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3d object detection network for autonomous driving. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1907–1915 (2017)
Lin, C.-C., Kuo, C.-H., Chiang, H.-T.: CNN-based classification for point cloud object with bearing angle image. IEEE Sensors J. 22(1), 1003–1011 (2022). https://doi.org/10.1109/JSEN.2021.3130268
Wang, Y., et al.: Pillar-based object detection for autonomous driving. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12367, pp. 18–34. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58542-6_2
Börcs, A., Nagy, B., Benedek, C.: Instant object detection in lidar point clouds. IEEE Geosci. Remote Sens. Lett. 14(7), 992–996 (2017)
Acknowledgments
This research was financially supported by the Intelligent Recognition Industry Service Center (IRIS) from The Featured Areas Research Center Program within the framework of the Higher Education Sprout Project by the Ministry of Education (MOE) in Taiwan and Ministry of Science and Technology, Taiwan, R.O.C. under Grant no.: MOST 111-2221-E-224 -046-MY2.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lin, CC., Lin, KC. (2023). Object Recognition with Layer Slicing of Point Cloud. In: Barolli, L. (eds) Advances in Networked-based Information Systems. NBiS 2023. Lecture Notes on Data Engineering and Communications Technologies, vol 183. Springer, Cham. https://doi.org/10.1007/978-3-031-40978-3_41
Download citation
DOI: https://doi.org/10.1007/978-3-031-40978-3_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-40977-6
Online ISBN: 978-3-031-40978-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)