Research PaperNo Access

Object Detection in 3D Point Cloud Based on ECA Mechanism

Xinkai Wang

https://orcid.org/0000-0002-2649-0736

School of Electronics and Information Engineering, Liaoning University of Technology, Jinzhou 121000, P. R. China

E-mail Address: wxk2121@163.com

Search for more papers by this author

Xu Jia

https://orcid.org/0000-0001-7920-5532

School of Electronics and Information Engineering, Liaoning University of Technology, Jinzhou 121000, P. R. China

E-mail Address: xfxf0614@163.com

Corresponding author.

Search for more papers by this author

Miyuan Zhang

School of Electronics and Information Engineering, Liaoning University of Technology, Jinzhou 121000, P. R. China

Search for more papers by this author

, and

Houda Lu

School of Electronics and Information Engineering, Liaoning University of Technology, Jinzhou 121000, P. R. China

Search for more papers by this author

https://doi.org/10.1142/S0218126623500809Cited by:2 (Source: Crossref)

Abstract

Aiming at the problems of high complexity and low detection accuracy of single-stage three-dimensional (3D) detection method, a vehicle object detection algorithm based on the Efficient Channel Attention (ECA) mechanism is proposed. This paper provides a good solution to the problems of low object recognition accuracy and high model complexity in the field of 3D object detection. First, we voxelized the original point cloud data, taking the average coordinates and intensity values as the initial features. By entering into the Voxel Feature Encoding (VFE) layer, we can extract the features of each voxel. Then, referring to the VoxelNet model, the ECA mechanism is introduced, which reduces the complexity of the model while maintaining the good performance in the model. Finally, experiments on the widely used KITTI dataset show that the algorithm performs well, and the accuracy of the proposed ECA algorithm has reached 87.75%. Compared with the current mainstream algorithm SE-SSD of object detection, the accuracy is increased by 0.21%.

This paper was recommended by Regional Editor Takuro Sato.

Keywords:

References

1. X. Chen et al., Multi-view 3d object detection network for autonomous driving, Proc. IEEE Conf. Computer Vision and Pattern Recognition (IEEE Computer Society, 2017), pp. 1907–1915. Crossref, Google Scholar
2. K. Hara, H. Kataoka and Y. Satoh, Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and ImageNet? Proc. IEEE Conf. Computer Vision and Pattern Recognition (IEEE, 2018), pp. 6546–6555. Crossref, Google Scholar
3. D. Z. Wang and I. Posner, Voting for voting in online point cloud object detection, Robot. Sci. Syst. 1 (2015) 10–15. Google Scholar
4. X. Li et al., 3D multi-scale FCN with random modality voxel dropout learning for intervertebral disc localization and segmentation from multi-modality MR images, Med. Image Anal. 45 (2018) 41–54. Crossref, Web of Science, Google Scholar
5. S. Shi et al., PV-RCNN: Point-voxel feature set abstraction for 3d object detection, Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (IEEE, 2020), pp. 10529–10538. Crossref, Google Scholar
6. W. Zheng et al., SE-SSD: Self-ensembling single-stage object detector from point cloud, Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (2021), pp. 14494–14503. Crossref, Google Scholar
7. C. R. Qi et al., Pointnet: Deep learning on point sets for 3D classification and segmentation, Proc. IEEE Conf. Computer Vision and Pattern Recognition (IEEE, 2017), pp. 75–88. Google Scholar
8. C. R. Qi et al., Pointnet++: Deep hierarchical feature learning on point sets in a metric space, Adv. Neural Inf. Process. Syst. (2017) 5099–5108. Google Scholar
9. C. R. Qi et al., Frustum pointnets for 3D object detection from RGB-D data, Proc. IEEE Conf. Computer Vision and Pattern Recognition (IEEE, 2018), pp. 918–927. Crossref, Google Scholar
10. S. Shi, X. Wang and H. Li, Pointrcnn: 3D object proposal generation and detection from point cloud, Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (IEEE, 2019), pp. 770–779. Crossref, Google Scholar
11. Z. Yang et al., STD: Sparse-to-dense 3D object detector for point cloud, Proc. IEEE/CVF Int. Conf. Computer Vision (IEEE, 2019), pp. 1951–1960. Crossref, Google Scholar
12. Z. Yang et al., 3DSSD: Point-based 3D single stage object detector, Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (IEEE, 2020), pp. 11040–11048. Crossref, Google Scholar
13. Y. Zhou and O. Tuzel, Voxelnet: End-to-end learning for point cloud based 3D object detection, Proc. IEEE Conf. Computer Vision and Pattern Recognition (IEEE, 2018), pp. 4490–4499. Crossref, Google Scholar
14. Y. Yan, Y. Mao and B. Li, Second: Sparsely embedded convolutional detection, Sensors 18 (2018) 3337. Crossref, Web of Science, Google Scholar
15. W. Zheng et al., CIA-SSD: Confident IoU-aware single-stage object detector from point cloud, arXiv:2012.03015 (2020). Google Scholar
16. A. H. Lang et al., Pointpillars: Fast encoders for object detection from point clouds, Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (IEEE, 2019), pp. 12697–12705. Crossref, Google Scholar
17. Z. Liu et al., TANet: Robust 3D object detection from point clouds with triple attention, Proc. AAAI Conf. Artif. Intell. 34 (2020) 11677–11684. Google Scholar
18. Z. Yang et al., 3D-MAN: 3D multi-frame attention network for object detection, Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (2021), pp. 1863–1872. Crossref, Google Scholar
19. Y. Chen et al., Fast point R-CNN, Proc. IEEE/CVF Int. Conf. Computer Vision (IEEE, 2019), pp. 9775–9784. Crossref, Google Scholar
20. T. Yin, X. Zhou and P. Krahenbuhl, Center-based 3D object detection and tracking, Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (IEEE, 2021), pp. 11784–11793. Crossref, Google Scholar
21. J. Du, C. Jiang, Z. Han, H. Zhang, S. Mumtaz and Y. Ren, Contract mechanism and performance analysis for data transaction in mobile social networks, IEEE Trans. Netw. Sci. Eng. 6 (2019) 103–115. Crossref, Web of Science, Google Scholar
22. Q. Qi, Q. Huo, J. Wang, H. Sun, Y. Cao and J. Liao, Personalized sketch-based image retrieval by convolutional neural network and deep transfer learning, IEEE Access 7 (2019) 16537–16549. Crossref, Web of Science, Google Scholar
23. Y. Peng, A. Jolfaei and K. Yu, A novel real-time deterministic scheduling mechanism in industrial cyber-physical systems for energy internet, IEEE Trans. Ind. Inform. 18 (2021) 5670–5680. Crossref, Web of Science, Google Scholar
24. L. Zhao et al., A collaborative v2x data correction method for road safety, IEEE Trans. Reliab. 71 (2022) 951–962. Crossref, Web of Science, Google Scholar
25. S. Tu et al., Social phenomena and fog computing networks: A novel perspective for future networks, IEEE Trans. Comput. Soc. Syst. 9 (2021) 32–44. Crossref, Web of Science, Google Scholar
26. K. Yu et al., Securing critical infrastructures: Deep-learning-based threat detection in IIoT, IEEE Commun. Mag. 59 (2021) 76–82. Crossref, Web of Science, Google Scholar
27. J. Zhang et al., AntiConcealer: Reliable detection of adversary concealed behaviors in EdgeAI assisted IoT, IEEE Internet Things J. 9 (2021) 22184–22193. Crossref, Web of Science, Google Scholar
28. C. He et al., Structure aware single-stage 3D object detection from point cloud, Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (IEEE, 2020), pp. 11873–11882. Crossref, Google Scholar
29. D. Xu, K. Yu and J. A. Ritcey, Cross-layer device authentication with quantum encryption for 5G enabled IIoT in industry 4.0, IEEE Trans. Ind. Inform. 18 (2021) 6368–6378. Crossref, Web of Science, Google Scholar
30. J. Zhang et al., Trustworthy target tracking with collaborative deep reinforcement learning in EdgeAI-Aided IoT, IEEE Trans. Ind. Inform. 18 (2021) 1301–1309. Crossref, Web of Science, Google Scholar
31. M. Waqas et al., The role of artificial intelligence and machine learning in wireless networks security: Principle, practice and challenges, Artif. Intell. Rev. 4 (2022) 1–47. Google Scholar
32. L. Tan et al., Speech emotion recognition enhanced traffic efficiency solution for autonomous vehicles in a 5G-enabled space-air-ground integrated intelligent transportation system, IEEE Trans. Intell. Transp. Syst. 23 (2021) 2830–2842. Crossref, Web of Science, Google Scholar
33. F. Ding et al., Perceptual enhancement for autonomous vehicles: Restoring visually degraded images for context prediction via adversarial training, IEEE Trans. Intell. Transp. Syst. 23 (2021) 9430–9441. Crossref, Web of Science, Google Scholar
34. Z. Yu et al., Multi-attribute adaptive aggregation transformer for vehicle re-identification, Inf. Process. Manage. 59 (2022) 102868. Crossref, Web of Science, Google Scholar
35. F. Ding et al., Anti-forensics for face swapping videos via adversarial training, IEEE Trans. Multimedia 24 (2021) 3429–3441. Crossref, Web of Science, Google Scholar
36. C. R. Qi et al., Deep hough voting for 3D object detection in point clouds, Proc. IEEE/CVF Int. Conf. Computer Vision (IEEE, 2019), pp. 9277–9286. Crossref, Google Scholar
37. T. Guo et al., Constructing a prior-dependent graph for data clustering and dimension reduction in the edge of AIoT, Future Gener. Comput. Syst. 128 (2022) 381–394. Crossref, Web of Science, Google Scholar
38. Y. He et al., A NOMA-enabled framework for relay deployment and network optimization in double-layer airborne access VANETs, IEEE Trans. Intell. Transp. Syst. 23 (2022) 22452–22466. Crossref, Web of Science, Google Scholar