EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Keypoint3D: Keypoint-Based and Anchor-Free 3D Object Detection for Autonomous Driving with Monocular Vision

Zhen Li, Yuliang Gao, Qingqing Hong, Yuren Du, Seiichi Serikawa, Lifeng Zhang

Remote Sensing · 22.02.2023 · 15 (5) · 1210

DOI: 10.3390/rs15051210 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 22.02.2023. Verfasst von Zhen Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Kyushu Institute of Technology SPRING Scholarship Awardee, University Fellowship Founding Project for Innovation Creation in Science and Technology Fellowship Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Autonomous driving has received enormous attention from the academic and industrial communities. However, achieving full driving autonomy is not a trivial task, because of the complex and dynamic driving environment. Perception ability is a tough challenge for autonomous driving, while 3D object detection serves as a breakthrough for providing precise and dependable 3D geometric information. Inspired by practical driving experiences of human experts, a pure visual scheme takes sufficient responsibility for safe and stable autonomous driving. In this paper, we proposed an anchor-free and keypoint-based 3D object detector with monocular vision, named Keypoint3D. We creatively leveraged 2D projected points from 3D objects’ geometric centers as keypoints for object modeling. Additionally, for precise keypoints positioning, we utilized a novel self-adapting ellipse Gaussian filter (saEGF) on heatmaps, considering different objects’ shapes. We tried different variations of DLA-34 backbone and proposed a semi-aggregation DLA-34 (SADLA-34) network, which pruned the redundant aggregation branch but achieved better performance. Keypoint3D regressed the yaw angle in a Euclidean space, which resulted in a closed mathematical space avoiding singularities. Numerous experiments on the KITTI dataset for a moderate level have proven that Keypoint3D achieved the best speed-accuracy trade-off with an average precision of 39.1% at 18.9 FPS on 3D cars detection.

Förderung

  • Kyushu Institute of Technology SPRING Scholarship Awardee
  • University Fellowship Founding Project for Innovation Creation in Science and Technology Fellowship Program

Zitieren

APA

Li, Z., Gao, Y., Hong, Q., Du, Y., Serikawa, S., & Zhang, L. (2023). Keypoint3D: Keypoint-Based and Anchor-Free 3D Object Detection for Autonomous Driving with Monocular Vision. Remote Sensing, 15(5), 1210. https://doi.org/10.3390/rs15051210

Vancouver

Li Z, Gao Y, Hong Q, Du Y, Serikawa S, Zhang L. Keypoint3D: Keypoint-Based and Anchor-Free 3D Object Detection for Autonomous Driving with Monocular Vision. Remote Sensing. 2023;15(5):1210. doi:10.3390/rs15051210

BibTeX
@article{Li2023,
  author = {Li, Zhen and Gao, Yuliang and Hong, Qingqing and Du, Yuren and Serikawa, Seiichi and Zhang, Lifeng},
  title = {Keypoint3D: Keypoint-Based and Anchor-Free 3D Object Detection for Autonomous Driving with Monocular Vision},
  journal = {Remote Sensing},
  year = {2023},
  volume = {15},
  number = {5},
  pages = {1210},
  doi = {10.3390/rs15051210}
}
Kostenlos starten →