analiza aiqbench
This research addresses cyclist safety by adapting automotive LiDAR perception models specifically for bicycle-mounted sensors, demonstrating significant performance gains through domain-specific fine-tuning. The study introduces the BikeScenes dataset to bridge the gap in high-quality annotated data required for advancing autonomous systems focused on vulnerable road users. This work highlights a critical shift toward specialized datasets and model transfer techniques essential for next-generation edge AI in robotics.
BikeScenes: LiDAR Semantic Segmentation for Bicycles
arXiv:2510.25901v2 Announce Type: replace-cross Abstract: The vulnerability of cyclists, exacerbated by the rising popularity of faster e-bikes, motivates adapting automotive perception technologies for bicycle safety. We use our multi-sensor SenseBike research platform to study 3D LiDAR semantic segmentation for bicycles. We introduce the novel BikeScenes-lidarseg Dataset, comprising 3021 consecutive LiDAR scans around the university campus of the TU Delft, semantically annotated for 29 dynamic and static classes. As an initial baseline study, we evaluate how a SemanticKITTI pre-trained FRNet model transfers to this bicycle-mounted solid-state LiDAR setting. Fine-tuning on BikeScenes increases mean Intersection-over-Union (mIoU) from 13.8% to 63.6% on our held-out subsequences. These results show the practical value of in-domain data for this platform, while also highlighting the need for larger bicycle datasets. We contribute BikeScenes as a resource for advancing research in cyclist-centric perception.
Abstract:The vulnerability of cyclists, exacerbated by the rising popularity of faster e-bikes, motivates adapting automotive perception technologies for bicycle safety. We use our multi-sensor SenseBike research platform to study 3D LiDAR semantic segmentation for bicycles. We introduce the novel BikeScenes-lidarseg Dataset, comprising 3021 consecutive LiDAR scans around the university campus of the TU Delft, semantically annotated for 29 dynamic and static classes. As an initial baseline study, we evaluate how a SemanticKITTI pre-trained FRNet model transfers to this bicycle-mounted solid-state LiDAR setting. Fine-tuning on BikeScenes increases mean Intersection-over-Union (mIoU) from 13.8% to 63.6% on our held-out subsequences. These results show the practical value of in-domain data for this platform, while also highlighting the need for larger bicycle datasets. We contribute BikeScenes as a resource for advancing research in cyclist-centric perception.
Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
arXiv:2510.25901 [cs.CV]
(or arXiv:2510.25901v2 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2510.25901 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 227 cuvinte
Subiecte conexe
Toward Robust LiDAR Semantic Segmentation for Real-World Deployment: Evaluation under Coarse Labels, Adverse Conditions, and Domain Shifts
arXiv · 3 sept. 2026
Lang3DSeg: Annotation-Free Open-Vocabulary 3D Segmentation with Point Transformers
arXiv · 2 oct. 2026
SplatLabel: Pseudo-Labelling through 4D Gaussian Splatting
arXiv · 25 sept. 2026
Integrate NVIDIA Omniverse RTX Sensor Simulation Into Existing Apps
NVIDIA · 20 iul. 2026