TF-Lane: Traffic Flow Module for Robust Lane Perception
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914299672264704 |
|---|---|
| author | Xie, Yihan Xia, Han Yang, Zhen |
| author_facet | Xie, Yihan Xia, Han Yang, Zhen |
| contents | Autonomous driving systems require robust lane perception capabilities, yet existing vision-based detection methods suffer significant performance degradation when visual sensors provide insufficient cues, such as in occluded or lane-missing scenarios. While some approaches incorporate high-definition maps as supplementary information, these solutions face challenges of high subscription costs and limited real-time performance. To address these limitations, we explore an innovative information source: traffic flow, which offers real-time capabilities without additional costs. This paper proposes a TrafficFlow-aware Lane perception Module (TFM) that effectively extracts real-time traffic flow features and seamlessly integrates them with existing lane perception algorithms. This solution originated from real-world autonomous driving conditions and was subsequently validated on open-source algorithms and datasets. Extensive experiments on four mainstream models and two public datasets (Nuscenes and OpenLaneV2) using standard evaluation metrics show that TFM consistently improves performance, achieving up to +4.1% mAP gain on the Nuscenes dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_01277 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TF-Lane: Traffic Flow Module for Robust Lane Perception Xie, Yihan Xia, Han Yang, Zhen Computer Vision and Pattern Recognition I.4.8 Autonomous driving systems require robust lane perception capabilities, yet existing vision-based detection methods suffer significant performance degradation when visual sensors provide insufficient cues, such as in occluded or lane-missing scenarios. While some approaches incorporate high-definition maps as supplementary information, these solutions face challenges of high subscription costs and limited real-time performance. To address these limitations, we explore an innovative information source: traffic flow, which offers real-time capabilities without additional costs. This paper proposes a TrafficFlow-aware Lane perception Module (TFM) that effectively extracts real-time traffic flow features and seamlessly integrates them with existing lane perception algorithms. This solution originated from real-world autonomous driving conditions and was subsequently validated on open-source algorithms and datasets. Extensive experiments on four mainstream models and two public datasets (Nuscenes and OpenLaneV2) using standard evaluation metrics show that TFM consistently improves performance, achieving up to +4.1% mAP gain on the Nuscenes dataset. |
| title | TF-Lane: Traffic Flow Module for Robust Lane Perception |
| topic | Computer Vision and Pattern Recognition I.4.8 |
| url | https://arxiv.org/abs/2602.01277 |