Road Lane Semantic Segmentation for High Definition Map

Jang, Wonje; An, Jhonghyun; Lee, Sangyun; Cho, Minho; Sun, Myungki; Kim, Euntai

doi:10.1109/ivs.2018.8500661

Cited by 19 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the nature of the targeted application is quite specific, the performed literature research didn't reveal other methods aiming to solve the precise task of visual end-to-end lane ID estimation. Generally, the community is interested in a larger scope including applications such as lane segmentation [Oliveira et al, 2016;Jang et al, 2018;Meyer et al, 2018], estimation [Kim and Park, 2017;Gurghian et al, 2016;Rabe et al, 2016], prediction [Tang et al, 2018;Son et al, 2015] or detection [Li et al, 2016;Lee et al, 2017;Niu et al, 2016;Jung et al, 2015]. Although these methods could be leveraged to solve the task at hand, this would however require additional intermediate steps and further processing to estimate the current lane ID.…”

Section: Discussionmentioning

confidence: 99%

Real-Time Lane ID Estimation Using Recurrent Neural Networks With Dual Convention

Halfaoui,

Bouzaraa,

Urfalioglu

et al. 2020

Preprint

View full text Add to dashboard Cite

Acquiring information about the road lane structure is a crucial step for autonomous navigation. To this end, several approaches tackle this task from different perspectives such as lane marking detection or semantic lane segmentation. However, to the best of our knowledge, there is yet no purely vision based end-to-end solution to answer the precise question: How to estimate the relative number or "ID" of the current driven lane within a multilane road or a highway? In this work, we propose a real-time, vision-only (i.e. monocular camera) solution to the problem based on a dual left-right convention. We interpret this task as a classification problem by limiting the maximum number of lane candidates to eight. Our approach is designed to meet low-complexity specifications and limited runtime requirements. It harnesses the temporal dimension inherent to the input sequences to improve upon high-complexity stateof-the-art models. We achieve more than 95% accuracy on a challenging test set with extreme conditions and different routes.

show abstract

Section: Discussionmentioning

confidence: 99%

Real-Time Lane ID Estimation Using Recurrent Neural Networks With Dual Convention

Halfaoui,

Bouzaraa,

Urfalioglu

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Jang et al also proposed a method for automatically constructing HD maps using a monocular camera setup. Their approach involved obtaining odometry data from the wheel encoder of the vehicle, estimating the vehicle's position, and detecting HD maps information from the obtained images [30].…”

Section: Camera-based Data-collection Methodsmentioning

confidence: 99%

“…Deep-learning-based SLAM methods can better understand the semantic information in the environment, improve the accuracy of data association, and enhance the robustness and generalization ability of the algorithms. Research on local semantic-map construction for HD map updating based on SLAM algorithms has also received extensive attention [30,40,[77][78][79]. These methods typically leverage deep-learning techniques to segment data, extract lane features, and perform loop-closure detection to achieve the construction of local maps.…”

Section: Local Map Reconstructionmentioning

confidence: 99%

A Review of Crowdsourcing Update Methods for High-Definition Maps

Guo,

Zhou,

et al. 2024

IJGI

View full text Add to dashboard Cite

High-definition (HD) maps serve as crucial infrastructure for autonomous driving technology, facilitating vehicles in positioning, environmental perception, and motion planning without being affected by weather changes or sensor-visibility limitations. Maintaining precision and freshness in HD maps is paramount, as delayed or inaccurate information can significantly impact the safety of autonomous vehicles. Utilizing crowdsourced data for HD map updating is widely recognized as a superior method for preserving map accuracy and freshness. Although it has garnered considerable attention from researchers, there remains a lack of comprehensive exploration into the entire process of updating HD maps through crowdsourcing. For this reason, it is imperative to review and discuss crowdsourcing techniques. This paper aims to provide an overview of the overall process of crowdsourced updates, followed by a detailed examination and comparison of existing methodologies concerning the key techniques of data collection, information extraction, and change detection. Finally, this paper addresses the challenges encountered in crowdsourced updates for HD maps.

show abstract

“…Most existing methods for HD-maps perform visual understanding in the image plane [15], [29], followed by backprojection to BEV. Another category of methods implicitly exploits the knowledge of the ground plane, while performing the pixel-level understanding on the image plane [20], [26], [28].…”

Section: Related Workmentioning

confidence: 99%

Understanding Bird’s-Eye View of Road Semantics Using an Onboard Camera

Can

Liniger

Unal

et al. 2022

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Autonomous navigation requires scene understanding of the action-space to move or anticipate events. For planner agents moving on the ground plane, such as autonomous vehicles, this translates to scene understanding in the bird's-eye view (BEV). However, the onboard cameras of autonomous cars are customarily mounted horizontally for a better view of the surrounding. In this work, we study scene understanding in the form of online estimation of semantic BEV maps using the video input from a single onboard camera. We study three key aspects of this task, image-level understanding, BEV level understanding, and the aggregation of temporal information. Based on these three pillars we propose a novel architecture that combines these three aspects. In our extensive experiments, we demonstrate that the considered aspects are complementary to each other for BEV understanding. Furthermore, the proposed architecture significantly surpasses the current state-of-the-art. Code: https://github.com/ybarancan/BEV feat stitch.

show abstract

Road Lane Semantic Segmentation for High Definition Map

Cited by 19 publications

References 10 publications

Real-Time Lane ID Estimation Using Recurrent Neural Networks With Dual Convention

Real-Time Lane ID Estimation Using Recurrent Neural Networks With Dual Convention

A Review of Crowdsourcing Update Methods for High-Definition Maps

Understanding Bird’s-Eye View of Road Semantics Using an Onboard Camera

Contact Info

Product

Resources

About