RECORD
LineNet: a Zoomable CNN for Crowdsourced High Definition Maps Modeling in Urban Environments
Computer Vision and Pattern Recognition · Submitted 16 Jul 2018
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim And the maps can be constructed precisely even with inaccurate crowdsourced data.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
High Definition (HD) maps play an important role in modern traffic scenes. However, the development of HD maps coverage grows slowly because of the cost limitation. To efficiently model HD maps, we proposed a convolutional neural network with a novel prediction layer and a zoom module, called LineNet. It is designed for state-of-the-art lane detection in an unordered crowdsourced image dataset. And we introduced TTLane, a dataset for efficient lane detection in urban road modeling applications. Combining LineNet and TTLane, we proposed a pipeline to model HD maps with crowdsourced data for the first time. And the maps can be constructed precisely even with inaccurate crowdsourced data.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | High Definition (HD) maps play an important role in modern traffic scenes. | background 1.00 | 0.05 | 0.02 | asserted 1.00 |
| s1 | However, the development of HD maps coverage grows slowly because of the cost limitation. | background 0.62 | 0.10 | 0.02 | asserted 1.00 |
| s2 | To efficiently model HD maps, we proposed a convolutional neural network with a novel prediction layer and a zoom module, called LineNet. | contribution 0.51 | 0.95 | 0.09 | asserted 1.00 |
| s3 | It is designed for state-of-the-art lane detection in an unordered crowdsourced image dataset. | method 0.70 | 0.69 | 0.05 | asserted 0.99 |
| s4 | And we introduced TTLane, a dataset for efficient lane detection in urban road modeling applications. | contribution 0.95 | 0.93 | 0.06 | asserted 0.99 |
| s5 | Combining LineNet and TTLane, we proposed a pipeline to model HD maps with crowdsourced data for the first time. | contribution 0.99 | 0.94 | 0.37 | asserted 1.00 |
| s6 | And the maps can be constructed precisely even with inaccurate crowdsourced data. | result 0.92 | 0.81 | 0.50 | asserted 0.74 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
High Definition (HD) maps play an important role in modern traffic scenes. However, the development of HD maps coverage grows slowly because of the cost limitation. To efficiently model HD maps, we proposed a convolutional neural network with a novel prediction layer and a zoom module, called LineNet. It is designed for state-of-the-art lane detection in an unordered crowdsourced image dataset. And we introduced TTLane, a dataset for efficient lane detection in urban road modeling applications. Combining LineNet and TTLane, we proposed a pipeline to model HD maps with crowdsourced data for the first time. And the maps can be constructed precisely even with inaccurate crowdsourced data.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.