Name
Title | ||
|---|---|---|
LineNet: a Zoomable CNN for Crowdsourced High Definition Maps Modeling in Urban Environments. |
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. |
Year | Venue | Field |
|---|---|---|
2018 | arXiv: Computer Vision and Pattern Recognition | High definition,Pattern recognition,Computer science,Convolutional neural network,Zoom,Lane detection,Artificial intelligence |
DocType | Volume | Citations |
Journal | abs/1807.05696 | 0 |
PageRank | References | Authors |
0.34 | 5 | 7 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Dun Liang | 1 | 0 | 0.68 |
| Yuanchen Guo | 2 | 0 | 0.68 |
| Shaokui Zhang | 3 | 0 | 0.34 |
| Song-Hai Zhang | 4 | 224 | 23.56 |
| Peter M. Hall | 5 | 503 | 50.23 |
| Min Zhang | 6 | 134 | 38.40 |
| Shi-Min Hu | 7 | 3466 | 188.22 |