Scipediacontent: Scipediacontent moved page Draft Content 961427833 to Proesmans et al 2018a

2021-01-28T18:20:22Z

Scipediacontent moved page Draft Content 961427833 to Proesmans et al 2018a

Scipediacontent: Created page with " == Abstract == Modern cars are incorporating an increasing number of driver assist features, among which automatic lane keeping. The latter allows the car to properly positi..."

2021-01-28T18:20:19Z

Created page with " == Abstract == Modern cars are incorporating an increasing number of driver assist features, among which automatic lane keeping. The latter allows the car to properly positi..."

New page

== Abstract ==

Modern cars are incorporating an increasing number of driver assist features, among which automatic lane keeping. The latter allows the car to properly position itself within the road lanes, which is also crucial for any subsequent lane departure or trajectory planning decision in fully autonomous cars. Traditional lane detection methods rely on a combination of highly-specialized, hand-crafted features and heuristics, usually followed by post-processing techniques, that are computationally expensive and prone to scalability due to road scene variations. More recent approaches leverage deep learning models, trained for pixel-wise lane segmentation, even when no markings are present in the image due to their big receptive field. Despite their advantages, these methods are limited to detecting a pre-defined, fixed number of lanes, e.g. ego-lanes, and can not cope with lane changes. In this paper, we go beyond the aforementioned limitations and propose to cast the lane detection problem as an instance segmentation problem - in which each lane forms its own instance - that can be trained end-to-end. To parametrize the segmented lane instances before fitting the lane, we further propose to apply a learned perspective transformation, conditioned on the image, in contrast to a fixed "bird's-eye view" transformation. By doing so, we ensure a lane fitting which is robust against road plane changes, unlike existing approaches that rely on a fixed, pre-defined transformation. In summary, we propose a fast lane detection algorithm, running at 50 fps, which can handle a variable number of lanes and cope with lane changes. We verify our method on the tuSimple dataset and achieve competitive results.

== Original document ==

The different versions of the original document can be found in:

* [http://arxiv.org/abs/1802.05591 http://arxiv.org/abs/1802.05591]

* [http://arxiv.org/pdf/1802.05591 http://arxiv.org/pdf/1802.05591]

* [http://dx.doi.org/10.1109/ivs.2018.8500547 http://dx.doi.org/10.1109/ivs.2018.8500547]

* [http://xplorestaging.ieee.org/ielx7/8472796/8500355/08500547.pdf?arnumber=8500547 http://xplorestaging.ieee.org/ielx7/8472796/8500355/08500547.pdf?arnumber=8500547],
: [http://dx.doi.org/10.1109/ivs.2018.8500547 http://dx.doi.org/10.1109/ivs.2018.8500547]

* [https://arxiv.org/pdf/1802.05591.pdf https://arxiv.org/pdf/1802.05591.pdf],
: [https://dblp.uni-trier.de/db/journals/corr/corr1802.html#abs-1802-05591 https://dblp.uni-trier.de/db/journals/corr/corr1802.html#abs-1802-05591],
: [https://arxiv.org/abs/1802.05591 https://arxiv.org/abs/1802.05591],
: [http://ui.adsabs.harvard.edu/abs/2018arXiv180205591N/abstract http://ui.adsabs.harvard.edu/abs/2018arXiv180205591N/abstract],
: [https://ieeexplore.ieee.org/document/8500547 https://ieeexplore.ieee.org/document/8500547],
: [https://www.arxiv-vanity.com/papers/1802.05591 https://www.arxiv-vanity.com/papers/1802.05591],
: [https://academic.microsoft.com/#/detail/2964199920 https://academic.microsoft.com/#/detail/2964199920]

← Older revision	Revision as of 18:20, 28 January 2021
(No difference)

Proesmans et al 2018a - Revision history

Scipediacontent: Scipediacontent moved page Draft Content 961427833 to Proesmans et al 2018a

Scipediacontent: Created page with " == Abstract == Modern cars are incorporating an increasing number of driver assist features, among which automatic lane keeping. The latter allows the car to properly positi..."