当前位置: X-MOL 学术IEEE Trans. Pattern Anal. Mach. Intell. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Ultra Fast Deep Lane Detection With Hybrid Anchor Driven Ordinal Classification.
IEEE Transactions on Pattern Analysis and Machine Intelligence ( IF 23.6 ) Pub Date : 2022-06-13 , DOI: 10.1109/tpami.2022.3182097
Zequn Qin , Pengyi Zhang , Xi Li

Modern methods mainly regard lane detection as a problem of pixel-wise segmentation, which is struggling to address the problems of efficiency and challenging scenarios like severe occlusions and extreme lighting conditions. Inspired by human perception, the recognition of lanes under severe occlusions and extreme lighting conditions is mainly based on contextual and global information. Motivated by this observation, we propose a novel, simple, yet effective formulation aiming at ultra fast speed and the problem of challenging scenarios. Specifically, we treat the process of lane detection as an anchor-driven ordinal classification problem using global features. First, we represent lanes with sparse coordinates on a series of hybrid (row and column) anchors. With the help of the anchor-driven representation, we then reformulate the lane detection task as an ordinal classification problem to get the coordinates of lanes. Our method could significantly reduce the computational cost with the anchor-driven representation. Using the large receptive field property of the ordinal classification formulation, we could also handle challenging scenarios. Extensive experiments on four lane detection datasets show that our method could achieve state-of-the-art performance in terms of both speed and accuracy. A lightweight version could even achieve 300+ frames per second(FPS). Our code is at https://github.com/cfzd/Ultra-Fast-Lane-Detection-v2.

中文翻译:

具有混合锚驱动序数分类的超快速深度车道检测。

现代方法主要将车道检测视为像素级分割的问题,它正在努力解决效率问题和严重遮挡和极端光照条件等具有挑战性的场景。受人类感知的启发,严重遮挡和极端光照条件下的车道识别主要基于上下文和全局信息。受此观察的启发,我们提出了一种新颖、简单但有效的配方,旨在解决超快的速度和具有挑战性的场景问题。具体来说,我们将车道检测过程视为使用全局特征的锚驱动序数分类问题。首先,我们在一系列混合(行和列)锚点上表示具有稀疏坐标的车道。在锚驱动表示的帮助下,然后,我们将车道检测任务重新表述为一个序数分类问题,以获得车道的坐标。我们的方法可以通过锚驱动表示显着降低计算成本。使用序数分类公式的大感受野属性,我们还可以处理具有挑战性的场景。在四个车道检测数据集上进行的大量实验表明,我们的方法在速度和准确性方面都可以达到最先进的性能。轻量级版本甚至可以达到每秒 300+ 帧 (FPS)。我们的代码位于 https://github.com/cfzd/Ultra-Fast-Lane-Detection-v2。使用序数分类公式的大感受野属性,我们还可以处理具有挑战性的场景。在四个车道检测数据集上进行的大量实验表明,我们的方法在速度和准确性方面都可以达到最先进的性能。轻量级版本甚至可以达到每秒 300+ 帧 (FPS)。我们的代码位于 https://github.com/cfzd/Ultra-Fast-Lane-Detection-v2。使用序数分类公式的大感受野属性,我们还可以处理具有挑战性的场景。在四个车道检测数据集上进行的大量实验表明,我们的方法在速度和准确性方面都可以达到最先进的性能。轻量级版本甚至可以达到每秒 300+ 帧 (FPS)。我们的代码位于 https://github.com/cfzd/Ultra-Fast-Lane-Detection-v2。
更新日期:2022-06-13
down
wechat
bug