arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.07120cs.CVcs.RO
收藏

用于自动驾驶的上下文道路车道和符号生成

Contextual road lane and symbol generation for autonomous driving

ZF TCI(采埃孚技术创新中心)

Ajay Soni, Pratik Padamwar, Krishna Reddy Konda

摘要:

在本文中,我们提出了一种新的方法,车道检测和分割使用生成模型。传统的判别模型已被用于对道路上的像素进行语义分类。我们通过训练一个生成对抗网络来模拟车道和道路符号的概率分布。基于学习的概率分布,上下文感知的车道和道路标志被生成为一个给定的图像,进一步量化为最近的类标签。在BDD 100K和百度ApolloScape数据集上进行了测试,结果表明该方法优于现有技术,并通过在淡出和遮挡场景中生成车道来显示对不利条件的鲁棒性。

英文摘要:

In this paper we present a novel approach for lane detection and segmentation using generative models. Traditionally discriminative models have been employed to classify pixels semantically on a road. We model the probability distribution of lanes and road symbols by training a generative adversarial network. Based on the learned probability distribution, context-aware lanes and road signs are generated for a given image which are further quantized for nearest class label. Proposed method has been tested on BDD100K and Baidu ApolloScape datasets and performs better than state of the art and exhibits robustness to adverse conditions by generating lanes in faded out and occluded scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑