论文标题
上下文道路车道和自动驾驶的符号生成
Contextual road lane and symbol generation for autonomous driving
论文作者
论文摘要
在本文中，我们提出了一种使用生成模型的新型方法检测和分割的方法。传统上，歧视模型已被用来在道路上以语义对像素进行分类。我们通过训练生成的对抗网络对车道和道路符号的概率分布进行建模。根据学习的概率分布，为给定图像生成了上下文感知的车道和路标，该图像将进一步量化最近的类标签。提出的方法已在BDD100K和Baidu Apolloscape数据集上进行了测试，并且通过在淡出淡出并遮挡的场景中生成泳道，对不利条件的表现出色，并且对不利条件的鲁棒性进行了鲁棒性。
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.
