论文标题
端到端的车道形状预测变压器
End-to-end Lane Shape Prediction with Transformers
论文作者
论文摘要
车道检测是将车道标记识别为近似曲线的过程，被广泛用于自动驾驶汽车中的车道出发警告和自适应巡航控制。流行的管道以两个步骤解决了它 - 功能提取和后处理虽然有用，但在学习全球环境和泳道的长而薄的结构方面过于效率和缺陷。为了解决这些问题，我们提出了一种端到端方法，该方法使用使用变压器构建的网络来学习更丰富的结构和上下文，该方法直接输出车道形状模型的参数。车道形状模型是根据道路结构和相机姿势制定的，为网络输出参数提供了物理解释。变压器用自我发项机制的非本地相互作用对非本地相互作用进行建模，以捕获细长的结构和全球环境。提出的方法在Tusimple基准测试上进行了验证，并显示了最先进的精度，最轻巧的型号尺寸和最快的速度。此外，我们的方法对具有挑战性的自我收集的车道检测数据集显示出极好的适应性，显示了其在实际应用程序中的强大部署潜力。代码可在https://github.com/liuruijin17/lstr上找到。
Lane detection, the process of identifying lane markings as approximated curves, is widely used for lane departure warning and adaptive cruise control in autonomous vehicles. The popular pipeline that solves it in two steps -- feature extraction plus post-processing, while useful, is too inefficient and flawed in learning the global context and lanes' long and thin structures. To tackle these issues, we propose an end-to-end method that directly outputs parameters of a lane shape model, using a network built with a transformer to learn richer structures and context. The lane shape model is formulated based on road structures and camera pose, providing physical interpretation for parameters of network output. The transformer models non-local interactions with a self-attention mechanism to capture slender structures and global context. The proposed method is validated on the TuSimple benchmark and shows state-of-the-art accuracy with the most lightweight model size and fastest speed. Additionally, our method shows excellent adaptability to a challenging self-collected lane detection dataset, showing its powerful deployment potential in real applications. Codes are available at https://github.com/liuruijin17/LSTR.
