论文标题
罗纳尔德：可靠的稳健的神经网络输出增强活性车道检测
RONELD: Robust Neural Network Output Enhancement for Active Lane Detection
论文作者
论文摘要
准确的车道检测对于自动驾驶汽车的导航至关重要，尤其是划定车辆当前行驶的单一道路空间的活动车道。最新的最先进的车道检测算法利用卷积神经网络（CNN）来训练诸如Tusimple和Culane等流行基准的深度学习模型。尽管这些模型中的每一个都在从同一数据集获得的火车和测试输入上效果特别好，但性能在不同环境的未见数据集上大大下降。在本文中，我们提出了一种实时鲁棒神经网络输出增强，用于活跃的车道检测方法（Roneld）方法，以识别，跟踪和优化深度学习概率映射输出的活动泳道。我们首先从概率图输出中自适应提取车道点，然后检测到弯曲和直泳道，然后再使用加权最小二乘正方形在直道上的线性回归，以固定因真实图像中边缘图的碎片而产生的损坏的车道边缘。最后，我们通过跟踪前帧假设真正的活动车道。实验结果表明，使用Roneld在交叉数据库验证测试中，精度提高了两倍。
Accurate lane detection is critical for navigation in autonomous vehicles, particularly the active lane which demarcates the single road space that the vehicle is currently traveling on. Recent state-of-the-art lane detection algorithms utilize convolutional neural networks (CNNs) to train deep learning models on popular benchmarks such as TuSimple and CULane. While each of these models works particularly well on train and test inputs obtained from the same dataset, the performance drops significantly on unseen datasets of different environments. In this paper, we present a real-time robust neural network output enhancement for active lane detection (RONELD) method to identify, track, and optimize active lanes from deep learning probability map outputs. We first adaptively extract lane points from the probability map outputs, followed by detecting curved and straight lanes before using weighted least squares linear regression on straight lanes to fix broken lane edges resulting from fragmentation of edge maps in real images. Lastly, we hypothesize true active lanes through tracking preceding frames. Experimental results demonstrate an up to two-fold increase in accuracy using RONELD on cross-dataset validation tests.
