See the Future: A Semantic Segmentation Network Predicting Ego-Vehicle Trajectory With a Single Monocular Camera
See the Future: A Semantic Segmentation Network Predicting Ego-Vehicle Trajectory With a Single Monocular Camera
复制标题
预见未来：用单目相机预测自我车辆轨迹的语义分割网络
DOI：
10.1109/lra.2020.2975414
复制
发表时间：
2020-04-01
影响因子：
5.2
通讯作者：
Liu, Ming
中科院分区：
文献类型：
--
作者：
Sun, Yuxiang;Zuo, Weixun;Liu, Ming
自车轨迹预测是自动驾驶汽车检测碰撞并避免事故发生的重要手段。最近的方法采用预先已知或在线获取的道路拓扑或几何形状作为其预测模型的运动约束。然而，先前已知的信息（例如，预先制作的地图）可能会因为道路建设引起的时间变化而变得不可靠。然而，在线感知可能需要高成本的传感器，如大型视场激光扫描仪，以获得当地环境的总体结构，这使得预测难以负担，尤其是驾驶辅助系统。因此，在这封信中，我们提供了一个不使用道路拓扑或几何的自我车辆轨迹预测的解决方案。我们将此问题表述为两类语义分割问题，并开发了一种新的基于序列的深度神经网络来预测轨迹。我们在运行时需要的唯一传感器是一个前视单目摄像头。我们的网络的输入是几个连续的图像，输出是预测的轨迹掩模，可以直接覆盖在当前的前视图像上。我们从KITTI中创建了不同预测范围的数据集。实验结果证实了该方法的有效性和相对于基线的优越性。
Ego-vehicle trajectory prediction is important for autonomous vehicles to detect collisions and accordingly avoid accidents. Recent approaches employ prior-known or on-line acquired road topology or geometries as motion constraints for their predictive models. However, the prior-known information (e.g., pre-built maps) might become unreliable due to, for example, temporal changes caused by road constructions. Whereas on-line perception may require high-cost sensors, such as large filed-of-view laser scanners, to get an overview structure of the local environment, making the prediction difficult to afford, especially for driving assistance systems. So in this letter, we provide a solution without using road topology or geometries for ego-vehicle trajectory prediction. We formulate this problem as a two-class semantic segmentation problem and develop a novel sequence-based deep neural network to predict the trajectory. The only sensor we need during runtime is a single front-view monocular camera. The inputs to our network are several consecutive images, and the output is the predicted trajectory mask that can be directly overlaid on the current front-view image. We create our datasets with different prediction horizons from KITTI. The experimental results confirm the effectiveness of our approach and the superiority over the baselines.