A LiDAR Point Cloud Generator: from a Virtual World to Autonomous Driving
A LiDAR Point Cloud Generator: from a Virtual World to Autonomous Driving
复制标题
DOI：
10.1145/3206025.3206080
复制
发表时间：
2018-03
期刊：
影响因子：
--
通讯作者：
Xiangyu Yue;Bichen Wu;S. Seshia;K. Keutzer;A. Sangiovanni-Vincentelli
中科院分区：
文献类型：
--
作者：
Xiangyu Yue;Bichen Wu;S. Seshia;K. Keutzer;A. Sangiovanni-Vincentelli
3D LiDAR扫描仪在自动驾驶中发挥着越来越重要的作用，因为它们可以生成环境的深度信息。然而，创建具有点级标签的大型3D LiDAR点云数据集需要大量的手动注释。这危及监督式深度学习算法的有效开发，这些算法通常需要大量数据。我们提出了一个框架，快速创建点云与准确的点级别的标签从电脑游戏。据我们所知，这是关于自动驾驶LiDAR点云模拟框架的第一篇出版物。该框架支持从自动驾驶场景和用户配置场景中收集数据。来自自动驾驶场景的点云可以用作深度学习算法的训练数据，而来自用户配置场景的点云可以用于系统地测试神经网络的脆弱性，并使用伪造的示例通过再训练使神经网络更加鲁棒。此外，场景图像可以同时捕获，以便传感器融合任务，提出了一种方法来做点云和捕获的场景图像之间的自动配准。通过使用生成的合成数据增强训练数据集，我们在点云分割中的准确性（+9%）得到了显着提高。我们的实验还表明，通过使用来自用户配置场景的点云来测试和重新训练网络，可以修复神经网络的弱点/盲点。
3D LiDAR scanners are playing an increasingly important role in autonomous driving as they can generate depth information of the environment. However, creating large 3D LiDAR point cloud datasets with point-level labels requires a significant amount of manual annotation. This jeopardizes the efficient development of supervised deep learning algorithms which are often data-hungry. We present a framework to rapidly create point clouds with accurate point-level labels from a computer game. To our best knowledge, this is the first publication on LiDAR point cloud simulation framework for autonomous driving. The framework supports data collection from both auto-driving scenes and user-configured scenes. Point clouds from auto-driving scenes can be used as training data for deep learning algorithms, while point clouds from user-configured scenes can be used to systematically test the vulnerability of a neural network, and use the falsifying examples to make the neural network more robust through retraining. In addition, the scene images can be captured simultaneously in order for sensor fusion tasks, with a method proposed to do automatic registration between the point clouds and captured scene images. We show a significant improvement in accuracy (+9%) in point cloud segmentation by augmenting the training dataset with the generated synthesized data. Our experiments also show by testing and retraining the network using point clouds from user-configured scenes, the weakness/blind spots of the neural network can be fixed.