Automatic large-scale data acquisition via crowdsourcing for crosswalk classification: A deep learning approach
Automatic large-scale data acquisition via crowdsourcing for crosswalk classification: A deep learning approach
复制标题
DOI：
10.1016/j.cag.2017.08.004
复制
发表时间：
2017-11-01
影响因子：
2.5
通讯作者：
Oliveira-Santos, Thiago
中科院分区：
文献类型：
--
作者：
Berriel, Rodrigo F.;Rossi, Franco Schmidt;Oliveira-Santos, Thiago
正确识别人行横道是驾驶活动和移动自主性的一项重要任务。多年来，在文献中已经提出了许多人行横道分类、检测和定位系统。这些系统使用不同的视角来解决人行横道分类问题：卫星图像，驾驶舱视图（从汽车顶部或挡风玻璃后面）和行人视角。文献中的大多数作品都是使用小型和局部数据集（即多样性较低的数据集）进行设计和评估的。扩展到大型数据集对注释过程提出了挑战。此外，在文献中仍然需要进行跨数据库实验，因为通常很难在最终应用的相同地点和条件下收集数据。在本文中，我们提出了一个基于深度学习的人行横道分类系统。为此，利用OpenStreetMap和Google街景等众包平台，通过自动获取和注释大型数据库来实现自动训练。此外，这项工作还提出了一个使用全自动数据采集和注释训练的模型与部分注释的模型的比较研究。跨数据库的实验也包括在实验中，以表明所提出的方法，使使用与真实的世界的应用程序。我们的研究结果表明，在全自动数据库上训练的模型实现了较高的总体准确率（94.12%），并且通过手动注释数据库的特定部分可以实现统计上的显著改善（达到96.30%）。最后，跨数据库的实验结果表明，这两个模型是强大的图像和场景的许多变化，表现出一致的行为。(C)2017爱思唯尔有限公司版权所有
Correctly identifying crosswalks is an essential task for the driving activity and mobility autonomy. Many crosswalk classification, detection and localization systems have been proposed in the literature over the years. These systems use different perspectives to tackle the crosswalk classification problem: satellite imagery, cockpit view (from the top of a car or behind the windshield), and pedestrian perspective. Most of the works in the literature are designed and evaluated using small and local datasets, i.e. datasets that present low diversity. Scaling to large datasets imposes a challenge for the annotation procedure. Moreover, there is still need for cross-database experiments in the literature because it is usually hard to collect the data in the same place and conditions of the final application. In this paper, we present a crosswalk classification system based on deep learning. For that, crowdsourcing platforms, such as OpenStreetMap and Google Street View, are exploited to enable automatic training via automatic acquisition and annotation of a large-scale database. Additionally, this work proposes a comparison study of models trained using fully-automatic data acquisition and annotation against models that were partially annotated. Cross-database experiments were also included in the experimentation to show that the proposed methods enable use with real world applications. Our results show that the model trained on the fully automatic database achieved high overall accuracy (94.12%), and that a statistically significant improvement (to 96.30%) can be achieved by manually annotating a specific part of the database. Finally, the results of the cross-database experiments show that both models are robust to the many variations of image and scenarios, presenting a consistent behavior. (C) 2017 Elsevier Ltd. All rights reserved.