arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.00733cs.CVeess.IV
收藏

结合深度学习和基于模型的方法进行鲁棒的实时的语义地标检测

Combining Deep Learning and Model-Based Methods for Robust Real-Time Semantic Landmark Detection

University of the Bundeswehr Munich(慕尼黑联邦国防军大学)

Benjamin Naujoks, Patrick Burger, Hans-Joachim Wuensche

摘要:

与抽象特征相比,重要对象,即所谓的地标,是车辆定位和导航的更自然的手段,特别是在具有挑战性的非结构化环境中。主要的挑战是在各种光照条件和不断变化的环境(生长的植被)中识别地标,同时只有很少的训练样本可用。我们提出了一种新的方法,利用深度学习以及基于模型的方法来克服对大数据集的需求。使用RGB图像和光检测和测距(LiDAR)点云,我们的方法结合了卷积神经网络(CNN)的最先进的分类结果,通过考虑先前时间步长的先验知识,具有鲁棒的基于模型的方法。在一个具有挑战性的现实场景中,以树木和灌木丛作为地标进行的评估显示,与纯粹基于学习的最先进的3D探测器相比,结果令人鼓舞,同时速度明显更快。

英文摘要:

Compared to abstract features, significant objects, so-called landmarks, are a more natural means for vehicle localization and navigation, especially in challenging unstructured environments. The major challenge is to recognize landmarks in various lighting conditions and changing environment (growing vegetation) while only having few training samples available. We propose a new method which leverages Deep Learning as well as model-based methods to overcome the need of a large data set. Using RGB images and light detection and ranging (LiDAR) point clouds, our approach combines state-of-the-art classification results of Convolutional Neural Networks (CNN), with robust model-based methods by taking prior knowledge of previous time steps into account. Evaluations on a challenging real-wold scenario, with trees and bushes as landmarks, show promising results over pure learning-based state-of-the-art 3D detectors, while being significant faster.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑