arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.11124cs.CVcs.LGstat.ML
收藏

一种用于基于图像的摄像机定位的生成地图

A Generative Map for Image-based Camera Localization

fortiss GmbH(fortiss有限公司);Technical University of Munich(慕尼黑工业大学)

Mingpan Guo, Stefan Matthes, Jiaojiao Ye, Hao Shen

摘要:

在基于图像的相机定位系统中,关于环境的信息通常存储在某种表示中,其可以被称为地图。传统上,大多数地图都是建立在手工制作的功能。最近,神经网络作为一种数据驱动的地图表示方法引起了人们的关注,并在视觉定位方面显示出了很好的效果。然而,这些神经网络图通常很难被人类解释。可读的地图不仅是人类可以访问的,而且还提供了一种在地面真实姿态不可用时进行验证的方法。为了解决这个问题,我们提出了Generative Map,这是一种用于学习人类可读神经网络地图的新框架,通过将生成模型与卡尔曼滤波器相结合,这也允许它包含额外的传感器信息,如立体视觉里程计。为了进行评估,我们使用来自7-Scenes和Oxford RobotCar数据集的真实世界图像。我们证明,我们的生成地图可以查询与感兴趣的姿势从测试序列预测的图像,这非常类似于真实的场景。对于本地化,我们表明生成地图实现了与当前回归模型相当的性能。此外,我们的框架完全从头开始训练,不像回归模型依赖于大型ImageNet预训练网络。

英文摘要:

In image-based camera localization systems, information about the environment is usually stored in some representation, which can be referred to as a map. Conventionally, most maps are built upon hand-crafted features. Recently, neural networks have attracted attention as a data-driven map representation, and have shown promising results in visual localization. However, these neural network maps are generally hard to interpret by human. A readable map is not only accessible to humans, but also provides a way to be verified when the ground truth pose is unavailable. To tackle this problem, we propose Generative Map, a new framework for learning human-readable neural network maps, by combining a generative model with the Kalman filter, which also allows it to incorporate additional sensor information such as stereo visual odometry. For evaluation, we use real world images from the 7-Scenes and Oxford RobotCar datasets. We demonstrate that our Generative Map can be queried with a pose of interest from the test sequence to predict an image, which closely resembles the true scene. For localization, we show that Generative Map achieves comparable performance with current regression models. Moreover, our framework is trained completely from scratch, unlike regression models which rely on large ImageNet pretrained networks.

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。

↑