通过优先级级联搜索和快速一对多RANSAC的设备上可扩展的基于图像的定位
On-device Scalable Image-based Localization via Prioritized Cascade Search and Fast One-Many RANSAC
摘要：
我们提出了一个完整的设备上的系统，大规模的城市定位使用图像的设计。所提出的设计集成了紧凑的图像检索和2D-3D对应搜索，以估计在广泛的城市区域的位置。我们的设计是GPS不可知的，不需要网络连接。为了克服移动设备的资源限制，我们提出了一个系统设计，利用图像检索的可扩展性优势和基于3D模型的定位精度。此外，我们提出了一种新的基于散列的级联搜索的快速计算的2D-3D对应。此外，我们提出了一个新的一个多RANSAC准确的姿态估计。新的一对多RANSAC解决了城市定位中重复建筑结构（例如窗户、阳台）的挑战。大量的实验表明，我们的2D-3D对应搜索在多个基准数据集上达到了最先进的定位精度。此外，我们的实验上的大型谷歌街景（GSV）图像数据集显示的潜力，大规模的本地化完全在一个典型的移动终端。
英文摘要：
We present the design of an entire on-device system for large-scale urban localization using images. The proposed design integrates compact image retrieval and 2D-3D correspondence search to estimate the location in extensive city regions. Our design is GPS agnostic and does not require network connection. In order to overcome the resource constraints of mobile devices, we propose a system design that leverages the scalability advantage of image retrieval and accuracy of 3D model-based localization. Furthermore, we propose a new hashing-based cascade search for fast computation of 2D-3D correspondences. In addition, we propose a new one-many RANSAC for accurate pose estimation. The new one-many RANSAC addresses the challenge of repetitive building structures (e.g. windows, balconies) in urban localization. Extensive experiments demonstrate that our 2D-3D correspondence search achieves state-of-the-art localization accuracy on multiple benchmark datasets. Furthermore, our experiments on a large Google Street View (GSV) image dataset show the potential of large-scale localization entirely on a typical mobile device.
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。
