IEEE Trans Image Process. 2019 Apr;28(4):1675-1690. doi: 10.1109/TIP.2018.2881829. Epub 2018 Nov 19.
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 and balconies) in urban localization. Extensive experiments demonstrate that our 2D-3D correspondence search achieves the state-of-the-art localization accuracy on multiple benchmark datasets. Furthermore, our experiments on a large Google street view image dataset show the potential of large-scale localization entirely on a typical mobile device.
我们提出了一种使用图像进行大规模城市定位的全设备系统设计。该设计集成了紧凑的图像检索和 2D-3D 对应搜索，以估计广阔城市区域的位置。我们的设计与 GPS 无关，也不需要网络连接。为了克服移动设备的资源限制，我们提出了一种系统设计，利用图像检索的可扩展性优势和基于 3D 模型的定位的准确性。此外，我们提出了一种新的基于哈希的级联搜索，用于快速计算 2D-3D 对应关系。此外，我们提出了一种新的多对一 RANSAC 用于准确的姿势估计。新的多对一 RANSAC 解决了城市定位中重复建筑物结构（如窗户和阳台）的挑战。广泛的实验表明，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，我们在大型 Google 街景图像数据集上的实验表明，完全在典型移动设备上进行大规模定位具有潜力。
