Accurate Geo-Registration by Ground-to-Aerial Image Matching

By Qi Shan, Changchang Wu, Brian Curless, Yasutaka Furukawa, Carlos Hernández, S. M. Seitz. 2014

118 citations recorded by the source corpus.

We address the problem of geo-registering ground-based multi-view stereo models by ground-to-aerial image matching. The main contribution is a fully automated geo-registration pipeline with a novel viewpoint-dependent matching method that handles ground to aerial viewpoint variation. We conduct large-scale experiments which consist of many popular outdoor landmarks in Rome. The proposed approach demonstrates a high success rate for the task, and dramatically outperforms state-of-the-art techniques, yielding geo-registration at pixel-level accuracy.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Revisiting IM2GPS in the Deep Learning Era (2017, background): “Many approaches make used of aerial imagery for localization [3, 3, 27, 17].”
Wide-Area Image Geolocalization with Aerial Reference Imagery (2015, methodology): “[34] geo-register ground-level multiview stereo models using ground-to-aerial image matching.”
Geolocation Estimation of Photos Using a Hierarchical Model and Scene Classification (2018, background): “For this reason, some approaches additionally make use of satellite aerial imagery to enhance the geolocalization in sparsely covered regions [35,40,44,45].”
Multi-View Stereo: A Tutorial (2015, methodology): “Due to the scale and viewpoint changes, standard SfM procedure tends to fail [168].”
24/7 Place Recognition by View Synthesis (2018, unknown): “[44] use 3D structure to synthesize virtual views to match across extreme viewpoint changes for alignment of aerial to ground-level imagery.”
Cross-View Image Matching for Geo-Localization in Urban Environments (2017, background): “In particular, this problem has attracted considerable attention due to the availability of ground-level geo-tagged imagery [8, 27, 21, 28, 19, 18].”
Localizing and Orienting Street Views Using Overhead Imagery (2016, methodology): “Shan et al. [27] propose a fully automated system that registers ground-based multi-view Stereo models to aerial imagery using traditional multi-view and Structure from Motion technique.”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, methodology): “Instead of seeking invariant feature detections, Shan et al. (2014) propose a viewpoint-dependent matching technique by exploiting approximate alignment information and underlying 3D geometry.”
Learning deep representations for ground-to-aerial geolocalization (2015, background): “Shan et al. [24] propose ground-aerial image matching that first builds 3D point cloud from ground images with noisy geo-tags and performs depth-based warping to reproject ground images to one aerial view based on the estimated geometry.”
CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization (2018, background): “As a result, matching ground view photos to aerial imagery gradually becomes an increasingly popular geo-localization approach [5, 22, 37, 23, 49, 50, 46, 41, 53, 43].”