Large Scale Visual Geo-Localization of Images in Mountainous Terrain

Baatz, Georges; Saurer, Olivier; Köser, Kevin; Pollefeys, Marc

doi:10.1007/978-3-642-33709-3_37

Cited by 122 publications

(118 citation statements)

References 17 publications

Supporting

Mentioning

115

Contrasting

Unclassified

Order By: Relevance

“…While the experiments in this paper are at a modest scale (1600km 2 region of interest), the approach scales up easily both in terms of data availability and computational complexity. Our approach is the first to use overhead imagery and land cover survey data to geolocate photographs, and it is complementary with the impressive mountain-based geolocation method of [2] which also uses a widely available geographic feature (digital elevation maps). Middle: similar (in green) and dissimilar (in red) groundlevel and satellite image pairs used for training the SVM in our discriminative translation approach.…”

Section: Resultsmentioning

confidence: 99%

“…2 Figure 3 shows a snapshot of the dataset at our region of interest. The dataset contains two hierarchical levels of classes including 8 general classes (e.g., Developed & Other Human Use, Shrubland & Grassland, etc.)…”

Section: Land Cover Attribute Imagerymentioning

confidence: 99%

“…A query image in an unsampled location has no hope of being accurately geolocated. Recently, [2] presented an algorithm that does not require ground-level training images. They leverage a digital elevation model to synthesize 3D surfaces in mountainous terrain and match the contour of mountains extracted from ground-level images to the 3D model.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Cross-View Image Geo-localization

Lin¹,

Belongie²,

Hays³

2016

Large-Scale Visual Geo-Localization

View full text Add to dashboard Cite

The recent availability of large amounts of geotagged imagery has inspired a number of data driven solutions to the image geolocalization problem. Existing approaches predict the location of a query image by matching it to a database of georeferenced photographs. While there are many geotagged images available on photo sharing and street view sites, most are clustered around landmarks and urban areas. The vast majority of the Earth's land area has no ground level reference photos available, which limits the applicability of all existing image geolocalization methods. On the other hand, there is no shortage of visual and geographic data that densely covers the Earthwe examine overhead imagery and land cover survey data -but the relationship between this data and ground level query photographs is complex. In this paper, we introduce a cross-view feature translation approach to greatly extend the reach of image geolocalization methods. We can often localize a query even if it has no corresponding groundlevel images in the database. A key idea is to learn the relationship between ground level appearance and overhead appearance and land cover attributes from sparsely available geotagged ground-level images. We perform experiments over a 1600 km 2 region containing a variety of scenes and land cover types. For each query, our algorithm produces a probability density over the region of interest.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Land Cover Attribute Imagerymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cross-View Image Geo-localization

Lin¹,

Belongie²,

Hays³

2016

Large-Scale Visual Geo-Localization

View full text Add to dashboard Cite

show abstract

“…Baatz et al (2012) use contourlets to match the horizon line of a query photograph to renderings of a digital elevation model, thus enabling accurate geo-localization in mountainous environments. Arandjelović and Zisserman (2011) incorporate domain knowledge into their descriptor by combining HoG features with an occupancy map derived from a figure-background segmentation.…”

Section: Related Workmentioning

confidence: 99%

Automatic Registration of Images to Untextured Geometry Using Average Shading Gradients

Plötz

Roth

2017

Int J Comput Vis

View full text Add to dashboard Cite

Many existing approaches for image-to-geometry registration assume that either a textured 3D model or a good initial guess of the 3D pose is available to bootstrap the registration process. In this paper we consider the registration of photographs to 3D models even when no texture information is available. This is very challenging as we cannot rely on texture gradients, and even shading gradients are hard to estimate since the lighting conditions are unknown. To that end, we propose average shading gradients, a rendering technique that estimates the average gradient magnitude over all lighting directions under Lambertian shading. We use this gradient representation as the building block of a registration pipeline based on matching sparse features. To cope with inevitable false matches due to the missing texture information and to increase robustness, the pose of the 3D model is estimated in two stages. Coarse pose hypotheses are first obtained from a single correct match each, subsequently refined using SIFT flow, and finally verified. We apply our algorithm to registering images of real-world objects to untextured 3D meshes of limited accuracy. Moreover, we show that registration can be performed even for paintings despite lacking photo-realism.

show abstract

“…Image analysis in mountain regions is a well investigated area, with applications that support environmental studies on climate change and tourism [7]. Mountain image analysis research focuses on peak identification in public photographs [2,1] and the problem of segmenting the portion of the photograph corresponding to a certain mountain in snow covered areas [24,22]. A prominent application field of mountain image analysis is snow information extraction.…”

Section: Related Workmentioning

confidence: 99%

A Framework for Outdoor Mobile Augmented Reality and Its Application to Mountain Peak Detection

Fedorov

Frajberg

Fraternali

2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Outdoor augmented reality applications project information of interest onto views of the world in real-time. Their core challenge is recognizing the meaningful objects present in the current view and retrieving and overlaying pertinent information onto such objects. In this paper we report on the development of a framework for mobile outdoor augmented reality application, applied to the overlay of peak information onto views of mountain landscapes. The resulting app operates by estimating the virtual panorama visible from the viewpoint of the user, using an online Digital Terrain Model (DEM), and by matching such panorama to the actual image framed by the camera. When a good match is found, meta-data from the DEM (e.g, peak name, altitude, distance) are projected in real time onto the view. The application, besides providing a nice experience to the user, can be employed to crowdsource the collection of annotated mountain images for environmental applications.

show abstract

Large Scale Visual Geo-Localization of Images in Mountainous Terrain

Cited by 122 publications

References 17 publications

Cross-View Image Geo-localization

Cross-View Image Geo-localization

Automatic Registration of Images to Untextured Geometry Using Average Shading Gradients

A Framework for Outdoor Mobile Augmented Reality and Its Application to Mountain Peak Detection

Contact Info

Product

Resources

About