Towards Complete, Geo-referenced 3d Models from Crowd-sourced Amateur Images
نویسندگان
چکیده
Despite a lot of recent research, photogrammetric reconstruction from crowd-sourced imagery is plagued by a number of recurrent problems. (i) The resulting models are chronically incomplete, because even touristic landmarks are photographed mostly from a few “canonical” viewpoints. (ii) Man-made constructions tend to exhibit repetitive structure and rotational symmetries, which lead to gross errors in the 3D reconstruction and aggravate the problem of incomplete reconstruction. (iii) The models are normally not geo-referenced. In this paper, we investigate the possibility of using sparse GNSS geo-tags from digital cameras to address these issues and push the boundaries of crowd-sourced photogrammetry. A small proportion of the images in Internet collections (≈ 10%) do possess geo-tags. While the individual geo-tags are very inaccurate, they nevertheless can help to address the problems above. By providing approximate geo-reference for partial reconstructions they make it possible to fuse those pieces into more complete models; the capability to fuse partial reconstruction opens up the possibility to be more restrictive in the matching phase and avoid errors due to repetitive structure; and collectively, the redundant set of low-quality geo-tags can provide reasonably accurate absolute geo-reference. We show that even few, noisy geo-tags can help to improve architectural models, compared to puristic structure-from-motion only based on image correspondence.
منابع مشابه
Sar Simulation Based Change Detection with High-resolution Sar Images in Urban Environments
Combined processing using different sensor types, i.e. for applications like change detection, requires a good geo-referencing. Furthermore the individual sensor properties have to be taken into account. SAR systems are side-looking and run-time systems. They suffer from occlusions and ambiguities especially in urban areas. Additionally layover and shadow effects disturb the geo-referencing of ...
متن کاملState of the Art and Challenges in Crowd Sourced Modeling
The recent ubiquitous availability of large crowd sourced photo collections (e.g. Facebook, Picassa, Flickr) has opened a wide field of new applications ranging from virtual tourism, cultural heritage preservation to intelligence and defense applications. The research in this active area was energized by the seminal PhotoTourism paper (Snavely et al., 2006) starting from registering 3000 photos...
متن کاملA Portable Multi-sensor System for Geo-referenced Image Sequences
The demand of high-resolution spatial information such as geo-referenced images and realistic 3D models is rapidly increasing. Most existing systems to acquire such information involve expensive platforms such as manned or unmanned, air or ground vehicles to obtain high-resolution images and GPS/IMU data. Thanks to the availability of small image acquisition devices and light-weighted MEMS GPS/...
متن کامل3D Reconstruction of Dynamic Textures in Crowd Sourced Data
We propose a framework to automatically build 3D models for scenes containing structures not amenable for photo-consistency based reconstruction due to having dynamic appearance. We analyze the dynamic appearance elements of a given scene by leveraging the imagery contained in Internet image photo-collections and online video sharing websites. Our approach combines large scale crowd sourced SfM...
متن کاملAutomated CAD Model Based Geo-Referencing for High- Resolution SAR Data Fusion in Urban Environments
Fusion of SAR and optical images has to cope with the different imaging properties of both sensor types. In order to allow a meaningful data fusion, highly accurate geo-referenced images have to be provided. Based on CAD models of buildings, for example from available 3D-city models, simulated SAR images can be created using a SAR simulator. The correspondence between images of buildings create...
متن کامل