ABSTRACT
Cartographic databases can be kept up to date through aerial image analysis. Such analysis is optimized when one knows what parts of an aerial image are roads and when one knows locations of complex road structures, such as overpasses and intersections. This paper proposes self-supervised computer vision algorithms that analyze a publicly available cartographic resource (i.e., screenshots of road vectors) to, without human intervention, identify road image-regions and detects overpasses.
Our algorithm segments a given input image into two parts: road- and non-road image regions. It does so not by learning a global appearance model of roads from hand-labeled data, but rather by approximating a locally consistent model of the roads' appearance from self-obtained data. In particular, the learned local model is used to execute a binary classification. We then apply an MRF to smooth potentially inconsistent binary classification outputs.
To detect overpasses, our method scrutinizes screenshots of road vector images to approximate the geometry of the underlying road vector and use the estimated geometry to localize overpasses.
Our methods, based on experiments using inter-city highway ortho-images, show promising results. Segmentation results showed on average over 90% recall; overpass detection results showed 94% accuracy.
- E. Baltsavias and C. Zhang. Automated updating of road databases from aerial imagery. International Journal of Applied Earth Observation and Geoinformation, 6:199--213, 2005.Google ScholarCross Ref
- L. Cao and J. Krumm. From gps traces to a routable road map. In Proceedings of the ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, pages 3--12, 2009. Google ScholarDigital Library
- C.-C. Chen, C. A. Knoblock, and C. Shahabi. Automatically conflating road vector data with orthoimagery. GeoInformation, 10:495--530, 2006. Google ScholarDigital Library
- Y.-Y. Chiang and C. A. Knoblock. Automatic extraction of road intersection position, connectivity and orientations from raster maps. In Proceedings of the ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, 2008. Google ScholarDigital Library
- P. Dollar, Z. Tu, and S. Belongie. Supervised learning of edges and object boundaries. In Proceedings of Computer Vision and Pattern Recognition, pages 1964--1971, 2006. Google ScholarDigital Library
- M. flavie Auclair Fortier, D. Ziou, C. Armenakis, and S. Wang. Automated updating of road information from aerial images. In Proceedings of American Society Photogrammetry and Remote Sensing, pages 16--23, 2000.Google Scholar
- T. Geraud and J.-B. Mouret. Fast road network extractioin in satellite images using mathematical morphology and markov random fields. Journal on Applied Signal Processing, 16:2503--2514, 2004. Google ScholarDigital Library
- G. Heitz and D. Koller. Learning spatial context: Using stuff to find things. In Proceedings of European Conference on Computer Vision, 2008. Google ScholarDigital Library
- J. Hu, A. Razdan, J. C. Femiani, M. Cui, and P. Wonka. Road network extraction and intersection detection from aerial images by tracking road footprints. IEEE Transactions on Geoscience and Remote Sensing, 45(12):4144--4157, 2007.Google ScholarCross Ref
- P. Kahn, L. Kitchen, and E. Riseman. A fast line finder for vision-guided robot navigation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12(11):1098--1102, 1990. Google ScholarDigital Library
- S. Kluckner, M. Donoser, and H. Bischof. Super-pixel class segmentation in large-scale aerial imagery. In Proceedings of Annual Workshop of the Austrian Association for Pattern Recognition, 2010.Google Scholar
- J.-F. Lalonde, A. A. Efros, and S. G. Narasimhan. Detecting ground shadows in outdoor consumer photographs. In Proceedings of European Conference on Computer Vision, pages 322--335, 2010. Google ScholarDigital Library
- F. Leberl, H. Bischof, H. Grabner, and S. Kluckner. Recognizing cars in aerial imagery to improve orthophotos. In Proceedings of International Symposiums on Advances in Geographic Information Systems, 2007. Google ScholarDigital Library
- T. Leung and J. Malik. Representing and recognizing the visual appearance of materials using three-dimensional textons. International Journal of Computer Vision, 43(1):29--44, 2001. Google ScholarDigital Library
- J. Malik, S. Belongie, T. Leung, and J. Shi. Contour and texture analysis for image segmentation. International Journal of Computer Vision, 43(1):7--27, 2001. Google ScholarDigital Library
- D. R. Martin, C. C. Fowlkes, and J. Malik. Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(1), 2004. Google ScholarDigital Library
- V. Mnih and G. E. Hinton. Learning to detect roads in high-resolution aerial images. In Proceedings of European Conference on Computer Vision, pages 210--223, 2010. Google ScholarDigital Library
- V. Nair and J. J. Clark. An unsupervised, online learning framework for moving object detection. In Proceedings of Computer Vision and Pattern Recognition, pages 317--324, 2004. Google ScholarDigital Library
- A. Y. Ng, M. I. Jordan, and Y. Weiss. On spectral clusterings: Analysis and an algorithm. In Proceedings of Neural Information Processing Systems, pages 849--856, 2001.Google Scholar
- M. Ortner, X. Descombes, and J. Zerubia. Building outline extraction from digital elevation models using marked point processes. International Journal of Computer Vision, 72(2):107--132, 2007. Google ScholarDigital Library
- C. Qian, B. Gale, and J. Bach. Earth documentation: Overpass detection using mobile lidar. In Proceedings of IEEE International Conference on Image Processing, pages 3901--3904, 2010.Google ScholarCross Ref
- J. Schpok. Geometric overpass extraction from vector road data and dsms. In Proceedings of ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, pages 3--8, 2011. Google ScholarDigital Library
- Y.-W. Seo. Augmenting Cartographic Resources and Assessing Roadway State for Vehicle Navigation. PhD thesis, The Robotics Institute, Carnegie Mellon University, April 2012. tech. report CMU-RI-TR-12-13.Google Scholar
- Y.-W. Seo, C. Urmson, D. Wettergreen, and J.-W. Lee. Augmenting cartographic resources for autonomous driving. In Proceedings of ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, pages 13--22, 2009. Google ScholarDigital Library
- B. Soleimani, M.-H. Z. Ashtiani, B. H. Soleimani, and H. Moradi. A disaster invariant feature for localization. In Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 1096--1101, 2010.Google ScholarCross Ref
- A. Tabibiazar and O. Basir. Kernel-based modeling and optimization for density estimation in transportation systems using floating car data. In Proceedings of International IEEE Conference on Intelligent Transportation Systems, pages 576--581, 2011.Google ScholarCross Ref
- C. Tomasi and R. Manduchi. Bilateral filtering for gray and color images. In Proceedings of International Conference on Computer Vision, pages 839--846, 1998. Google ScholarDigital Library
- Y. Weiss. Segmentation using eigenvectors: A unifying view. In Proceedings of International Conference on Computer Vision, pages 975--982, 1999. Google ScholarDigital Library
Index Terms
- Exploiting publicly available cartographic resources for aerial image analysis
Recommendations
Ortho-image analysis for producing lane-level highway maps
SIGSPATIAL '12: Proceedings of the 20th International Conference on Advances in Geographic Information SystemsThis paper presents new aerial image analysis algorithms that, from highway ortho-images, produce lane-level detailed maps. We analyze screenshots of road vectors to obtain the relevant spatial and photometric cues of road image-regions. We then refine ...
Augmenting cartographic resources for autonomous driving
GIS '09: Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information SystemsIn this paper we present algorithms for automatically generating a road network description from aerial imagery. The road network inforamtion (RNI) produced by our algorithm includes a composite topoloigical and spatial representation of the roads ...
Comments