Road extraction from motion cues in aerial video

ABSTRACT

Aerial video provides strong cues for automatic road extraction that are not available in static aerial images. Using stabilized (or geo-referenced) video data, capturing the distribution of spatio-temporal image derivatives gives a powerful, local representation of the scene variation and motion typical at each pixel. This allows a functional attribution of the scene; a "road" is defined as paths of consistent motion --- a definition which is valid in a large and diverse set of environments. Using a classical relationship between image motion and spatio-temporal image derivatives, road features can be extracted as image regions that have significant image variation and a motion consistent with its neighbors. The video pre-processing to generate image derivative distributions over arbitrarily long sequences is implemented in real time on standard laptops, and the flow field computation and interpretation involves a small number of 3 by 3 matrix operations at each pixel location. Example results are shown for an urban scene with both well-traveled and infrequently traveled roads, indicating that both can be discovered simultaneously. This method works robustly in scenes with significant traffic motion and is thus ideal for urban traffic scenes, which often are difficult to analyze using static imagery.

REFERENCES

• 1: P. Agouris, A. Stefanidis, and S. Gyftakis. Differential snakes for change detection in road segments. Photogrammetric Engineering & Remote Sensing, 67(12), 2001.
• 2: M. Bicego, S. Dalfini, G. Vernazza, and V. Murino. Automatic road extraction from aerial images by probabilistic contour tracking. In Proc. of IEEE Int. Conf. on Image Processing (ICIP03), volume III, pages 585--588, 2003.
• 3: X.-T. Dai, L. Lu, and G. Hager. Real-time video mosaicing with adaptive parameterized warping. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, volume (Demo Program), 2001.
• 4: P. Doucette, P. Agouris, A. Stefanidis, and M. Musavi. Self-organized clustering for road extraction in classified imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 55(5-6):347--358, 2001.
• 5: A. Faber and W. Forstner. Detection of dominant orthogonal structures in small scale imagery. International Archives of Photogrammetry and Remote Sensing, 33(Part B3/1):274--281, 2000.
• 6: Hany Farid , Eero P. Simoncelli, Optimally Rotation-Equivariant Directional Derivative Kernels, Proceedings of the 7th International Conference on Computer Analysis of Images and Patterns, p.207-214, September 10-12, 1997
• 7: Donald Geman , Bruno Jedynak, An Active Testing Model for Tracking Roads in Satellite Images, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.18 n.1, p.1-14, January 1996 [doi>10.1109/34.476006]
• 8: W. E. L. Grimson , C. Stauffer , R. Romano , L. Lee, Using Adaptive Tracking to Classify and Monitor Activities in a Site, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, p.22, June 23-25, 1998
• 9: S. Hinz and A. Baumgartner. Automatic extraction of urban road networks from multi-view aerial imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 53:83--98, 2003.
• 10: Berthold K. Horn, Robot Vision, McGraw-Hill Higher Education, 1986
• 11: S. V. Huffel and J. Vandewalle. The Total Least Squares Problem: Computational Aspects and Analysis. Society for Industrial and Applied Mathematics, Philadelphia, 1991.
• 12: I. Laptev , H. Mayer , T. Lindeberg , W. Eckstein , C. Steger , A. Baumgartner, Automatic extraction of roads from aerial images based on scale space and snakes, Machine Vision and Applications, v.12 n.1, p.23-31, July 2000 [doi>10.1007/s001380050004]
• 13: H. H. Nagel, Extending the `oriented smoothness constraint' into the temporal domain and the estimation of derivatives of optical flow, Proceedings of the first european conference on Computer vision, p.139-148, April 1990, Antibes, France
• 14: Robert Pless , Tomásˇ Brodský , Yiannis Aloimonos, Detecting Independent Motion: The Statistics of Temporal Continuity, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.22 n.8, p.768-773, August 2000 [doi>10.1109/34.868679]
• 15: R. Pless, J. Larson, S. Siebers, and B. Westover. Evaluation of local models of dynamic backgrounds. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003.
• 16: F. M. Porikli. Road extraction by point-wise gaussian models. In SPIE AeroSense Technologies and Systems for Defense and Security, volume 5093, pages 758--764, 2003.
• 17: K. Price. Urban street grid description and verification. In IEEE Workshop on Applications of Computer Vision, pages 148--154, 2000.
• 18: F. Tupin, H. Maitre, J.-F. Mangin, J.-M. Nicolas, and E. Pechersky Detection of linear features in SAR images: Application to the road network extraction. IEEE Trans. Geosci. Remote Sensing, 36(2):434--453, Mar. 1998.
• 19: C. Wiedemann, C. Heipke, H. Mayer, and S. Hinz. Automatic extraction and evaluation of road networks from moms-2p imagery. International Archives of Photogrammetry and Remote Sensing, 32(3):285--291, 1998.
• 20: L. Wixson, Detecting Salient Motion by Accumulating Directionally-Consistent Flow, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.22 n.8, p.774-780, August 2000 [doi>10.1109/34.868680]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.8 Scene Analysis

Additional Classification:
  H. Information Systems
  H.2 DATABASE MANAGEMENT
      H.2.8 Database applications
          Subjects: Spatial databases and GIS

General Terms:
Algorithms, Measurement

Keywords:
aerial video, statistical video processing