Image-based change detection of areal objects using differential snakes

ABSTRACT

Change detection is an important issue for modern geospatial information systems. In this paper we address change detection of areal objects (i.e. objects with closed-curve outlines). We specifically focus on the detection of movement (translation and rotation) and/or deformation of such objects using aerial imagery. The innovative approach we present in this paper combines geometric analysis with our model of differential snakes to support change detection. Geometric analysis proceeds by comparing the first moments of the two outlines describing the same object in different instances, to estimate translation. Moment information allows us to determine the principal axes and eigenvectors of these outlines, and this we can determine object rotation as the angle between these principal axes. Next, we apply polygon-clipping techniques to calculate the intersection and difference of these two outlines. We use this result to estimate the radial deformation of the object (expansion and contraction). The results are further refined through the use of our differential snakes model, to distinguish true change from the effects of inaccuracy in object determination. The aggregation of these tools defines a powerful approach for change detection. In the paper we present the theoretical background behind these components, and experimental results that demonstrate the performance of our approach.

REFERENCES

• 1: Agouris P., S. Gyftakis, A. Stefanidis, 2001. Dynamic Node Distribution in Adaptive Snakes for Road Extraction, Vision Interface (VI '01), Ottawa, pp. 134--140.
• 2: Agouris, P., A. Stefanidis, and S. Gyftakis, 2001. Differential Snakes for Change Detection in Road Segments. Photogrammetric Engineering & Remote Sensing, 67(12): 1391--1399.
• 3: Agouris, P., S. Gyftakis, and A. Stefanidis (2001). Quality-Aware Deformable Models for Change Detection, IEEE International Conference on Image Processing (ICIP) 2001, Thessaloniki, Greece, 2: 805--808.
• 4: Kalle Åström , Fredrik Kahl, Motion Estimation in Image Sequences Using the Deformation of Apparent Contours, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.21 n.2, p.114-127, February 1999 [doi>10.1109/34.748821]
• 5: Bascle, B., P. Bouthemy, R. Deriche, and F. Meyer, 1994. Tracking Complex Primitives in an Image Sequence. Proceedings of 12th International Conference on Pattern Recognition, Jerusalem: 426--431.
• 6: Michael J. Black , Yaser Yacoob, Recognizing Facial Expressions in Image Sequences Using Local Parameterized Models of Image Motion, International Journal of Computer Vision, v.25 n.1, p.23-48, Oct. 1997 [doi>10.1023/A:1007977618277]
• 7: Andrew Blake , Rupert Curwen , Andrew Zisserman, A framework for spatiotemporal control in the tracking of visual contours, International Journal of Computer Vision, v.11 n.2, p.127-145, Oct. 1993 [doi>10.1007/BF01469225]
• 8: Jörg Bredno , Thomas M. Lehmann , Klaus Spitzer, A General Discrete Contour Model in Two, Three, and Four Dimensions for Topology-Adaptive Multichannel Segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.25 n.5, p.550-563, May 2003 [doi>10.1109/TPAMI.2003.1195990]
• 9: Ching-Chien Chen , Craig A. Knoblock , Cyrus Shahabi , Yao-Yi Chiang , Snehal Thakkar, Automatically and accurately conflating orthoimagery and street maps, Proceedings of the 12th annual ACM international workshop on Geographic information systems, November 12-13, 2004, Washington DC, USA [doi>10.1145/1032222.1032231]
• 10: Dal Poz, A. P., S. Gyftakis, P. Agouris, 2000. Automated Road Extraction: Comparison of Methodologies and Experiments. Proc. ASPRS 2000, Washington, DC.
• 11: Douglas Decarlo , Dimitris Metaxas, Optical Flow Constraints on Deformable Models with Applications to Face Tracking, International Journal of Computer Vision, v.38 n.2, p.99-127, July 2000 [doi>10.1023/A:1008122917811]
• 12: Daniel Freedman, Effective Tracking through Tree-Search, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.25 n.5, p.604-615, May 2003 [doi>10.1109/TPAMI.2003.1195994]
• 13: Kass, M., A. Witkin, and D. Terzopoulos, 1987. Snakes: Active contour models. Proc. 1st International Conference on Computer Vision, London: 259--268.
• 14: F. Leymarie , M. D. Levine, Tracking Deformable Objects in the Plane Using an Active Contour Model, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.15 n.6, p.617-634, June 1993 [doi>10.1109/34.216733]
• 15: Li, M., and C. Kambhamettu, 2002. Motion-based Post Processing of Deformable Contours. Proceedings of 3rd Indian Conference on Computer Vision, Graphics and Image Processing, Ahmedabad, India, CD-ROM.
• 16: Ravikanth Malladi , James A. Sethian , Baba C. Vemuri, Shape Modeling with Front Propagation: A Level Set Approach, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.17 n.2, p.158-175, February 1995 [doi>10.1109/34.368173]
• 17: D. Metaxas , D. Terzopoulos, Shape and Nonrigid Motion Estimation Through Physics-Based Synthesis, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.15 n.6, p.580-591, June 1993 [doi>10.1109/34.216727]
• 18: Wladimir Peckar , Christoph Schnörr , Karl Rohr , H. Siegfried Stiehl, Parameter-Free Elastic Deformation Approach for 2D and 3D Registration Using Prescribed Displacements, Journal of Mathematical Imaging and Vision, v.10 n.2, p.143-162, March 1999 [doi>10.1023/A:1008375006703]
• 19: Natan Peterfreund, Robust Tracking of Position and Velocity With Kalman Snakes, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.21 n.6, p.564-569, June 1999 [doi>10.1109/34.771328]
• 20: Schutte K. 1995. An Edge labeling Approach to Concave Polygon Clipping, ACM Transactions on Graphics, 1:1--10.
• 21: Stan Sclaroff , John Isidoro, Active blobs: region-based, deformable appearance models, Computer Vision and Image Understanding, v.89 n.2-3, p.197-225, February 2003 [doi>10.1016/S1077-3142(03)00003-1]
• 22: Dinggang Shen , Christos Davatzikos, An Adaptive-Focus Deformable Model Using Statistical and Geometric Information, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.22 n.8, p.906-913, August 2000 [doi>10.1109/34.868689]
• 23: Lawrence H. Staib , James S. Duncan, Boundary Finding with Parametrically Deformable Models, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.14 n.11, p.1061-1075, November 1992 [doi>10.1109/34.166621]
• 24: Anthony Stefanidis , Kristin Eickhorst , Peggy Agouris , Panos Partsinevelos, Modeling and comparing change using spatiotemporal helixes, Proceedings of the 11th ACM international symposium on Advances in geographic information systems, p.86-93, November 07-08, 2003, New Orleans, Louisiana, USA [doi>10.1145/956676.956688]
• 25: Demetri Terzopoulos , Richard Szeliski, Tracking with Kalman snakes, Active vision, MIT Press, Cambridge, MA, 1993
• 26: Yu Zhong , Anil K. Jain , M.-P. Dubuisson-Jolly, Object Tracking Using Deformable Templates, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.22 n.5, p.544-549, May 2000 [doi>10.1109/34.857008]

INDEX TERMS

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

General Terms:
Algorithms, Design, Experimentation, Performance

Keywords:
active contour models, change detection, geospatial database updates