This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Performance Evaluation and Analysis of Monocular Building Extraction From Aerial Imagery
April 1999 (vol. 21 no. 4)
pp. 311-326

Abstract—Research in monocular building extraction from aerial imagery has neglected performance evaluation in three areas: unbiased metrics for quantifying detection and delineation performance, an evaluation methodology for applying these metrics to a representative body of test imagery, and an approach for understanding the impact of image and scene content on building extraction algorithms. This paper addresses these areas with an end-to-end performance evaluation of four existing monocular building extraction systems, using image space and object space-based metrics on 83 test images of 18 sites. This analysis is supplemented by an examination of the effects of image obliquity and object complexity on system performance, as well as a case study on the effects of edge fragmentation. This widely applicable performance evaluation approach highlights the consequences of various traditional assumptions about camera geometry, image content, and scene structure, and demonstrates the utility of rigorous photogrammetric object space modeling and primitive-based representations for building extraction.

[1] C. Braun, "Interpretation and Correction of Single Line Drawings for the Reconstruction of Objects in Space," Proc. ISPRS Commission III Symp. Spatial Information from Digital Photogrammetry and Computer Vision, H. Ebner, C. Heipke, and K. Eder, eds., vol. 30, part 3/1, pp. 85-90,Munich, Germany, 1994.
[2] M. Bro-Nielsen, "Building Detection in Aerial Images," Master's thesis, Inst. of Mathematical Statistics and Operations Research, Technical Univ. of Denmark, Aug. 1992.
[3] R.T. Collins, A.R. Hanson, E.M. Riseman, C. Jaynes, F. Stolle, X. Wang, and Y.-Q. Cheng, "UMass Progress in 3D Building Model Acquisition," Proc. ARPA Image Understanding Workshop, vol. I, pp. 305-315,Palm Springs, Calif., Feb. 1996.
[4] R.W. Conners, M.M. Trivedi, and C.A. Harlow, "Segmentation of a High-Resolution Urban Scene Using Texture Operators," Computer Vision, Graphics, and Image Processing, vol. 25, pp. 273-310, 1984.
[5] A. Fischer, T.H. Kolbe, and F. Lang, "Integration of 2D and 3D Reasoning for Building Reconstruction Using a Generic Hierarchical Model," Proc. Workshop Semantic Modeling for the Acquisition of Topographic Information, W. Forstner, ed., Bonn, Germany, 1997..
[6] P. Fua, "Cartographic Applications of Model-Based Optimization," Proc. ARPA Image Understanding Workshop, vol. I, pp. 409-419,Palm Springs, Calif., Feb. 1996.
[7] P. Fua and A.J. Hanson, "An Optimization Framework for Feature Extraction," Machine Vision and Applications, vol. 4, no. 2, pp. 59-87, 1991.
[8] N. Haala and K.-H. Anders, "Acquisition of 3D Urban Models by Analysis of Aerial Images, Digital Surface Models and Existing 2D Building Information," Proc. SPIE: Integrating Photogrammetric Techniques with Scene Analysis and Machine Vision III, D.M. McKeown, J.C. McGlone, and O. Jamet, eds., vol. 3,072, pp. 212-222, Apr. 1997.
[9] N. Haala and C. Brenner, "Interpretation of Urban Surface Models Using 2D Building Information," Proc. Automatic Extraction of Man-Made Objects from Aerial and Space Images (II), A. Gruen, E.P. Baltsavias, and O. Henricsson, eds., pp. 213-222,Monte Verita, Ascona, Switzerland, May 1997..
[10] A.J. Hanson, A.P. Pentland, and L.H. Quam, "Design of a Prototype Interactive Cartographic Display and Analysis Environment," Proc. DARPA Image Understanding Workshop, pp. 475-482, Feb. 1987.
[11] D. Harwood, S. Chang, and L. Davis, "Interpreting Aerial Photographs by Segmentation and Search," Proc. DARPA Image Understanding Workshop, pp. 507-520, Feb. 1987.
[12] O. Henricsson, "Analysis of Image Structures using Color Attributes and Similarity Relations," Inst. of Geodesy and Photogrammetry, Swiss Federal Inst. of Technology (ETH), Zurich, Switzerland, May 1996.
[13] M. Herman and T. Kanade, “Incremental Reconstruction of 3D Scenes from Multiple, Complex Images,” Artificial Intelligence, vol. 30, no. 3, pp. 289-341, Dec. 1986.
[14] S. Heuel and R. Nevatia, "Including Interaction in an Automated Modeling System," Proc. ARPA Image Understanding Workshop, vol. I, pp. 429-434,Palm Springs, Calif., Feb. 1996.
[15] Y. Hsieh, "Design and Evaluation of a Semi-Automated Site Modeling System," Proc. ARPA Image Understanding Workshop, vol. I, pp. 435-459,Palm Springs, Calif., Feb. 1996.
[16] Y. Hsieh, "Sitecity: A Semi-Automated Site Modeling System," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 499-506, June 1996.
[17] A. Huertas and R. Nevatia, “Detecting Buildings in Aerial Images,” Computer Vision, Graphics and Image Processing, vol. 41, no. 2, pp. 131-152, Feb. 1988.
[18] R. Irving and D. McKeown, “Methods for Exploiting the Relationship between Buildings and Their Shadows in Aerial Imagery,” IEEE Trans. Systems, Man, and Cybernetics, vol. 19, no. 6, pp. 1564-1575, Nov./Dec. 1989.
[19] C. Jaynes, F. Stolle, and R. Collins, "Task Driven Perceptual Organization for Extraction of Rooftop Polygons," Proc. ARPA Image Understanding Workshop, vol. I, pp. 359-365, Nov. 1994.
[20] C.O. Jaynes, A. Hanson, and E. Riseman, "Building Reconstruction from Optical and Range Images," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 380-386, June 1997.
[21] M. Kass, A. Witkin, and D. Terzopoulos, "Snakes: Active Contour Models," Int'l J. Computer Vision, vol. 1, no. 4, pp. 321-331, 1987.
[22] C. Lin, A. Huertas, and R. Nevatia, "Detection of Buildings Using Perceptual Grouping and Shadows," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 62-69, June 1994.
[23] C. Lin and R. Nevatia, "Buildings Detection and Description from Monocular Aerial Images," Proc. ARPA Image Understanding Workshop, pp. 461-468, Feb. 1996.
[24] Y. Liow and T. Pavlidis, Use of Shadows for Extracting Buildings in Aerial Images Computer Vision, Graphics, and Image Processing, vol. 49, no. 2, pp. 242-277, Feb. 1990.
[25] J.C. McGlone, "Bundle Adjustment with Object Space Geometric Constraints for Site Modeling," Proc. SPIE Conf. Integrating Photogrammetric Techniques with Scene Analysis and Machine Vision II, D.M. McKeown and I.J. Dowman, eds., vol. 2,486, pp. 25-36, Apr.19-21 1995.
[26] J.C. McGlone and J. Shufelt, “Projective and Object Space Geometry for Monocular Building Extraction,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 54-61, June 1994.
[27] D.M. McKeown, "Toward Automatic Cartographic Feature Extraction," Mapping and Spatial Modelling for Navigation, L.F. Pau, ed., NATO ASI series, vol. F65, pp. 149-180, 1990.
[28] D.M. McKeown and J.L. Denlinger, "Map-Guided Feature Extraction from Aerial Imagery," Proc. IEEE Workshop Computer Vision: Representation and Control, pp. 205-213,Annapolis, Md., 1984.
[29] R. Mohan and R. Nevatia, “Using Perceptual Organization to Extract 3-D Structures,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 11, no. 11, pp. 1,121-1,139, Nov. 1989.
[30] M. Nagao and T. Matsuyama, A Structural Analysis of Complex Aerial Photographs.New York: Plenum, 1980.
[31] R. Nevatia and K.R. Babu, "Linear Feature Extraction and Description," Computer Graphics and Image Processing, vol. 13, pp. 257-269, July 1980.
[32] B. Nicolin and R. Gabler, "A Knowledge-Based System for the Analysis of Aerial Images," IEEE Trans. Geoscience and Remote Sensing, vol. 25, no. 3, pp. 317-329, May 1987.
[33] M. Roux and H. Maitre, "Three-Dimensional Description of Dense Urban Areas Using Maps and Aerial Images," Proc. Automatic Extraction of Man-Made Objects from Aerial and Space Images (II), A. Gruen, E.P. Baltsavias, and O. Henricsson, eds., pp. 311-322,Monte Verita, Ascona, Switzerland, May 1997.
[34] M. Roux and D. McKeown, “Feature Matching for Building Extraction from Multiple Views,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 46-53, June 1994.
[35] J.A. Shufelt, "Exploiting Photogrammetric Methods for Building Extraction in Aerial Images," Int'l Archives of Photogrammetry and Remote Sensing, vol. XXXI, B6/S, pp. 74-79, July 1996.
[36] J.A. Shufelt, "Performance Evaluation and Analysis of Vanishing Point Detection Techniques," Proc. ARPA Image Understanding Workshop, pp. 1,113-1,132, Feb. 1996.
[37] J.A. Shufelt, “Projective Geometry and Photometry for Object Detection and Delineation,” PhD thesis CMU-CS-96-164, Carnegie Mellon Univ., July 1996.
[38] J.A. Shufelt, "Geometric Constraints on Hypothesis Generation for Monocular Building Extraction," Proc. SPIE: Integrating Photogrammetric Techniques with Scene Analysis and Machine Vision III, D.M. McKeown, J.C. McGlone, and O. Jamet, eds., vol. 3,072, pp. 231-250, Apr. 1997.
[39] J. Shufelt and D. McKeown, “Fusion of Monocular Cues to Detect Man-Made Structures in Aerial Imagery,” Computer Vision, Graphics, and Image Processing, vol. 57, no. 3, pp. 307-330, May 1993.
[40] Manual of Photogrammetry, C.C. Slama, ed., fourth ed. Am. Soc. Photogrammetry, 1980.
[41] M. Tavakoli and A. Rosenfeld, "Building and Road Extraction from Aerial Photographs," IEEE Trans. Systems, Man, and Cybernetics, vol. 12, no. 1, pp. 84-91, Jan./Feb. 1982.
[42] V. Venkateswar and R. Chellappa, "A Framework for Interpretation of Aerial Images," Proc. 10th Int'l Conf. Pattern Recognition, pp. 204-206, 1990.
[43] A. Zlotnick, "Locating Corners in Noisy Curves by Delineating Imperfect Sequences," Technical Report CMU-CS-88-199, Carnegie Mellon Univ., Dec. 1988.

Index Terms:
Monocular building extraction, performance evaluation, object detection, feature delineation, photogrammetry, computer vision, metrics.
Citation:
Jefferey A. Shufelt, "Performance Evaluation and Analysis of Monocular Building Extraction From Aerial Imagery," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 21, no. 4, pp. 311-326, April 1999, doi:10.1109/34.761262
Usage of this product signifies your acceptance of the Terms of Use.