Semiautomated system for three-dimensional modeling of buildings from aerial video

In this paper, a semiautomated system for modeling 3D objects, especially buildings from aerial video, over a semi-urban scene is presented. First, the video frames are preprocessed to minimize the rotational effects of camera motion. The 3D translational coordinates of the sensor are used to stitch the video frames into nadir and stereo mosaics. The features extracted from the stereo mosaics, like elevation, edges and corners, visual entropy, and color information, are employed in a Bayesian framework to identify the 3D objects in the scene, such as buildings and trees. The initial 3D building models are further optimized by projecting them onto individual video frames. A novel method for setting the input parameters of vision algorithms required for feature extraction, using the data-driven probabilistic inference in Bayesian Networks, has been designed. This method automates the 3D object identification process and precludes the need for manual intervention. Improvements that can be used to increase the accuracy of 3D models when Lidar data is fused with aerial video during the object identification process are also discussed.

[1]  Stuart J. Russell,et al.  Adaptive Probabilistic Networks with Hidden Variables , 1997, Machine Learning.

[2]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[3]  David Heckerman,et al.  A Tutorial on Learning with Bayesian Networks , 1999, Innovations in Bayesian Networks.

[4]  Allen R. Hanson,et al.  Decision Making and Uncertainty Management in a 3D Reconstruction System , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Prudhvi Gurram,et al.  Extraction of digital elevation map from parallel-perspective stereo mosaics , 2008, Electronic Imaging.

[6]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Andrew Zisserman,et al.  Automatic reconstruction of piecewise planar models from multiple views , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[8]  Jie Cheng,et al.  An Algorithm for Bayesian Belief Network Construction from Data , 2004 .

[9]  Armin B. Cremers,et al.  Extracting Buildings from Aerial Images Using Hierarchical Aggregation in 2D and 3D , 1998, Comput. Vis. Image Underst..

[10]  Harry N. Gross,et al.  An Advanced Synthetic Image Generation Model and its Application to Multi/Hyperspectral Algorithm Development , 1999 .

[11]  Allen R. Hanson,et al.  Ascender II, a Visual Framework for 3D Reconstruction , 1999, ICVS.

[12]  Eli Saber,et al.  Automatic color image segmentation by dynamic region growth and multimodal merging of color and texture information , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[13]  Prudhvi Gurram,et al.  A Segment-Based Mesh Design for Building Parallel-Perspective Stereo Mosaics , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[14]  C. Brenner.  Building reconstruction from images and laser scanning , 2005 .

[15]  Prudhvi K. Gurram,et al.  Automated 3D object modeling from aerial video imagery , 2009 .

[16]  George Vosselman,et al.  Reconstruction of 3D building models from aerial images and maps , 2003 .

[17]  Stephen R. Lach,et al.  Semi-Automated DIRSIG scene modeling from 3D lidar and passive imagery , 2008 .

[18]  A. Murat Tekalp,et al.  Fusion of color and edge information for improved segmentation and edge linking , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[19]  Eli Saber,et al.  Unsupervised color image segmentation using a dynamic color gradient thresholding algorithm , 2008, Electronic Imaging.

[20]  Ramakant Nevatia,et al.  Expandable Bayesian Networks for 3D Object Description from Multiple Views and Multiple Mode Inputs , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Allen R. Hanson,et al.  Generalized parallel-perspective stereo mosaics from airborne video , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  John P. Kerekes,et al.  3D Scene Reconstruction through a Fusion of Passive Video and Lidar Imagery , 2007, 36th Applied Imagery Pattern Recognition Workshop (aipr 2007).