Hierarchical DSfM for structural condition assessment
-
Developed a novel method for image-based 3D reconstruction of large infrastructure systems capable of resolving 0.1 mm details, an order of magnitude improvement over existing methods
-
Through designing a multi-scale imaging network and hierarchical image-matching technique, the developed method is capable of registering images at a much higher rate in comparison with conventional methods
-
By using a memory efficient global pixel-wise image matching method, it is possible to generate highly dense 3D point clouds on a single computer
-
This method performs robustly in generating accurate and complete 3D models of large-scale structural models with the ability to control the local point density at critical locations




Related Publications
-
Khaloo, A. and Lattanzi, D. (2016) "Hierarchical Dense Structure-from-Motion Reconstructions for Infrastructure Condition Assessment," ASCE Journal of Computing in Civil Engineering, 31(1), 04016047.
-
Khaloo, A., and Lattanzi, D. (2015) "A Hierarchical Computer Vision Approach to Infrastructure Inspection," ASCE International Workshop on Computing in Civil Engineering (IWCCE). pp. 540-547, Austin, TX, June 2015. (Honorary Certificates of Appreciation & Selected Student Demo)
-
Khaloo, A., and Lattanzi, D. (2015) "Extracting Structural Models through Computer Vision," ASCE Structures Congress . pp. 538-548, Portland, OR, April 2015. (travel award)


GPU Grant Program