Efficient GPU Photo Hull Reconstruction for Surveillance

Title data

Ober-Gecks, Antje ; Zwicker, Marius ; Henrich, Dominik:
Efficient GPU Photo Hull Reconstruction for Surveillance.
In: Proceedings of the International Conference on Distributed Smart Cameras. - Venezia Mestre, Italy , 2014 . - 21
DOI: https://doi.org/10.1145/2659021.2659064

Project information

Abstract in another language

We present a GPU-based implementation of the photo hull using the generalized voxel coloring with item buffer (GVC-IB) approach with the aim of reconstructing humans online in surveillance scenarios. To allow for a fast computation on the GPU, an incremental calculated standard deviation is used in the likelihood ratio test that is applied as color consistency criterion. Concerning the necessary fast and efficient computation of complete voxel-pixel projections, a number of volume rendering methods is examined, such as texture mapping and raycasting. The termination of the voxel carving during photo hull computation is realized by integrating the anytime concept. The input of the voxel carving is a visual hull reconstruction. An algorithm that provides an exact and conservative occlusion handling is redesigned for a fast computation on the GPU.