Optimizing Placements of 360-degree Panoramic Cameras in Indoor Environments by Integer Programming

TL;DR

This paper presents an efficient integer programming method to optimally place 360-degree cameras in indoor environments, improving coverage for building documentation in architecture and construction.

Contribution

It introduces a simple, globally optimal integer programming formulation for camera placement, outperforming human solutions in coverage quality.

Findings

Computed solutions surpass human decisions in coverage quality

The approach is computationally efficient and globally optimal

Effective for indoor environment documentation in AEC industries

Abstract

We propose a computational approach to find a minimal set of 360-degree camera placements that together sufficiently cover an indoor environment for the building documentation problem in the architecture, engineering, and construction (AEC) industries. Our approach, based on a simple integer programming (IP) problem formulation, solves very efficiently and globally optimally. We conducted a study of using panoramas to capture the appearances of a real-world indoor environment, in which we found that our computed solutions are better than human solutions decided by both non-professional and professional users.