A New Clustering-based View Planning Method for Building Inspection with Drone

TL;DR

This paper introduces a novel clustering-based approach for drone view planning in building inspection, combining spectral clustering, potential fields, and hyper-heuristics to optimize coverage with fewer viewpoints.

Contribution

It presents a new two-step method integrating spectral clustering, local potential fields, and hyper-heuristics for near-optimal drone view planning in building inspection.

Findings

Achieves higher coverage with fewer viewpoints

Outperforms existing methods in solution quality

Demonstrates effectiveness through experimental results

Abstract

With the rapid development of drone technology, the application of drones equipped with visual sensors for building inspection and surveillance has attracted much attention. View planning aims to find a set of near-optimal viewpoints for vision-related tasks to achieve the vision coverage goal. This paper proposes a new clustering-based two-step computational method using spectral clustering, local potential field method, and hyper-heuristic algorithm to find near-optimal views to cover the target building surface. In the first step, the proposed method generates candidate viewpoints based on spectral clustering and corrects the positions of candidate viewpoints based on our newly proposed local potential field method. In the second step, the optimization problem is converted into a Set Covering Problem (SCP), and the optimal viewpoint subset is solved using our proposed hyper-heuristic algorithm. Experimental results show that the proposed method is able to obtain better solutions with fewer viewpoints and higher coverage.