Power Line Detection for Aerial Images Using Object-Based Markov Random Field With Discrete Multineighborhood System

Robust power line detection from aerial images is an essential step for intelligent unmanned aerial vehicle (UAV) inspection. However, compared to regular object detection tasks, the generalization ability and accuracy of current methods are seriously insufficient due to the variability of power line scenes and the low proportion of power lines in the image. In this letter, we propose an object-based Markov random field with a discrete multineighborhood system (OMRF-DMNS) model, which can provide a solution for tackling power line detection challenges. First, the proposed method constructs a discrete multineighborhood system (DMNS) for the noncontact nodes. This not only greatly improves the antinoise ability of the model, but also lays the foundation for the transfer of context information among nodes under different receptive fields. Second, a multilevel logical model with multineighborhood joint reasoning (MLL-MNJR) is defined on the DMNS, which makes full use of the line features and location information to achieve semantic inference of nodes. Therefore, the OMRF-DMNS model can fully mine the multidimensional feature associations and context information among nodes, enabling it to effectively distinguish between power line segments and interference noises. Experimental results demonstrate that the proposed method significantly outperforms previous methods in different power line scenes.