Detailed Aerial Mapping of Photovoltaic Power Plants Through Semantically Significant Keypoints

2025-10-06

AI Summary

This paper addresses the challenge of component-level fine-grained 3D modeling of photovoltaic (PV) power plants from aerial imagery. We propose a semantic keypoint-based structured matching method that integrates multi-view detection outputs via visual segmentation, topology-aware structural inference, and cross-image keypoint matching to achieve hierarchical semantic reconstruction—progressing from PV modules to mounting structures, rows, and columns—while embedding georeferenced 3D localization. Our key innovation lies in using semantic keypoints as structural anchors to enable high-precision module-level alignment and model compression while preserving array topology integrity. Experiments on two real-world PV plants demonstrate that the resulting compact semantic 3D models achieve centimeter-level geospatial accuracy and strong interpretability, significantly enhancing the practicality and robustness of operation-and-maintenance-oriented automated modeling.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Structured Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Bridging structured and unstructured data

Abstract

An accurate and up-to-date model of a photovoltaic (PV) power plant is essential for its optimal operation and maintenance. However, such a model may not be easily available. This work introduces a novel approach for PV power plant mapping based on aerial overview images. It enables the automation of the mapping process while removing the reliance on third-party data. The presented mapping method takes advantage of the structural layout of the power plants to achieve detailed modeling down to the level of individual PV modules. The approach relies on visual segmentation of PV modules in overview images and the inference of structural information in each image, assigning modules to individual benches, rows, and columns. We identify visual keypoints related to the layout and use these to merge detections from multiple images while maintaining their structural integrity. The presented method was experimentally verified and evaluated on two different power plants. The final fusion of 3D positions and semantic structures results in a compact georeferenced model suitable for power plant maintenance.

Problem

• Automating aerial mapping of photovoltaic plants using semantic keypoints
• Creating detailed georeferenced models down to individual PV modules
• Eliminating reliance on third-party data for power plant maintenance

Innovation

• Aerial images enable automated photovoltaic plant mapping
• Visual segmentation identifies individual modules and structures
• Keypoint-based fusion creates georeferenced 3D maintenance models