cs.CVNov 3, 2026

High-fidelity training-free photovoltaic module mapping from multi-view UAV imagery

Authors: WenHao Duan, Qi Chen, Penglei Zhang, Ruizhe Deng, Zhiling Guo, Haoran Zhang, Yuntian Chen

Organizations: School of Geography and Information Engineering, China University of Geosciences (Wuhan), Wuhan 430074, China · Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, Zhejiang 315200, China · Zhejiang Key Laboratory of Industrial Intelligence and Digital Twin, Eastern Institute of Technology, Ningbo, Zhejiang 315200, China · Department of Building Environment and Energy Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong, China · 

Abstract

High-fidelity photovoltaic (PV) module mapping requires complete instance recovery and accurate delineation. Vision foundation models offer zero-shot segmentation, but converting incomplete and inconsistent predictions across views into a complete, geometrically accurate map of individual modules remains challenging. We propose the Multi-View PV Module Mapper (MV-PVMapper), a training-free framework coupling vision foundation models with unmanned aerial vehicle (UAV) photogrammetry. First, Segment Anything Model 3 (SAM 3) generates candidates from original images using text prompts. Their contours are then transferred into object space through per-module slope correction to limit distortion from surface-model noise, and verified against representative module dimensions to guide cross-view instance selection. Finally, accepted instances return to all covering images as box prompts for SAM~3, supplementing text prompts with spatial cues for iterative segmentation, verification and fusion. On five-direction surveys of three operational rooftop PV plants at approximately 1 cm nadir ground sampling distance, two feedback iterations recover 7,710 of 7,711 reference modules with no false positives at an intersection-over-union (IoU) matching threshold of 0.5. Macro-averaged area precision and recall reach 99.00 % and 98.52 %, respectively. Averaged across sites, the aggregated Jaccard index reaches 97.55 %, compared with 60.73 % and 41.24 % for orthomosaic segmentation and multi-view pixel-voting baselines, respectively; average precision at the stricter IoU threshold of 0.95 reaches 95.67 %. Ablation studies show that module-size constraints are critical for instance separation, while slope correction and feedback to all covering views improve boundary accuracy. These results are achieved without task-specific image annotation or segmentation-model weight updates.

Figures & tables

Explore similar work

CardsList
  1. A 10K drone image dataset with component-level annotations for rooftop photovoltaic inspection

    Nov 10, 2026Penglei Zhang, Wan Zhang, Ruizhe Deng +8Remote Sensing BenchmarksRemote Sensing Image Segmentation

  2. Evaluating Semantic and Spatial Guidance for Foundation Model Segmentation of Small-Scale PV in Remote Sensing Imagery

    Aug 11, 2026Roni Blushtein-Livnon, Tal Svoray, Osher Rafaeli +4Remote Sensing Image SegmentationPromptable Image Segmentation

  3. MultiSolSegment: Multi-channel segmentation of overlapping features in electroluminescence images of photovoltaic cells

    Mar 6, 2026Ojas Sanghi, Norman Jost, Benjamin G. Pierce +3Image SegmentationFault Detection