PV power plant inspection by image mosaicing techniques for IR real-time images

Mohammadreza Aghaei, Sonia Leva, Francesco Grimaccia

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

11 Citations (Scopus)


Operation and maintenance play a crucial role for the performance of PV power plants. In this experimental paper a novel approach is proposed included planning and mapping of PV power plants by digital image processing techniques. For this purpose, aerial thermovisual photography is carried out in a PV plant by a light Unmanned Aerial System (UAS) with a thermograph camera onboard. The main objective of current paper is to develop a digital image processing algorithm in order to provide an Image Mosaicing (IM) for richer description of the plant by merging many infrared (IR) images. The algorithm is able to analyze the image mosaicing (IM) in order to count total number of PV modules, defect and healthy modules in PV strings. The results have demonstrated that proposed digital image processing (DIP) algorithm is very efficient and reliable for analysis of infrared (IR) images to provide a depth perspective of PV power plants during procedure inspection.

Original languageEnglish
Title of host publication2017 IEEE 44th Photovoltaic Specialist Conference, PVSC 2017
PublisherInstitute of Electrical and Electronics Engineers
Number of pages6
ISBN (Electronic)9781509056057
Publication statusPublished - 1 Jan 2017
Externally publishedYes
Event44th IEEE Photovoltaic Specialist Conference, PVSC 2017 - Washington, United States
Duration: 25 Jun 201730 Jun 2017
Conference number: 44


Conference44th IEEE Photovoltaic Specialist Conference, PVSC 2017
Abbreviated titlePVSC 2017
Country/TerritoryUnited States


  • Digital image processing (DIP)
  • Image mosaicing (IM)
  • Infrared (IR) image
  • Operation and maintenance
  • PV module
  • PV power plant
  • Unmanned aerial system (UAS)


Dive into the research topics of 'PV power plant inspection by image mosaicing techniques for IR real-time images'. Together they form a unique fingerprint.

Cite this