Using Mask R CNN to Isolate PV Panels from Background Object in Images

Abstract

Identifying foreground objects in an image is one of the most common operations used in image processing. In this work, Mask R CNN algorithm is used to identify solar photovoltaic PV panels in aerial images and create a mask that can be used to remove the background from the images. This allows processing the PV panels separately. Using ML to solve this problem can generate more accurate results in comparison to more traditional image processing techniques like using edge detection or Gaussian filtering especially in images where the view might not be easily separable from the objects of interest. The trained model was found to be successful in detecting the PV panels and selecting the pixels that belong to them while ignoring the background pixels. This kind of work can be useful in collecting information about PV installation present in aerial or satellite imagery, or in analyzing the health and integrity of PV modules in large scale installations e.g., in a solar power plant. The results show that this method is effective with a high potential for improved results if the model is trained using larger and more diverse datasets. Muhammet Sait | Atilla Erguzen | Erdal Erdal "Using Mask R-CNN to Isolate PV Panels from Background Object in Images" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-5 | Issue-1 , December 2020, URL: https://www.ijtsrd.com/papers/ijtsrd38173.pdf Paper URL : https://www.ijtsrd.com/engineering/computer-engineering/38173/using-mask-rcnn-to-isolate-pv-panels-from-background-object-in-images/muhammet-sait

Authors and Affiliations

Muhammet Sait | Atilla Erguzen | Erdal Erdal

Keywords

Related Articles

Health Care Monitor with Emergency Support

The world of medical science is an emerging area that has accelerated with new technologies and this is the time when the vision of œThe internet of things has turned into reality. People demand more care at reduced cli...

Chatbot for Railway using Diloug Flow

Chatbot is a program or a virtual person who can speak effectively to the human beings using Artificial intelligent and using interactive skills. Today the main challenge of the chatbot is to which will look like human b...

Adversities that Disrupt Positive Development among Emerging Adult Students in Universities in Cameroon A conceptual review

Higher education is universally applauded as a means to empower young people with skills, knowledge, experiences and significant relationships which can enable them to play their roles successfully as leaders of tomorrow...

Experimental Analysis on Vulnerability of RCC Members Due to Floods

This projects gives the remedial measures for the buildings that is severely affected by floods. The buildings in the flood prone areas of Chennai city is mapped using ArcGIS. Mapping of these areas helps to make immedia...

Augmented Reality Map

Augmented Reality AR is the technology that overlaps virtual objects onto real world objects. It has three main features the combination of the real world and the virtual world, real time interaction, and 3D registration...

Download PDF file
  • EP ID EP692362
  • DOI -
  • Views 88
  • Downloads 0

How To Cite

Muhammet Sait, Atilla Erguzen (2020). Using Mask R CNN to Isolate PV Panels from Background Object in Images. International Journal of Trend in Scientific Research and Development, 5(1), -. https://europub.co.uk/articles/-A-692362