Combining Deep Learning and JSEG Cuda Segmentation Algorithm for Electrical Components Recognition

Abstract

A segmentation and recognition system for thermographic images of electric power distribution network using Artificial Intelligence is proposed in this article. The infrared thermography is usually used to proceed inspections in electrical power distribution lines, assisted by a human operator, which is usually responsible for operating all the equipment, selecting the hottest spots in the image (corresponding to the places needing maintenance), making reports and calling the technical team, which will do the repairs. The proposed automatic diagnosis system aims to replace the manual inspection operation using image processing algorithms. A method of segmentation for thermal images known as JSEG is implemented and tested and a Convolution Neural Network is responsible to recognize the segmented elements. The results show the feasibility of the algorithm, and the monitoring system.