Impact of Segmentation Techniques for Conditıon Monitorıng of Electrical Equipments from Thermal Images

Abstract

Infrared Thermography is used in condition monitoring of electrical equipment. Thermal images or thermographs are acquired using an IR camera and the hotspot/coldspot temperature is calculated. Image segmentation is the most important step in isolating the hotspot/coldspot. A segmentation technique must retain the full size and shape of the anomaly while completely removing the unwanted regions. Though various segmentation techniques are cited in the literature, these segmentation techniques could not detect anomalies of irregular shapes. In this paper, an Improved Active Contour Modeling technique is proposed to isolate the Region of Interest. The performance of the proposed technique is compared with that of the conventional segmentation techniques. IACM removes the undesirable regions and is successful in detecting the Region of Interest of any shape and size.