Detection of cabinet in equipment floor based on AlexNet and SSD model

Abstract

With the rapid development of technologies such as computer technology and sensors technology, intelligent inspection robots gradually replace manual inspections in industrial inspection positions. In order to improve the accuracy and stability of the cabinet detection of inspection robot, this study proposes a new model which combines the adjusted AlexNet model and adjusted single shot multi‐box detector (SSD) model to detect cabinet and its effective information at railway station equipment floor. The first is to determine whether there is a cabinet in view based on the AlexNet. If a cabinet exists, then locate the effective information position of the objects with the SSD. The experimental results reveal that the new model can detect the cabinet, two digital metres and indicator lights more efficiently.