RetinaNet with Harmony Search Algorithm for Dynamic and Static Object Detection and Classification Model

Abstract

Object detection is becoming a challenging problem in several computer vision related applications. The recently developed deep learning (DL) models enable to design of effective object detection models with enhanced outcomes. But it is difficult to attain many characteristics from the objects identified in real time. To resolve this issue, this study introduces an optimal RetinaNet with harmony search algorithm for dynamic and static object detection (RNHSA-DSOD) model. The proposed RNHSA-DSOD technique aims to identify the dynamic as well as static objects that exist in the input frame. Besides, the RNHSA-DSOD technique derives a RetinaNet based object detection model to recognize multiple objects. Next, harmony search algorithm (HSA) with multilayer perceptron (MLP) is applied for the classification of detected objects into multiple classes. The design of HSA for MLP model shows the novelty of the work. In order to demonstrate the enhanced outcomes of the RNHSA-DSOD technique, a series of simulations were carried out and the results indicated the enhanced outcomes of the RNHSA-DSOD technique over its recent techniques.