A hybrid gray wolf and genetic whale optimization algorithm for efficient moving object analysis

摘要

Object detection in realistic situations needs various essential applications. The foremost applications of machine vision like vision based monitoring system, object tracking etc. require background subtraction (BS) complied with identification of motion objects. Segregating forefront from background is a challenging task in videos discovered through motion cam since either forefront or background relevant information varies in each successive frame of the video series; hence a pseudo-motion is sensitive with background. Modified Kernel fuzzy c-means technique still bears a few drawbacks, for example, decreased convergence rate, acquiring stuck in the local minima and also in risk to instatement level of sensitivity. To overcome the above problems, here we recommend a technique for information clustering utilizing the OWC (Optimal Weighted Centroid) procedure that decides the optimum centroid for playing out the clustering procedure. To overcome the issues, here we recommend a technique Optimal Background separation using Optimal Weighted Centroid (OWC) - Modified Kernel Fuzzy C Means Algorithm (MKFCM) for information clustering utilizing the OWC (Optimal Weighted Centroid) procedure that decides the optimum centroid for playing out the clustering procedure. The OWC procedure makes use of the procedural activities of the Whale Optimization algorithm (WOA) with the fusion of the Grey Wolf Optimization (GWO). The prescribed new procedure is dynamic clustering technique for splitting up of moving object. Moving object tracking is accomplished through the blob detection which comes under the tracking stage. The examination stage has attribute extraction and also classification. Appearance-based as well as high quality based attributes are drawn out from the refined frames which are provided for classification. Since classification we are making use of J48 (C4.5) i.e., decision tree based classifier. The efficiency of the recommended strategy is examined with preceding strategies k-NN as well as MLP in regard to accuracy, f-measure, ROC as well as recall.