HYBRID METHOD FOR MOVING OBJECT EXPLORATION IN VIDEO SURVEILLANCE
Mohamed Uvaze Ahamed
mohamed.uvaze@cihanuniversity.edu.iq
Abstract- Moving objects in a video could be explored using hybrid methodologies as one of the enticing fields of vision in computers. It is extensively applied in video surveillance and target identification systems. Extracting reliable information accurately is a rigorous task in a challenging environment. This paper investigates the problem of detecting an object in dynamic scenes. We suggest two method 1) feature extraction using FBF 2) Image matching using ISURF. The ISURF (Improved Speeded up Robust Feature detection) is the improvised method of the original SURF algorithm. In this, the matching duration is reduced by limiting the total number of features to be compared. The FBF (Fast Bilateral Filtering) algorithm is suggested for feature extraction and denoising the captured keyframes. Thus this paper proposes a hybrid method for moving object exploration in a dynamic scene with reduced time.
Keywords- Surveillance, Feature Extraction, Feature Detection, SURF Algorithm, ISURF Algorithm, Object Exploration
Date: 26/02/2020
Place: Department of Computer Science