Tracking of Moving Objects in Video Sequences Based on Elliptical Subtractive Clustering
Zhi Hai Sun, Bin Hu, Ying Meng, Wenhui Zhou · Applied Mechanics and Materials · 2015
Visual object detection and tracking have become an important step between computer vision and video analysis. Recent methods almost use mean shift for tracking problems, which are difficult to overcome the shortcoming with the initial object model. Initial object model is almost initialized manually by user, which is not smart enough and inconvenient. This paper considers the integration strategy for elliptical subtractive clustering and mean shift, and proposes a novel tracking method based on elliptical subtractive clustering.