Minimal user interaction in coronary artery centerline extraction is important for computer aided system in Coronary Artery Disease detection. However, manual seeding leads to error propagation most of the time. In this paper, we propose a neighbourhood search feedback mechanism in centerline tracking to overcome this problem. Two contributions from this paper are: (1) Seed Point Optimization w...

Mean-Shift tracking is a popular algorithm for object tracking since it is easy to implement and it is fast and robust. In this paper, we address the problem of scale adaptation of the Hellinger distance based Mean-Shift tracker. We start from a theoretical derivation of scale estimation in the Mean-Shift framework. To make the scale estimation robust and suitable for tracking, we introduce reg...

Human faces are commonly found in video streams and provide useful information for video content analysis. This paper presents a robust face tracking system to extract multiple face sequences from MPEG video without human intervention. Specifically, a view-based DCT-domain face detection algorithm is first applied periodically to capture mostly frontal and slight slanting faces of variable size...

In this work, we consider the problem of tracking players, during a soccer game, through the use of multiple cameras. The main goal here consists in finding the position of the players on the pitch at each instance of time. The tracking is performed through a graph representation in which the nodes correspond to the blobs obtained by image segmentation and the edges, weighted using the blobs in...

In this paper, an adaptive step size auto focus search algorithm and a reduced zoom tracking algorithm are proposed. Many different auto focus search algorithms exist, such as global search, binary search, Fibonacci search, and so on. Global search can ensure the global peak is found correctly, but the search time is too long. The search time of binary or Fibonacci search is shortened, but the ...

A generic bi-directional scheme is proposed that robustifies the estimation of the maximum-a-posteriori (MAP) sequence of states of a visual object. It enables creative, non-technical users to obtain the path of interesting objects in offline available video material, which can then be used to create interactive movies. To robustify against tracker failure the proposed scheme merges the filteri...

We describe a method that can detect specific human behaviors even in crowded surveillance video scenes. Our developed system recognizes specific behaviors based on the trajectories created by detecting and tracking people in a video. It detects people using an HOG descriptor and SVM classifier, and it tracks the regions by calculating the two-dimensional color histograms. Our system identifies...