Tracking and data association
Mean Shift: A Robust Approach Toward Feature Space Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Making Good Features Track Better
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Convergence results for the particle PHD filter
IEEE Transactions on Signal Processing
A tutorial on particle filters for online nonlinear/non-GaussianBayesian tracking
IEEE Transactions on Signal Processing
Hi-index | 0.00 |
In this paper we present a system for the automatic detection and tracking of metallic objects concealed on moving people in sequences of millimetre-wave (MMW) images. The millimetre-wave sensor employed has been demonstrated for use in covert detection because of its ability to see through clothing, plastics and fabrics.The system employs two distinct stages: detection and tracking. In this paper a single detector, for metallic objects, is presented which utilises a statistical model also developed in this paper. The second stage tracks the target locations of the objects using a Probability Hypothesis Density filter. The advantage of this filter is that it has the ability to track a variable number of targets, estimating both the number of targets and their locations. This avoids the need for data association techniques as the identities of the individual targets are not required. Results are presented for both simulations and real millimetre-wave image test sequences demonstrating the benefits of our system for the automatic detection and tracking of metallic objects.