6 October 2011 Feature-based tracking algorithms for imaging infrared anti-ship missiles
Author Affiliations +
This paper investigates feature based tracking algorithms that could be used within models of imaging infrared anti-ship missile seekers in a simulation environment. The algorithms use global shape based object features such as Fourier Descriptors or Hu Moments to track a target in rendered sensor images. A template of the desired target is saved during acquisition, and matching is performed between the template and the features of unknown objects extracted from subsequent sensor images. The centroid of the object that matches the best becomes the seeker aim-point. A seeker using local features, generated by the Scale Invariant Feature Transform, to track objects will also be examined. It discriminates between objects within the sensor images by clustering SIFT features that have neighbouring regions of similar intensity. The cluster of features whose average neighbouring intensity is the closest to a desired target template is chosen as the highest priority cluster. A variable radius distance metric is used to reject features in this cluster that are too far from the seeker's previous aim-point. The new aim-point is calculated as the centroid of the cluster of remaining features. Comparisons of the three algorithms' ability to track a naval vessel deploying countermeasures will be also presented.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Greer J. Gray, Greer J. Gray, Nabil Aouf, Nabil Aouf, Mark A. Richardson, Mark A. Richardson, Brian Butters, Brian Butters, Roy Walmsley, Roy Walmsley, Edgar Nicholls, Edgar Nicholls, } "Feature-based tracking algorithms for imaging infrared anti-ship missiles", Proc. SPIE 8187, Technologies for Optical Countermeasures VIII, 81870T (6 October 2011); doi: 10.1117/12.897284; https://doi.org/10.1117/12.897284

Back to Top