Abstract
Sea mines are larger and much more expensive than land mines, but they may be well disseminated inside troubled waters. Thus, it is primordial to propose robust image recognition techniques which are adequate for the context of troubled waters. A recognition technique based on optical correlation has been developed for this specific purpose. A set of images of an object (assumed to represent a sea mine) was produced with a rotating camera around it. Then, these images were processed with an algorithm based on the correlation method to recognize the object. To improve the correlator performances we have proposed a correction that consists in emphasizing the contour of the object. For that purpose, the phase contrast method was used. To test the performance of this recognition technique several scenarios were considered, e.g. objects in air, mist, and placed in clear and troubled water. The latter case simulates the underwater mine situation.
© 2015 Optical Society of America
PDF ArticleMore Like This
M. Dubreuil, A. Alfalou, and C. Brosseau
FW3A.30 Frontiers in Optics (FiO) 2012
Dhirendra Kumar and Naveen K. Nishchal
DTh1A.6 Digital Holography and Three-Dimensional Imaging (DH) 2015
Dhirendra Kumar and Naveen K. Nishchal
T3A.61 International Conference on Fibre Optics and Photonics (Photonics) 2014