Title :
Algorithm research of infrared target recognition
Author :
Liu Wenzhe ; Wang Wensheng ; Ma Yongli
Author_Institution :
Lab. of Contemporary Opt. Meas. Technol., Changchun Univ. of Sci. & Technol., Changchun, China
Abstract :
Target recognition is an important content of computer intelligent vision surveillance system. A method of joint transform recognition is proposed for identifying and tracking the target from the infrared thermal image, which based on wavelet packet, Laplace operator and Fourier transform. The experimental result shows that the algorithm has a good performance in real-time, moreover, it can recognize the target accurately neither variety sizes nor cluttered backgrounds. And the algorithm can also solve the problem of slow speed and false recognition in infrared target detection effectively.
Keywords :
Laplace transforms; image matching; image recognition; object detection; wavelet transforms; Fourier transform; Laplace operator; computer intelligent vision surveillance system; infrared target recognition; infrared thermal image; joint transform recognition; wavelet packet; Correlation; Filtering; Laplace equations; Target recognition; Target tracking; Wavelet packets; Fourier transform; Laplace operator; correlation recognition; infrared target; wavelet packet;
Conference_Titel :
Natural Computation (ICNC), 2010 Sixth International Conference on
Conference_Location :
Yantai, Shandong
Print_ISBN :
978-1-4244-5958-2
DOI :
10.1109/ICNC.2010.5582962