Fast ground target detection method in infrared image sequences

Automatic target detection (ATD) in infrared (IR) imagery is a fundamental and challenging task in computer vision. A fast automatic target detection method in IR image sequence is proposed in this paper. Since the position and scale of target change real-timely, we can predict the target position in real-time image by using the history position of target and flight parameters information of previous and current frames, and then estimate the scale of target depending on flight parameters and imaging parameters for getting the model with the appropriate scale. In order to make the template matching more robust for target rotation, the template matching method based on parametric template vector is used to recognize the position of target. The detection result is identified by using multiframe integration based on recognition information of history and currant frames. Some experimental results using real-world images with complicated background validate the effectiveness and robustness of the proposed method under rotation and scale variance condition.

[1]  E. Abdelkawy,et al.  Wavelet-based image target detection methods , 2003, SPIE Defense + Commercial Sensing.

[2]  Paul D. Gader,et al.  Automatic target detection using entropy optimized shared-weight neural networks , 2000, IEEE Trans. Neural Networks Learn. Syst..

[3]  Soo-Chang Pei,et al.  A morphological approach of target detection on perspective plane , 2001, Signal Process..

[4]  Yi-Hsien Lin,et al.  Template matching using the parametric template vector with translation, rotation and scale invariance , 2008, Pattern Recognit..

[5]  Qun Zhao,et al.  Support vector machines for SAR automatic target recognition , 2001 .

[6]  Zhang Peng,et al.  The design of Top-Hat morphological filter and application to infrared target detection , 2006 .

[7]  Bir Bhanu,et al.  A system for model-based object recognition in perspective aerial images , 1998, Pattern Recognit..

[8]  Tianxu Zhang,et al.  Robust and fast Hausdorff distance for image matching , 2012 .

[9]  Francesca Bovolo,et al.  Semisupervised One-Class Support Vector Machines for Classification of Remote Sensing Data , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Jake K. Aggarwal,et al.  Bayesian recognition of targets by parts in second generation forward looking infrared images , 2000, Image Vis. Comput..

[11]  Xiang Zhou,et al.  Robust stereo image matching using a two-dimensional monogenic wavelet transform. , 2009, Optics letters.

[12]  B. Bhanu,et al.  Image understanding research for automatic target recognition , 1993, IEEE Aerospace and Electronic Systems Magazine.

[13]  J.A. Ratches,et al.  Target acquisition performance modeling of infrared imaging systems: past, present, and future , 2001, IEEE Sensors Journal.