Research on the Technology of Partial Masked Target Recognition

Abstract:

The result of target recognition is always influenced by the clutter background, low contrast and deficiency luminance of image. Besides the factors mentioned above, detection and recognition of partial masked target has the character of fragmented target, which leads to another problem. All the harmful factors cause that target recognition can not be realized by hybrid optoelectronic joint transform correlator (HOJTC) due to the weak correlation peaks, even no peaks appear. In this paper, input image of HOJTC is processed by the method of adaptive threshold, and power spectrum is processed by wavelet transform (WT) as well. The combination effectively controls the disturbance of noise and enhances the energy of diffractive light of target. Experiment of HOJTC shows that the method can enhance the contrast of correlation peaks of partial masked target and improve the detection and recognition capacity of HOJTC. As an example, the experiment results of fragmented airplane target before and after processing are shown in the paper, which demonstrate the effectiveness of the method.

• Periodical: Key Engineering Materials (Volume 552)
• Pages: 560-566
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.552.560
• Online since: May 2013
• Authors: Miao Hua, Yu Chen, Wen Sheng Wang
• Keywords: Adaptive Threshold, Correlation Peak, Hybrid Optoelectronic Joint Transform Correlator, Masked Target, Power Spectrum, Target Recognition, Wavelet Transform (WT)

References

[1] Song Feijun, S.Jutamulia. Advanced Optical Information Processing[M]. Beijing: Peking University Press, 2001.20～43.

[2] Wensheng Wang, Cuiping Liang, Hua Miao et al.. Hybrid optoelectronic joint transform correlator for the recognition of target in cluttered scenes[J]. Proc.SPIE, 2004: 204～213.

DOI: 10.1117/12.567880

[3] Defeng Zhang. Wavelet analysis with MATLAB. China machine press. 2010.

[4] Fengchun Tian. A Research on the Characteristics of Mexican-hat Mother Wavelet Used in Optic Realization [J]. Journal of Chongqing University,2002,25(12) : 62～65.

[5] Xiang Zhou, Hong Zhao. Three-Dimensional Profilometry Based on Mexican Hat Wavelet Transform[J]. Acta Optica Sinica, 2009,29(1):197～202.

DOI: 10.3788/aos20092901.0197

[6] Hua Miao, Xin Zou, Qi Lang,et al. Research on Spectrum Plane Processing Technology of Target Auto-Recognition in Cluttered Scenes [J]. Acta Optica Sinica,2009,29(2):366～369.

DOI: 10.3788/aos20092902.0366

[7] Qianqian Wang,Zhong Peng,Li Liu. An Adaptive Method of Image Segmentation[J]. Transactions of Beijing Institute of Technology, 2003, 23(4): 521-524.

[8] ELGAMMAL A,DURAISWAMI R,HARWOOD D,et al.Back-ground and foreground modeling using nonparametric kernel density estimation for visual surveillance[J].Proceedings of the IEEE, 2002, 90( 7) : 1151-1163．

DOI: 10.1109/jproc.2002.801448

[9] Wen Zhuo,Zhiguo Cao,Yang Xiao. Image Thresholding Based on Two-Dimensional Arimoto Entropy [J]. PatternRecognition and Artificial Intelligence,2009,22(2): 208-213.

[10] Ostu N.A threshold selection method from gray-level histogram[J].IEEETrans,1979.SMC-9: 62-66

[11] Bin Hu,Ningsheng Gong. An Improved Otsu's Thresholding Segmentation Method[J]. Microelectronics and Computer,2009,26( 12) : 153－156．