Multi-Spectral Ship Target Recognition Based on Feature Level Fusion
LIU Feng1, SHEN Tong-sheng2, GUO Shao-jun1，ZHANG Jian3
1. Naval Aeronautical and Astronautical University Department of Control Engineering, Yantai 264001, China
2. National Defense Science and Technology Information Center, Beijing 100142, China
3. PLA No.91206 Troops, Qingdao 264001, China
Abstract：Aiming at solving the problem of inadequate ability of recognizing single band warship targets on the sea in complicated situations, image fusion technology for three band feature levels of visible light, short wave infrared and medium wave infrared has been studied. Problems of time-consuming and fusion strategy existed in image fusion have been solved as top priorities. A new multi-band fusion method based on regional covariance matrix has been proposed in this paper. The advantage is that it can fuse several related features naturally through low dimensional vector. This paper has designed 11-dimensional and 5-dimensional feature vectors for visible light image and infrared image respectively, which not only ensures the differences among different targets but also decreases the calculation. Saliency detection has been adopted firstly in this paper to position the target area in the image quickly; and then, distance calculation formula of covariance matrix has been defined for the feature vectors of different band image designs and matching has been made in the following; integral image has been attained through one traversal operation for the image; purpose of quick calculation has been realized in the calculation for covariance; finally, K-nearest neighbor (KNN) algorithm has been adopted to make classification and recognition for various warship targets. Over 3 400 images of three-band warship target have been used as testing data. The experiment mainly includes two parts: first, comparing the recognition rate of single-band and three-band fusion recognition and to verify that the fusion method proposed in this paper has more extensive application range. Second, comparing several traditional pixel level methods in the calculation efficiency to verify the advantages of feature fusion adopted in this paper in calculation time. Experimental results have shown that the recognition rate of this method can reach 95.1% and time for single frame calculation is about 0.5 s, which has made distinctive improvement in both real time and detection rate.
[1] Hassen R, Zhou W, Salama M. IEEE Trans. Image Process., 2015, 24(9): 2714.
[2] Adu J, Gan J, Wang Y, et al. Infrared Physics & Technology, 2013, 61(5): 94.
[3] Qu X J, Zhang F, Zhang Y. Applied Mechanics and Materials，2013, 347: 2380.
[4] Lan X Y, Andy J, Pong C. IEEE Trans. Image Process., 2015, 24(12): 5826.
[5] YANG Guang, TONG Tao, LU Song-yan, et al(杨 桄, 童 涛, 陆松岩, 等). Optics and Precision Engineering(光学精密工程), 2014, 22(2): 489.
[6] Liu H, Yu Y L, Sun F C, et al. IEEE Transactions on Automation Science and Engineering, 2016, 99: 1.
[7] Yuan Y H, Sun Q S. Neurocomputing, 2013, 122(5): 229.
[8] Wu Y, Cheng J, Wang J, et al. IEEE Transactions on Image Processing, 2012, 21(5): 2824.
[9] Cheng M M, Zhang G X, Mitra X, et al. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3): 409.
[10] Krahenbuhl P. IEEE Conference on Computer Vision & Pattern Recognition, 2012, 157: 733.
[11] Yang C, Zhang L, Lu H, et al. IEEE Conference on Computer Vision and Pattern Recognition, 2013, 9: 3166.
[12] Bai X, Zhou F, Xue B. Optics Express, 2011, 19(9): 8444.
[13] Shi Z, Xu J, Zhang Y, et al. Infrared Physics & Technology, 2015, 71: 363.
