|
|
|
|
|
|
Research on Detection of Ship Target at Sea Based on Multi-Spectral Infrared Images |
QIU Rong-chao1, LOU Shu-li2, LI Ting-jun1, GONG Jian1 |
1. Naval Aviation University, Yantai 264000, China
2. School of Opto-Electronic Infomation Science and Technology, Yantai University, Yantai 264000,China |
|
|
Abstract When facing complex sea-sky background, island-shore background, bad weather, bright waves or decoys interference and other complex conditions, the detection rate, false alarm rate, detection distance or other performance indicators of the existing ship target detection system based on a single wide-wave infrared image will be affected. Considering the above problems, the detection method for ship target at sea based on multi-spectral infrared images was studied in this paper. Through the data acquisition system for multi-spectral infrared images, 107 groups of 5 medium-wave infrared images were collected actually. The spectrals from 1 to 5 were 3.7~4.8, 3.7~4.1, 4.4~4.8, 3.7~3.9 and 4.65~4.75 μm respectively. The sample data set was constructed by annotating the multi-spectral images manually, which was made up of 298 ship targets and 353 non-ship targets. Firstly, PCA transform was adopted to reduce the dimension of multi-spectral infrared images and selective search algorithm was adopted to generate the initial target candidate regions. In order to solve the problem that there are too many obvious non-ship target regions, the integral image was used to calculate the local contrast of the initial candidate regions and the ship target candidate regions were located according to the geometrical and grayscale features of infrared ship target. Secondly, each ship target candidate region was extended to incorporate the local context information. For the 5 spectral images corresponding to each ship target candidate region, dense SIFT feature of each spectral image was extracted. PCA was applied to SIFT feature, reducing its dimensionality from 128 to 64. Then the spatial and spectral position distribution information of each SIFT feature was added to the feature vector. Based on the Gaussian mixture model, the feature vectors of each candidate region were encoded to Fisher vector representation. Finally, linear SVM classifier was used to recognize ship targets. Experiment of the generation of ship target candidate regions showed that the proposed constraint method based on geometrical and grayscale features of infrared ship target can effectively overcome the shortcomings of selective search algorithm and quickly locate the ship target candidate regions from the initial target candidate regions. Experimental results on 25 groups of multi-spectral images showed that the generation of ship target candidate regions takes 0.353 s totally, while locating the ship target candidate regions takes only 0.005 s. Test of target recognition on 100 positive and negative samples showed that the recognition rate of the proposed target recognition algorithm reached 0.97, which is significantly higher than the target recognition rate based on single-wave infrared image. The proposed target recognition algorithm integrates the feature information of the multi-spectral target images and applies Fisher vector to extract the deep layer information in the gradient statistical features of the multi-spectral target images. Experimental results on 25 groups of multi-spectral images showed that the proposed ship target detection method can detect the ship targets at sea in different scenes such as sea-sky background, island background and bright waves interference. The locations of the ship targets are accurate and the ship recall rate reaches 0.95. The average detection time of each group of multi-spectral images is 1.33 s. The study results showed that with considering the radiation difference between the ship target and its local ocean background in the infrared image and the effective fusion of the radiation characteristics of ship target in multi-spectral infrared images, the divisibility of ship target can be enhanced, which results in the improvement of recognition rate and detection rate of ship target. This study provides new technical support for ship target detection based on multi-spectral infrared images.
|
Received: 2018-01-09
Accepted: 2018-04-16
|
|
|
[1] QIAN Ang, HE You-jin, LIU Liang(钱 昂, 何友金, 刘 亮). Infrared Technology(红外技术), 2014, 36(8): 671.
[2] Dolgopolov A V, Kazantsev P A, Bezuhliy N N, et al. Indian Journal of Science & Technology, 2017, 9(46): 1.
[3] GUO Shao-jun, SHEN Tong-sheng, XU Jian, et al(郭少军, 沈同圣, 徐 健, 等). Systems Engineering and Electronics(系统工程与电子技术), 2016, 38(1): 14.
[4] Yang F, Xu Q, Li B. IEEE Geoscience & Remote Sensing Letters, 2017, 14(5): 602.
[5] ZHANG Zhong-yu, JIAO Shu-hong(张仲瑜, 焦淑红). Infrared and Laser Engineering(红外与激光工程), 2015, (b12): 29.
[6] ZHANG Di-fei, ZHANG Jin-suo, YAO Ke-ming, et al(张迪飞, 张金锁, 姚克明, 等). Infrared and Laser Engineering(红外与激光工程), 2016, 45(1): 167.
[7] LIU Feng, SHEN Tong-sheng, GUO Shao-jun, et al(刘 峰, 沈同圣, 郭少军, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2017, 37(6): 1934.
[8] Uijlings J R, Sande K E, Gevers T, et al. International Journal of Computer Vision, 2013, 104(2): 154.
[9] Agrawal A, Mangalraj P, Bisherwal M A. Target Detection in SAR Images using SIFT, IEEE International Symposium on Signal Processing and Information Technology, 2016: 90.
[10] ZHOU Quan, WEI Xin, CHEN Jian-xin, et al(周 全, 魏 昕, 陈建新, 等). Journal of Electronics & Information Technology(电子与信息学报), 2015, 37(8): 1913.
[11] Simonyan K, Parkhi O, Vedaldi A, et al. Fisher Vector Factor in the Wild, Proc. Bmvc., 2013: 8. 1.
[12] GUAN Tao, LI Ling-ling(管 涛, 李玲玲). Journal of Image and Graphics(中国图象图形学报), 2012, 17(12): 1461.
[13] HU Qing-xin, Lü Peng(胡庆新, 吕 鹏). Journal of Computer Applications(计算机应用), 2016, 36(s1): 157.
[14] DU Lan, LIU Bin, WANG Yan, et al(杜 兰, 刘 彬, 王 燕, 等). Journal of Electronics & Information Technology(电子与信息学报), 2016, 38(12): 3018. |
[1] |
LI He1, WANG Yu2, FAN Kai2, MAO Yi-lin2, DING Shi-bo3, SONG Da-peng3, WANG Meng-qi3, DING Zhao-tang1*. Evaluation of Freezing Injury Degree of Tea Plant Based on Deep
Learning, Wavelet Transform and Visible Spectrum[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 234-240. |
[2] |
GAO Hong-sheng1, GUO Zhi-qiang1*, ZENG Yun-liu2, DING Gang2, WANG Xiao-yao2, LI Li3. Early Classification and Detection of Kiwifruit Soft Rot Based on
Hyperspectral Image Band Fusion[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 241-249. |
[3] |
YANG Chun-mei1, ZHU Zan-bin1, 2*, LI Yu-cheng1, MA Yan1, SONG Hai-yang3. Bark Content Determination of Ultra-Thin Fibreboard by
Hyperspectral Technique[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3266-3271. |
[4] |
ZHANG Hai-liang1, XIE Chao-yong1, LUO Wei1, WANG Chen2, NIE Xun1, TIAN Peng1, LIU Xue-mei3, ZHAN Bai-shao1*. Salmon Fat Visualization Based on MCR-ALS Hyperspectral
Reconstruction[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(08): 2601-2607. |
[5] |
LI Shu-fei1, LI Kai-yu1, QIAO Yan2, ZHANG Ling-xian1*. Cucumber Disease Detection Method Based on Visible Light Spectrum and Improved YOLOv5 in Natural Scenes[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(08): 2596-2600. |
[6] |
ZHANG Hong-tao, ZHAO Xin-tao, TAN Lian, WANG Long-jie. Research and Development of Microscopic Hyperspectral Imaging in
Biological Detection[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(08): 2348-2353. |
[7] |
MAO Yi-lin1, LI He1, WANG Yu1, FAN Kai1, SUN Li-tao2, WANG Hui3, SONG Da-peng3, SHEN Jia-zhi2*, DING Zhao-tang1, 2*. Quantitative Judgment of Freezing Injury of Tea Leaves Based on Hyperspectral Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(07): 2266-2271. |
[8] |
ZHONG Jing-jing1, 2, LIU Xiao1, 3, WANG Xue-ji1, 3, LIU Jia-cheng1, 3, LIU Hong1, 3, QI Chen1, 3, LIU Yu-yang1, 2, 3, YU Tao1, 3*. A Multidimensional Information Fusion Algorithm for Polarization
Spectrum Reconstruction Based on Nonsubsampled Contourlet
Transform[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(04): 1254-1261. |
[9] |
SU Ling1, 2, BU Ya-ping1, 2, LI Yuan-yuan2, WANG Qi1, 2*. Study on the Prediction Method of Pleurotus Ostreatus Protein and
Polysaccharide Content Based on Fourier Transform Infrared
Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(04): 1262-1267. |
[10] |
LI Kai-yu1, ZHANG Hui2, MA Jun-cheng3, ZHANG Ling-xian1*. Segmentation Method for Crop Leaf Spot Based on Semantic Segmentation and Visible Spectral Images[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(04): 1248-1253. |
[11] |
FENG Xin1, 2, FANG Chao1*, GONG Hai-feng2, LOU Xi-cheng1, PENG Ye1. Infrared and Visible Image Fusion Based on Two-Scale Decomposition and
Saliency Extraction[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(02): 590-596. |
[12] |
YANG Cheng-en1, SU Ling2, FENG Wei-zhi1, ZHOU Jian-yu1, WU Hai-wei1*, YUAN Yue-ming1, WANG Qi2*. Identification of Pleurotus Ostreatus From Different Producing Areas Based on Mid-Infrared Spectroscopy and Machine Learning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(02): 577-582. |
[13] |
XIA Tong, LIU Yi-wei, GAO Yuan, CHENG Jie*, YIN Jian. Model-Fitting Methods for Mineral Raman Spectra Classification[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(02): 583-589. |
[14] |
ZHANG Qian1, YANG Ying1*, LIU Gang1, 2, 3, WU Xiao1, NING Yuan-lin1. Detection of Dairy Cow Mastitis From Thermal Images by Data Enhancement and Improved ResNet34[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(01): 280-288. |
[15] |
LI Yun-xia1, MA Jun-cheng2, LIU Hong-jie3, ZHANG Ling-xian1*. Tillering Number Estimation of Winter Wheat Based on Visible
Spectrogram and Lightweight Convolutional Neural Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(01): 273-279. |
|
|
|
|