Rapid ship detection based on gradient texture features and multilayer perceptron

Dong Chao; Feng Junjian; Tian Lianfang; Zheng Bing

doi:10.3788/IRLA201948.1026004

Volume 48 Issue 10

Oct. 2019

Turn off MathJax

Article Contents

Article Navigation > Infrared and Laser Engineering > 2019 > 48(10): 1026004-1026004(10)

Dong Chao, Feng Junjian, Tian Lianfang, Zheng Bing. Rapid ship detection based on gradient texture features and multilayer perceptron[J]. Infrared and Laser Engineering, 2019, 48(10): 1026004-1026004(10). doi: 10.3788/IRLA201948.1026004

Citation:

Dong Chao, Feng Junjian, Tian Lianfang, Zheng Bing. Rapid ship detection based on gradient texture features and multilayer perceptron[J]. Infrared and Laser Engineering, 2019, 48(10): 1026004-1026004(10). doi: 10.3788/IRLA201948.1026004

Rapid ship detection based on gradient texture features and multilayer perceptron

doi: 10.3788/IRLA201948.1026004

1.
South China Sea Marine Survey and Technology Center,State Oceanic Administration,Guangzhou 510300,China;
2.
Key Laboratory of Technology for Safeguarding of Marine Rights and Interests and Application,State Oceanic Administration,Guangzhou 510300,China;
3.
School of Automation Science and Engineering,South China University of Technology,Guangzhou 510641,China

Received Date: 2019-06-05
Rev Recd Date: 2019-07-15
Publish Date: 2019-10-25

Abstract

Aiming at the issues of low ship detection rate caused by the failure of background modeling in the dynamic complex environment of traditional ship detection methods, a rapid ship detection algorithm based on gradient texture histogram features and multilayer perceptron was proposed. The feature fusion between gradient and texture histogram of the target was performed using multilayer perceptron, constructing the feature space for ship targets. Firstly, the region proposal model based on binarized normed gradient feature was trained to quickly generate a small number of ship candidate windows with high recall rate and then the gradient texture histogram features were extracted from each candidate window. Secondly, a multilayer perceptron was designed as a ship classifier to distinguish the gradient texture histogram features. Experimental results show that the proposed algorithm has an average precision of 90.0% and an average time of 20.4 ms/frame in multiple maritime scenes, which effectively realizes rapid ship detection in maritime scenes.
- rapid ship detection,
- gradient texture histogram,
- multilayer perceptron

References

[1]	Wang Huili, Zhu Ming, Lin Chunbo, et al. Ship detection of complex sea background in optical remote sensing images[J]. Optical and Precision Engineering, 2018, 26(3):723-732. (in Chinese)王慧利, 朱明, 蔺春波, 等. 光学遥感图像中复杂海背景下的舰船检测[J]. 光学精密工程, 2018, 26(3):723-732.
[2]	Ding Peng, Zhang Ye, Jia Ping, et al. Ship detection on sea surface based on multi-feature and multi-scale visual attention[J]. Optical and Precision Engineering, 2017, 45(1):167-172. (in Chinese)丁鹏, 张叶, 贾平, 等. 基于多尺度多特征视觉显著性的海面舰船检测[J]. 光学精密工程, 2017, 45(1):167-172.
[3]	Zhang Zhongyu, Jiao Shuhong. Infrared ship target detection method based on multiple feature fusion[J]. Infrared and Laser Engineering, 2015, 44(S):29-34. (in Chinese)张仲瑜, 焦淑红. 多特征融合的红外舰船目标检测方法[J]. 红外与激光工程, 2015, 45(S):29-34.
[4]	Prasad D K, Prasath C K, Rajan D, et al. Object detection in a maritime environment:performance evaluation of background subtraction methods[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 20(5):1787-1802.
[5]	Zhang Yang, Li Qingzhong, Zang Fengni. Ship detection for visual maritime surveillance from non-stationary platforms[J]. Ocean Engineering, 2017, 141:53-63.
[6]	Li J, Tian Y, Huang T. Visual saliency with statistical priors[J]. International Journal of Computer Vision, 2014, 107(3):239-253.
[7]	Wang X, Han T X, Yan S. An HOG-LBP human detector with partial occlusion handling[C]//2009 IEEE 12th International Conference on Computer Vision. IEEE, 2010:32-39.
[8]	Cheng Quan, Fan Yu, Liu Yuchun, et al. Moving target detection method based on block projection matching[J]. Infrared and Laser Engineering, 2018, 47(10):1026004. (in Chinese)程全, 樊宇, 刘玉春, 等. 分块投影匹配的运动目标检测方法[J]. 红外与激光工程, 2018, 47(10):1026004.
[9]	Lu Fuxing, Chen Xin, Chen Guilin, et al. Dim and small target detection based on background adaptive multi-feature fusion[J]. Infrared and Laser Engineering, 2019, 48(3):0326002. (in Chinese)陆福星, 陈忻, 陈桂林, 等. 背景自适应的多特征融合的弱小目标检测[J]. 红外与激光工程, 2019, 48(3):0326002.
[10]	Wu Tianshu, Zhang Zhijia, Liu Yunpeng, et al. A lightweight small object detection algorithm based on improved SSD[J]. Infrared and Laser Engineering, 2018, 47(7):0703005. (in Chinese)吴天舒, 张志佳, 刘云鹏, 等. 基于改进SSD的轻量化小目标检测算法[J]. 红外与激光工程, 2018, 47(7):0703005.
[11]	Guliyev N J, Ismailov V E. On the approximation by single hidden layer feedforward neural networks with fixed weights[J]. Neural Networks, 2017, 98:296-304.
[12]	Hosang J, Benenson R, Dollr P, et al. What makes for effective detection proposals?[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 38(4):814-830.
[13]	Cheng M M, Zhang Z, Lin W Y, et al. BING:Binarized normed gradients for objectness estimation at 300 fps[C]//Computer Vision Pattern Recognition, 2014.
[14]	Friedman J, Hastie T, Tibshirani R. Regularization paths for generalized linear models via coordinate descent[J]. Journal of Statistical Software, 2010, 33(1):1.
[15]	Mdakane L, Bergh F V D. Extended local binary pattern features for improving settlement type classification of QuickBird images[J]. Comptes Rendus Des Sances De La Socit De Biologie Et De Ses Filiales, 2012, 148(21-22):1851-1852.
[16]	Vogl T P, Mangis J K, Rigler A K, et al. Accelerating the convergence of the back-propagation method[J]. Biological Cybernetics, 1988, 59(4-5):257-263.
[17]	Uijlings J R R, van de Sande K E A. Selective search for object recognition[J]. International Journal of Computer Vision, 2013, 104(2):154-171.
[18]	Alexe B, Deselaers T, Ferrari V. Measuring the objectness of image windows[J]. IEEE Transactions on Software Engineering, 2012, 34(11):2189-2202.

Proportional views

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Get Citation

PDF

XML

Article Metrics

Article views(589) PDF downloads(57) Cited by()

Proportional views

Rapid ship detection based on gradient texture features and multilayer perceptron

1. South China Sea Marine Survey and Technology Center,State Oceanic Administration,Guangzhou 510300,China;

2. Key Laboratory of Technology for Safeguarding of Marine Rights and Interests and Application,State Oceanic Administration,Guangzhou 510300,China;

3. School of Automation Science and Engineering,South China University of Technology,Guangzhou 510641,China

Received Date: 2019-06-05

Rev Recd Date: 2019-07-15

Publish Date: 2019-10-25

Key words:

Abstract: Aiming at the issues of low ship detection rate caused by the failure of background modeling in the dynamic complex environment of traditional ship detection methods, a rapid ship detection algorithm based on gradient texture histogram features and multilayer perceptron was proposed. The feature fusion between gradient and texture histogram of the target was performed using multilayer perceptron, constructing the feature space for ship targets. Firstly, the region proposal model based on binarized normed gradient feature was trained to quickly generate a small number of ship candidate windows with high recall rate and then the gradient texture histogram features were extracted from each candidate window. Secondly, a multilayer perceptron was designed as a ship classifier to distinguish the gradient texture histogram features. Experimental results show that the proposed algorithm has an average precision of 90.0% and an average time of 20.4 ms/frame in multiple maritime scenes, which effectively realizes rapid ship detection in maritime scenes.

HTML

Reference (18)

[1]	Wang Huili, Zhu Ming, Lin Chunbo, et al. Ship detection of complex sea background in optical remote sensing images[J]. Optical and Precision Engineering, 2018, 26(3):723-732. (in Chinese)王慧利, 朱明, 蔺春波, 等. 光学遥感图像中复杂海背景下的舰船检测[J]. 光学精密工程, 2018, 26(3):723-732.
[2]	Ding Peng, Zhang Ye, Jia Ping, et al. Ship detection on sea surface based on multi-feature and multi-scale visual attention[J]. Optical and Precision Engineering, 2017, 45(1):167-172. (in Chinese)丁鹏, 张叶, 贾平, 等. 基于多尺度多特征视觉显著性的海面舰船检测[J]. 光学精密工程, 2017, 45(1):167-172.
[3]	Zhang Zhongyu, Jiao Shuhong. Infrared ship target detection method based on multiple feature fusion[J]. Infrared and Laser Engineering, 2015, 44(S):29-34. (in Chinese)张仲瑜, 焦淑红. 多特征融合的红外舰船目标检测方法[J]. 红外与激光工程, 2015, 45(S):29-34.
[4]	Prasad D K, Prasath C K, Rajan D, et al. Object detection in a maritime environment:performance evaluation of background subtraction methods[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 20(5):1787-1802.
[5]	Zhang Yang, Li Qingzhong, Zang Fengni. Ship detection for visual maritime surveillance from non-stationary platforms[J]. Ocean Engineering, 2017, 141:53-63.
[6]	Li J, Tian Y, Huang T. Visual saliency with statistical priors[J]. International Journal of Computer Vision, 2014, 107(3):239-253.
[7]	Wang X, Han T X, Yan S. An HOG-LBP human detector with partial occlusion handling[C]//2009 IEEE 12th International Conference on Computer Vision. IEEE, 2010:32-39.
[8]	Cheng Quan, Fan Yu, Liu Yuchun, et al. Moving target detection method based on block projection matching[J]. Infrared and Laser Engineering, 2018, 47(10):1026004. (in Chinese)程全, 樊宇, 刘玉春, 等. 分块投影匹配的运动目标检测方法[J]. 红外与激光工程, 2018, 47(10):1026004.
[9]	Lu Fuxing, Chen Xin, Chen Guilin, et al. Dim and small target detection based on background adaptive multi-feature fusion[J]. Infrared and Laser Engineering, 2019, 48(3):0326002. (in Chinese)陆福星, 陈忻, 陈桂林, 等. 背景自适应的多特征融合的弱小目标检测[J]. 红外与激光工程, 2019, 48(3):0326002.
[10]	Wu Tianshu, Zhang Zhijia, Liu Yunpeng, et al. A lightweight small object detection algorithm based on improved SSD[J]. Infrared and Laser Engineering, 2018, 47(7):0703005. (in Chinese)吴天舒, 张志佳, 刘云鹏, 等. 基于改进SSD的轻量化小目标检测算法[J]. 红外与激光工程, 2018, 47(7):0703005.
[11]	Guliyev N J, Ismailov V E. On the approximation by single hidden layer feedforward neural networks with fixed weights[J]. Neural Networks, 2017, 98:296-304.
[12]	Hosang J, Benenson R, Dollr P, et al. What makes for effective detection proposals?[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 38(4):814-830.
[13]	Cheng M M, Zhang Z, Lin W Y, et al. BING:Binarized normed gradients for objectness estimation at 300 fps[C]//Computer Vision Pattern Recognition, 2014.
[14]	Friedman J, Hastie T, Tibshirani R. Regularization paths for generalized linear models via coordinate descent[J]. Journal of Statistical Software, 2010, 33(1):1.
[15]	Mdakane L, Bergh F V D. Extended local binary pattern features for improving settlement type classification of QuickBird images[J]. Comptes Rendus Des Sances De La Socit De Biologie Et De Ses Filiales, 2012, 148(21-22):1851-1852.
[16]	Vogl T P, Mangis J K, Rigler A K, et al. Accelerating the convergence of the back-propagation method[J]. Biological Cybernetics, 1988, 59(4-5):257-263.
[17]	Uijlings J R R, van de Sande K E A. Selective search for object recognition[J]. International Journal of Computer Vision, 2013, 104(2):154-171.
[18]	Alexe B, Deselaers T, Ferrari V. Measuring the objectness of image windows[J]. IEEE Transactions on Software Engineering, 2012, 34(11):2189-2202.

Rapid ship detection based on gradient texture features and multilayer perceptron

doi: 10.3788/IRLA201948.1026004

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views