A deep attention mechanism method for maritime salient ship detection in complex sea background

Abstract

Saliency ship detection has received increasing attention due to its important applications in maritime field in recent years. Up to now, numerous studies on saliency detection have been done based on traditional methods and deep learning methods. But these previous research works are still not competent enough in detecting ship targets with complex backgrounds and noises. In this letter, we propose a deep attention mechanism method for more accurate and faster maritime salient ship detection. We optimize the initial ship saliency map by using a feature attention module to focus on salient objects. We reduce and improve the convolution kernel in refinement residual module to enhance the detection efficiency. In addition, Leaky ReLU is selected as the activation function to increase the non-linear capability of the method. Experiment results show that, the proposed method could obtain outstanding performance in salient ship detection in complex sea background.

References

[1] Cheng M. M., Zhang G. X., Niloy J. M., Huang X. L. and Hu S. M., Global Contrast Based Salient Region Detection, Conference on Computer Vision and Pattern Recognition, 409 (2011).

[2] SunM J, ZhouZ Q, HuQ H, WangZ, JiangJ M. IEEE Transactions on Cybernetics, 2018, 49: 2900

[3] Tom Cane and James Ferryman, Saliency-Based Detection for Maritime Object Tracking, Conference on Computer Vision and Pattern Recognition, 18 (2016).

[4] XuF, LiuJ-H. Optoelectronics Letters, 2016, 12: 473

[5] X. Bao, S. Zinger, R. Wijnhoven and Peter H. N. de With, Ship Detection in Port Surveillance Based on Context and Motion Saliency Analysis, SPIE, 86630D (2013).

[6] BiF, ZhuB, GaoL, BianM. IEEE Geoscience and Remote Sensing Letters, 2012, 9: 749

[7] LinH-N, ShiZ-W, ZouZ-X. IEEE Geoscience and Remote Sensing Letters, 2017, 14: 1665

[8] A. Mumtaz, A. Jabber, Z. Mahmood, R. Nawaz and Q. Ahsan, Saliency Based Algorithm for Ship Detection in Infrared Images, 13th International Bhurban Conference on Applied Sciences and Technology, 167 (2016).

[9] ShaoZ-F, WangL-G, WangZ-Y, DuW, WuW-J. IEEE Transactions on Circuits and Systems for Video Technology, 2020, 30: 781

[10] P. Isola, J. Y. Zhu, Zhou T. H. and A. Efros Alexei, Image-to-Image Translation with Conditional Adversarial Networks, Conference on Computer Vision and Pattern Recognition, 1125 (2017).

[11] Li Guan-bin and Yu Yi-zhou, Visual Saliency Based on Multiscale Deep Features, Conference on Computer Vision and Pattern Recognition, 5455 (2015).

[12] Zhang P., Wang D., Lu H., Wang H. and Ruan X., Amulet: Aggregating Multi-Level Convolutional Features for Salient Object Detection, IEEE International Conference on Computer Vision, 202 (2017).

[13] Xie Sai-ning and Tu Zhou-wen, Holistically-Nested Edge Detection, IEEE International Conference on Computer Vision, 1395 (2015).

[14] V. Mnih, N. Heess and A. Graves, Recurrent Models of Visual Attention, Advances in Neural Information Processing Systems, 2204 (2014).

[15] Dilip K. Prasad, Singapore Maritime Dataset, https://sites.google.com/site/dilipprasad/home/singapore-maritime-dataset, 2016.

[16] ChengM-M, MitraN J, HuangX-L, TorrP H S, HuS-M. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 37: 569

[17] Yan Qiong, Xu Li, Shi Jian-ping and Jia Jia-ya, Hierarchical Saliency Detection, Conference on Computer Vision and Pattern Recognition, 1155 (2013).

[18] Li Yin, Hou Xiao-di, Christof. Koch, James M. Rehg and Alan L. Yuille, The Secretsof Salient Object Segmentation Conference on Computer Vision and Pattern Recognition, 280 (2014).

[19] Yang Chuan, Zhang Li-he, Lu Hu-chuan, Ruan Xiang and Yang Ming-Hsuan, Saliency Detection via Graph-Based Manifold Ranking, Conference on Computer Vision and Pattern Recognition, 3166 (2013).

[20] HouQ-B, ChengM-M, HuX-W, AliB, TuZ-W, PhilipHS. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 41: 4

[21] Zhao Ting and Wu Xiang-qian, Pyramid Feature Attention Network for Saliency Detection, Conference on Computer Vision and Pattern Recognition, 1 (2019).

[22] D. P. Kingma and J. Ba. Adam, A Method for Stochastic Optimization, International Conference on Learning Representations, 1 (2015).

[23] T. Albrecht, G. A. W. West, T. Tan and T. Ly, Visual Maritime Attention Using Multiple Low-Level Features and Naive Bayes Classification, IEEE International Conference on Digital Image Computing: Techniques & Applications, 243 (2011).

[24] Zhang Jian-ming, Stan Sclaroff, Lin Zhe, Shen Xiaohui, Price Brian and Mech Radomír, Minimum Barrier Salient Object Detection at 80 FPS, IEEE International Conference on Computer Vision, 2015.

[25] Liu Hai-ying, Omar Javed, Geoff Taylor, Cao Xiao-chun and Niels Haering, Omni-Directional Surveillance for Unmanned Water Vehicles, Proc. Eighth Int. Workshop Visual Surveillance, 1 (2008).

[26] K. Makantasis, A. Doulamis and N. Doulamis, Vision-Based Maritime Surveillance System Using Fused Visual Attention Maps and Online Adaptable Tracker, IEEE 14th International Workshop on Image Analysis for Multimedia Interactive Services, 1 (2013).

[27] HouX-D, JonathanH, ChristofK. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 34: 194

[28] GuoS-J, LouS-L, LiuF. Chinese Journal of Liquid Crystals and Displays, 2016, 31: 1006 in Chinese)

[29] LvF-Q, WangH, LiuH. Journal of Shanghai Jiaotong University, 2012, 46: 1920(in Chinese)

[30] Rob Wijnhoven, Kris van Rens, Egbert G.T. Jaspers and Peter H.N. de With, Online Learning for Ship Detection in Maritime Surveillance, Symposium on Information Theory in the Benelux, 73 (2010).

[31] LiuG, ZhangY-S, ZhengX-W, SunX, FuK, WangH-Q. IEEE Geoscience and Remote Sensing Letters, 2014, 11: 617

[32] LinH-N, ShiZ-W, ZouZ-X. IEEE Geoscience and Remote Sensing Letters, 2017, 14: 1665