为了提高海上无人艇的舰船目标检测精度和速率，本文基于深度学习方法，利用卷积神经网络、区域建议网络及Fast R-CNN检测框架构建了舰船检测系统。该系统通过共享的卷积神经网络提取特征；通过区域建议网络生成候选区域；通过Fast R-CNN框架实现目标检测识别，从而实现端到端的舰船目标检测。实验结果表明，相比于传统机器学习目标检测算法，该舰船检测系统在检测精度及检测速率上均有大幅提高，达到83.79%的准确率及0.05 s/帧的检测速率。本文的舰船检测系统在检测精度及速率上均表现优异，满足了水面无人艇的工作要求。
In order to improve the detection speed and accuracy of ship target for unmanned surface vehicle, a ship detection system is constructed using convolutional neural networks, region proposal networks and Fast R-CNN detection framework based on deep learning method in this paper. The ship features are extracted by shared convolutional neural networks; the candidate region is generated through region proposal networks; and the target detection and recognition are realized through the Fast R-CNN framework to achieve end to end ship target detection. The experimental results show that, compared with the traditional machine learning algorithms for target detection, the precision and the detection rate of the proposed system has been greatly improved, the mean average precision reached 83.79% and the detection rate reached 0.05 seconds/frame. The ship detection system in this paper has excellent performance in detection accuracy and speed, and meets the actual requirements of unmanned surface vehicles.
2019,41(1): 111-115,124 收稿日期：2017-11-07
DOI：10.3404/j.issn.1672-7649.2019.01.021
分类号：TP391.41
基金项目：国家自然科学基金资助项目（61105071）；张家港江苏科技大学产业技术研究院自主产业化资助项目（509914003）
作者简介：袁明新(1978-),男,博士,副教授,研究方向为移动机器人视觉导航与控制、多机器人系统、人工智能
参考文献：
[1] 王旭升. 无人艇雷达图像目标检测系统的研究[D]. 大连:大连海事大学, 2016.
[2] 刘睿强. 深度学习算法在船舶电子海图识别中的应用[J]. 船舰科学技术, 2017, 39(2A):79-81 LIU Rui-qiang. Application of depth learning algorithm in ship electronic chart recognition[J]. Ship Science and Technology, 2017, 39(2A):79-81
[3] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110
[4] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//Computer Vision and Pattern Recognition(CVPR), IEEE Computer Society Conference on. San Diego, USA:IEEE, 2005, 1:886-893.
[5] KAZEMI F M, SAMADI S, POORREZA H R, et al. Vehicle recognition using curvelet transform and SVM[C]//Information Technology, 2007. ITNG'07. Fourth International Conference on. IEEE, 2007:516-521.
[6] FREUND Y, SCHAPIRE R E. A desicion-theoretic generalization of on-line learning and an application to boosting[C]//European Conference on Computational Learning Theory. Springer Berlin Heidelberg, 1995:23-37.
[7] FELZENSZWALB P, MCALLESTER D, RAMANAN D. A discriminatively trained, multiscale, deformable part model[C]//Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on. IEEE, 2008:1-8.
[8] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]//International Conference on Neural Information Processing Systems. Curran Associates Inc. 2012:1097-1105.
[9] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Computer Vision and Pattern Recognition(CVPR), IEEE Conference on. Columbus, USA:IEEE, 2014:580-587.
[10] HE K, ZHANG X, REN S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[M]//Computer Vision-ECCV 2014. New York:Springer International Publishing, 2014:346-361.
[11] GIRSHICK R. Fast r-cnn[C]//Proceedings of the IEEE International Conference on Computer Vision. 2015:1440-1448.
[12] REN S, HE K, GIRSHICK R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2016, 39(6):1137
[13] REDMON J, DIVYALA S, GIRSHICK R, et al. You only look once:Unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016:779-788.
[14] LIU W, ANGUELOV D, ERHAN D, et al. SSD:single shot multiBox detector[C]//European Conference on Computer Vision. Springer International Publishing, 2016:21-37.
[15] REDMON J, FARHADI A. YOLO9000:Better, Faster, Stronger[J]. arXiv preprint arXiv:1612. 08242, 2016.
[16] UIJLINGS J R R, VAN De, SANDE K E A, et al. Selective search for object recognition[J]. International Journal of Computer Vision, 2013, 104(2):154-171
[17] ZITNICK C L, DOLLAR P. Edge boxes:locating object proposals from edges[C]//European Conference on Computer Vision. Springer International Publishing, 2014:391-405.
[18] RUSSAKOVSKY O, DENG J, SU H, et al. Imagenet large scale visual recognition challenge[J]. International Journal of Computer Vision, 2015, 115(3):211-252
[19] ZEILER M D, FERGUS R. Visualizing and understanding convolutional networks[M]//Computer Vision-ECCV 2014. Springer International Publishing, 2014:818-833.
[20] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. Computer Science, 2014, 50(2):70-89
[21] JIA Y, SHELHAMER E, DONAHUE J, et al. Caffe:Convolutional architecture for fast feature embedding[C]//Proceedings of the 22nd ACM International Conference on Multimedia. ACM, 2014:675-678.
