Probabilistic Ship Detection and Classification Using Deep Learning

被引:59
作者
Kim, Kwanghyun [1 ]
Hong, Sungjun [1 ]
Choi, Baehoon [1 ]
Kim, Euntai [1 ]
机构
[1] Yonsei Univ, Sch Elect & Elect Engn, 50 Yonsei Ro, Seoul 03722, South Korea
来源
APPLIED SCIENCES-BASEL | 2018年 / 8卷 / 06期
基金
新加坡国家研究基金会;
关键词
ship detection; ship classification; ship dataset; deep learning; Faster R-CNN; autonomous ship; Intersection over Union (IoU) tracking; Bayesian fusion; COLLISION-AVOIDANCE;
D O I
10.3390/app8060936
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
For an autonomous ship to navigate safely and avoid collisions with other ships, reliably detecting and classifying nearby ships under various maritime meteorological environments is essential. In this paper, a novel probabilistic ship detection and classification system based on deep learning is proposed. The proposed method aims to detect and classify nearby ships from a sequence of images. The method considers the confidence of a deep learning detector as a probability; the probabilities from the consecutive images are combined over time by Bayesian fusion. The proposed ship detection system involves three steps. In the first step, ships are detected in each image using Faster region-based convolutional neural network (Faster R-CNN). In the second step, the detected ships are gathered over time and the missed ships are recovered using the Intersection over Union of the bounding boxes between consecutive frames. In the third step, the probabilities from the Faster R-CNN are combined over time and the classes of the ships are determined by Bayesian fusion. To train and evaluate the proposed system, we collected thousands of ship images from Google image search and created our own ship dataset. The proposed method was tested with the collected videos and the mean average precision increased by 89.38 to 93.92% in experimental results.
引用
收藏
页数:17
相关论文
共 24 条
[1]  
Crisp DJ, 2004, Tech. Rep. DSTO-RR-0272
[2]  
Dai J., 2016, ADV NEURAL INFORM PR, V29, P379, DOI [DOI 10.1016/J.JPOWSOUR.2007.02.075, DOI 10.48550/ARXIV.1605.06409, DOI 10.1109/CVPR.2017.690]
[3]   The Pascal Visual Object Classes (VOC) Challenge [J].
Everingham, Mark ;
Van Gool, Luc ;
Williams, Christopher K. I. ;
Winn, John ;
Zisserman, Andrew .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2010, 88 (02) :303-338
[4]  
Geiger A., 2012, C COMP VIS PATT REC
[5]  
Girshick R., 2014, P IEEE C COMP VIS PA, DOI [10.1109/CVPR.2014.81, DOI 10.1109/CVPR.2014.81, 10.1109/cvpr.2014.81]
[6]   Fast R-CNN [J].
Girshick, Ross .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :1440-1448
[7]   Probabilistic gait modelling and recognition [J].
Hong, Sungjun ;
Lee, Heesung ;
Kim, Euntai .
IET COMPUTER VISION, 2013, 7 (01) :56-70
[8]   Speed/accuracy trade-offs for modern convolutional object detectors [J].
Huang, Jonathan ;
Rathod, Vivek ;
Sun, Chen ;
Zhu, Menglong ;
Korattikara, Anoop ;
Fathi, Alireza ;
Fischer, Ian ;
Wojna, Zbigniew ;
Song, Yang ;
Guadarrama, Sergio ;
Murphy, Kevin .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :3296-+
[9]   Application of Artificial Neural Networks to Ship Detection from X-Band Kompsat-5 Imagery [J].
Hwang, Jeong-In ;
Chae, Sung-Ho ;
Kim, Daeseong ;
Jung, Hyung-Sup .
APPLIED SCIENCES-BASEL, 2017, 7 (09)
[10]   Caffe: Convolutional Architecture for Fast Feature Embedding [J].
Jia, Yangqing ;
Shelhamer, Evan ;
Donahue, Jeff ;
Karayev, Sergey ;
Long, Jonathan ;
Girshick, Ross ;
Guadarrama, Sergio ;
Darrell, Trevor .
PROCEEDINGS OF THE 2014 ACM CONFERENCE ON MULTIMEDIA (MM'14), 2014, :675-678