Fast Classification and Detection of Marine Targets in Complex Scenes with YOLOv3

被引：3
作者：
Shi, Tingchao [1 ]
Liu, Mingyong [1 ]
Yang, Yang [1 ]
Li, Sainan [1 ]
Wang, Peixin [1 ]
Huang, Yuxuan [1 ]
机构：
[1] Northwestern Polytech Univ, Sch Marine Engn, Xian 710072, Peoples R China
来源：
OCEANS 2019 - MARSEILLE | 2019年
基金：
中国国家自然科学基金;
关键词：
YOLOv3; Classification; Detection; Marine Targets;
D O I：
10.1109/oceanse.2019.8867137
中图分类号：
U6 [水路运输]; P75 [海洋工程];
学科分类号：
0814 ; 081505 ; 0824 ; 082401 ;
摘要：
In order to meet the needs of fast detection and classification of different marine targets during intelligent unmanned surface vehicle (USV) operations, In this paper, I introduce a convolutional neural network based on one of the most effective object detection algorithms, named YOLOv3, to classify and detect images of different marine targets. Firstly, I showed the network structure of the algorithm in this paper. Then, I explained how I got the optimal anchor box parameter of the algorithm. Finally, I improved the activation function to make the algorithm more robust to noise. The final results show that the MAP of the detector in this paper is 91.83%,and we reach a detection rate of 58.3 fps by improving the YOLOV3 algorithm.
引用
收藏
页数：5
相关论文
共 12 条
[1]  
Clevert D.-A., 2016, 4 INT C LEARN REPR I
[2]   Underwater cable detection in the images using edge classification based on texture information [J].
Fatan, Mehdi ;
Daliri, Mohammad Reza ;
Shahri, Alireza Mohammad .
MEASUREMENT, 2016, 91 :309-317
[3]  
Girshick R, 2015, IEEE INT C COMP VIS
[4]  
Girshick R., 2014, IEEE COMP SOC C COMP, DOI [10.1109/CVPR.2014.81, DOI 10.1109/CVPR.2014.81]
[5]  
He K, 2017, IEEE INT C COMP VIS
[6]  
Li X., 2016, OCEANS 2016 SHANGHAI
[7]   Deep Residual Networks for Plankton Classification [J].
Li, Xiu ;
Cui, Zuoying .
OCEANS 2016 MTS/IEEE MONTEREY, 2016,
[8]  
Page L, 1999, PAGEANK CITATION ANK
[9]  
REDMON J, 2016, PROC CVPR IEEE, P779, DOI [DOI 10.1109/CVPR.2016.91, 10.1109/CVPR.2016.91]
[10]  
Redmon J, 2018, Arxiv, DOI arXiv:1804.02767
12