帮助 关于我们

返回检索结果

Fish Density Estimation with Multi-Scale Context Enhanced Convolutional Neural Network

查看参考文献21篇

Zhou Yizhi 1,2   Yu Hong 1,2   Wu Junfeng 1,2 *   Cui Zhen 1   Pang Hongshuai 1   Zhang Fangyan 1  
文摘 With the development of fishery industry, accurate estimation of the number of fish in aquaculture waters is of great importance to fish behavior analysis, bait feeding and fishery resource investigation. In this paper, we propose a method for fish density estimation based on the multi-scale context enhanced convolutional network, which could map a fish school image taken at any angle to a density map, and calculate the number of fish in the image finally. In order to eliminate the influence of camera perspective effect and image resolution on density estimation, multi-scale filters are utilized in a convolutional neural network to process fish image in parallel. And then, the context enhancement module is merged in the network structure to help the network understand the global context information of the image. Finally, different feature maps are merged together to construct the density map of fish school images, and finally get the number of fish in the image. In order to make the effectiveness of our method valid, we test the proposed method on DlouDataset. The results show that the proposed method has lower mean square error and mean absolute error, which is helpful to improve the accuracy of the fish counting in dense fish school images.
来源 Journal of Communications and Information Networks ,2019,4(3):80-88 【核心库】
DOI 10.23919/JCIN.2019.8917888
关键词 fish counting ; density estimation ; neural network ; context enhancement module
地址

1. College of Information Engineering, Dalian Ocean University, Dalian, 116023  

2. Key Laboratory of Facility Fisheries, Ministry of Education, Key Laboratory of Facility Fisheries, Ministry of Education, Dalian, 116023

语种 英文
文献类型 研究性论文
ISSN 2096-1081
学科 电子技术、通信技术
基金 中国博士后科学基金 ;  国家自然科学基金 ;  supported by Institute of Marine Industry Technology of Universities in Liaoning Province
文献收藏号 CSCD:6588954

参考文献 共 21 共2页

1.  Feng C F. Application of fish behavior research in fishing. Journal of Dalian Ocean University,2009,24(2):166-170 被引 1 次    
2.  Yang T T. Green energy and content aware data transmission in maritime wireless communication network. IEEE Transactions on Intelligent Transportation System,2015,16(2):751-762 被引 4 次    
3.  Lin J Q. Marine fishery resources in China (ii). Ocean Science,1991,15(2):33-35 被引 1 次    
4.  Xu S. Application of computer vision in aquaculture and production. Journal of Tianjin Agricultural University,2014,21(4):43-46 被引 1 次    
5.  Cao Y. General distributed hash learning on image descriptors for k-Nearest neighbor search. IEEE Signal Processing Letters,2019,26(5):750-754 被引 1 次    
6.  Taparhudee W. Counting fish fry using digital image processing. Proceedings of the 50th Kasetsart University Annual Conference,2012:368-374 被引 1 次    
7.  Lu H D. Design and implementation of fish behavior automatic monitoring system based on computer vision. Modernization of Fisheries,2011,38(1):19-23 被引 1 次    
8.  Joseph R. YOLOv3: An Incremental Improvement. arXiv:1804.02767 被引 1 次    
9.  Xiao G. Research of the fish tracking method with occlusion based on monocular stereo visions. International Conference on Information System and Artificial Intelligence,2016:581-589 被引 1 次    
10.  Sindagi V A. Generating high-quality crowd density maps using contextual pyramid CNNs. Proceedings of the IEEE International Conference on Computer Vision 2017,2017:1861-1870 被引 1 次    
11.  Yang T T. Efficient scheduling for video transmission in maritime wireless communication network. IEEE Transactions on Vehicular Technology,2015,64(9):4215-4229 被引 2 次    
12.  Zhang Y Y. Single-image crowd counting via multi-column convolutional ceural network. 2016 IEEE Conference on Computer Vision and Pattern Recognition,2016:589-597 被引 5 次    
13.  Babu S D. Switching convolutional neural network for crowd counting. 2017 IEEE Conference on Computer Vision and Pattern Recognition,2017:4031-4039 被引 1 次    
14.  Wang S. Study on fishery modernization of turbot fry count method based on computer vision. Fishery Modernization,2015,42(1):16-19 被引 1 次    
15.  Huang L. Method of fish fry counting based on image processing. Hubei Agricultural Science,2012,51(9):1880-1882 被引 1 次    
16.  Guo J. Counting algorithm based on machine vision tracking. Sensor and Microsystems,2018,37(2):154-157 被引 1 次    
17.  Wang W J. Research on automatic counting system of fish fry based on computer vision. Modernization of Fishery,2016,43(3):34-38 被引 1 次    
18.  Zheng Q. ThunderNet: Towards real-time generic object detection. arXiv:1903.11752 被引 1 次    
19.  Hinton G E. A practical guide to training restricted boltzmann machines. Neural Networks: Tricks of The Trade,2012:599-619 被引 20 次    
20.  Min L. Network in Network. Computer Science,2013:1312.4400 被引 1 次    
引证文献 2 篇

1 于红 水产动物目标探测与追踪技术及应用研究进展 大连海洋大学学报,2020,35(6):793-804
被引 12 次

2 张涵钰 基于机器视觉的水产养殖计数研究综述 计算机应用,2023,43(9):2970-2982
被引 1 次

显示所有2篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号