期刊文献+

智能跟踪算法在采砂监管中的应用研究 被引量:7

Application prospect of smart tracking algorithm on sand mining supervision
下载PDF
导出
摘要 受利益的驱动,长江流域非法采砂行为屡禁不止,给采砂有效监管造成很大的困扰。采砂监管水平的提高需要高效准确的跟踪识别技术作支撑。提出了一种基于相关滤波器的可变跟踪框智能算法。该算法可以准确快速地跟踪江河湖面上的非法采砂船,计算量少,鲁棒性高,对硬件的要求并不严苛,可以自由应用于从低性能到高性能的各种设备。基于该算法开发了非法采砂船追踪器,再配合百度深度学习平台Easy DL后,可构成一套采砂船监控系统,能够实现对长江水域非法采砂船24 h的有效监控,从而大大提高监控非法采砂行为的效率。 Driven by the interests, the illegal sand mining in the Yangtze River Basin still happens frequently even after repeatedly banning, which has caused great troubles for the effective supervision of sand mining. In this paper, a variable tracking frame intelligent algorithm based on correlation filter is proposed, which can accurately and quickly track illegal sand mining vessels on the river. The algorithm has low computational quantity, high robustness, and without much requirement on the hardware. It can be freely applied to various hardware ranging from low performance to high performance. Based on the algorithm, the illegal sand mining ship tracker can be combined with the Baidu deep learning platform Easy DL to form a sand mining ship monitoring system, which can effectively monitor the illegal sand mining ship in the Yangtze River for 24 hours, thus greatly improving the illegal behaviour monitoring. Based on this system, the efficiency of sand mining is improved and labor costs are saved.
作者 颜智博 夏细禾 YAN Zhibo;XIA Xihe(Beijing University of Posts and Telecommunications, Beijing 100876,China;Supervising Bureau on Sand Mining, Changjiang Water Resources Commission, Wuhan 430010, China)
出处 《人民长江》 北大核心 2019年第6期6-10,共5页 Yangtze River
关键词 人工智能 智能跟踪算法 EASY DL平台 采砂船实时监控 artificial intelligence smart tracking algorithm Easy DL sand mining vessel supervision
  • 相关文献

参考文献14

二级参考文献58

共引文献27

同被引文献82

引证文献7

二级引证文献18

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部