摘要
目前水环境监督管理基本靠视频监控和巡河员定期巡视,用技防+人防的方式发现违法事件逐级上报来解决。由于图像采集点不足,并且传统图像信息分析技术使用难度大,需要投入大量人员现场巡河,导致人员成本高、效率比较低。当前人工智能技术的发展已经进入实用化阶段,将其成果有效用于水务管理决策系统当中,成为当前水务信息化的热点技术之一。本文对人工智能的发展趋势和应用到水务信息化中需要考虑的技术和工程问题进行了技术探讨与工程验证。
At present,the supervision and management of water environment basically relies on video surveillance and regular inspections by river patrol officers and the illegal incidents are escalated by means of technical defense+personnel defense.Due to insufficient image collection points and the difficulty in using traditional image information analysis techniques,it is necessary to invest a large number of personnel on the scene,resulting in high personnel costs and low efficiency.At present,the development of artificial intelligence technology has entered the practical stage,and the effective use of its results in the water management decision-making system has become one of the hot technologies of water informatization.This paper has carried out technical discussion and engineering verification on the development trend of artificial intelligence and the technical and engineering problems that need to be considered in the application of water information.
作者
雷健
LEI Jian(Beijing Institute of Water Resources Automation,Beijing 100036,China)
出处
《价值工程》
2019年第22期215-219,共5页
Value Engineering
关键词
人工智能
卷积神经网络
水务人工智能平台
样本扩增
artificial intelligence
convolutional neural network
water artificial intelligence platform
sample amplification