基于物联网园林视觉监控方法研究与仿真  

Monitoring Method Based on Iot Garden Vision Research and Simulation

作　　者：匡珍春[1] 吴刘萍[2] 

机构地区：[1]广东海洋大学实验教学部计算中心,广东湛江524088 [2]广东海洋大学农学院,广东湛江524088

出　　处：《计算机仿真》2016年第4期447-450,共4页Computer Simulation

基　　金：国家自然科学基金青年科学基金(51208118)

摘　　要：针对传统算法不能克服恶劣天气带来的影响,导致监控准确性低的问题。提出采用基于物联网的园林视觉监控方法。利用物联网中视觉传感器采集园林中游客的行为图像,提取游客行为的轮廓图像,利对游客行为图像轮廓进行傅里叶变换变换,并将变换结果转化为符号序列,利用隐马氏模型分类器实现对游客行为的识别和分类,最终实现对园林的准确监控。仿真结果表明,改进算法相比传统识别方法,识别准确率提高,识别时间缩短。In view of the traditional algorithm cannot overcome the effects of bad weather, lead to monitor the problem of low accuracy. Landscape visual monitoring method based on Internet of things is presented in this paper. In the use of the Internet of things vision sensors to collect the botanical garden in the behavior of tourist image, extraction of the contours of the image, and tourist behavior of tourists behavior to Fourier transform image contour, and will transform the results into a symbol sequence, using hidden markov model classifier to tourists behavior identification and classification, finally realizes the accurate monitoring of the garden. The simulation experimental results show that the improved algorithm is compared with the traditional identification methods for the recognition accuracy rate increased, the recognition time shortened.

关 键 词：物联网 园林 视觉监控 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]