摘要
为解决洱海湿地隐蔽性昆虫识别与监测问题,借助物联网技术,基于多特征昆虫识别算法设计了一种智能昆虫识别与实时监测系统。该系统通过红外对射、超声波、声音、颜色和图像等传感器采集昆虫特征信息,在单片机控制下,通过网络将特征数据传输至云服务器,再经过生命、声音和颜色等多特征数据分析,从而实现智能识别。性能测试表明:与图像边缘监测、相关反馈法相比,在时间和空间复杂度上具有一定优越性,该方法是可行的。
In order to identify and monitor the hidden insects in the Erhai wetland, this paper, with the help of the Internet designed an intelligent insect recognition and real-time monitoring system based on the multifeature insect recognition algorithm. The inforInation of insect characteristics was collected by infrared radiation sensors, ultrasonic sensors, sound sensors, color sensors and image sensors. Under the control of the single chip computer, the characteristic data was transmitted to the cloud server through the network. Then the intelligent recognition was realized by analyzing the characteristics such as life, sound and color. Performance tests show that: compared with image edge detection and correlation feedback method, it has some advantages in time and space complexity, and the method is feasible.
作者
罗桂兰
杨自忠
张梅
吴仕龙
张倩
安东
Luo Guilan;Yang Zizhong;Zhang Mei;Wu Shilong;Zhang Qian;An Dong(College of Mathematics and Computer,Dali University,Dali,Yunnan 671003,China;Institute of Insect Biological and Pharmaceutical Development,Dali University,Dali,Yunnan 671003,China)
出处
《大理大学学报》
CAS
2018年第6期6-12,共7页
Journal of Dali University
基金
国家自然科学基金资助项目(61661001)
云南省教育厅科学研究基金资助项目(2017ZDX018)
云南省大学生创新创业训练计划项目(S-CXCY-2017-28)
关键词
物联网
湿地昆虫
智能识别
实时监测
多特征提取
internet of things
wetland insects
intelligent recognition
real-time monitoring
multi-feature extraction