农田活害虫动态特征提取系统

2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC) Pub Date : 2018-05-01 DOI:10.1109/YAC.2018.8406543

Qian Jing, Nie Yu-man, Wang Yong-ping, Cao Ping-guo, Lei Jian-he, Song Quan-jun

{"title":"农田活害虫动态特征提取系统","authors":"Qian Jing, Nie Yu-man, Wang Yong-ping, Cao Ping-guo, Lei Jian-he, Song Quan-jun","doi":"10.1109/YAC.2018.8406543","DOIUrl":null,"url":null,"abstract":"Monitoring of farmland pests is an important prerequisite to sprinkle agriculture in a timely and appropriate manner, which provide an important guarantee for agricultural production. This paper presents a method for obtaining the dynamic characteristics of pests in farmland based on machine vision. First, the pests and the background images are segmented by color feature and thresholding methods. Then, the shape features and the number of pests were obtained by Gaussian filtering. Finally, the quantity of pest motion is obtained by frame-to-frame differencing method. The experimental results show that the accuracy rate of the experimental sample is 99%. It can provide quantitative information of pest activity for plant protection personnel. This system can also be applied in large-scale crop pest monitoring.","PeriodicalId":226586,"journal":{"name":"2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Dynamic features extraction system of live pests in farmland\",\"authors\":\"Qian Jing, Nie Yu-man, Wang Yong-ping, Cao Ping-guo, Lei Jian-he, Song Quan-jun\",\"doi\":\"10.1109/YAC.2018.8406543\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Monitoring of farmland pests is an important prerequisite to sprinkle agriculture in a timely and appropriate manner, which provide an important guarantee for agricultural production. This paper presents a method for obtaining the dynamic characteristics of pests in farmland based on machine vision. First, the pests and the background images are segmented by color feature and thresholding methods. Then, the shape features and the number of pests were obtained by Gaussian filtering. Finally, the quantity of pest motion is obtained by frame-to-frame differencing method. The experimental results show that the accuracy rate of the experimental sample is 99%. It can provide quantitative information of pest activity for plant protection personnel. This system can also be applied in large-scale crop pest monitoring.\",\"PeriodicalId\":226586,\"journal\":{\"name\":\"2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/YAC.2018.8406543\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/YAC.2018.8406543","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

农田有害生物监测是及时、适当地进行洒水农业的重要前提，为农业生产提供了重要保障。提出了一种基于机器视觉的农田害虫动态特征获取方法。首先，采用颜色特征和阈值分割方法对害虫和背景图像进行分割;然后，通过高斯滤波得到害虫的形状特征和数量;最后，采用逐帧差分法得到害虫的运动量。实验结果表明，实验样本的准确率为99%。可为植保人员提供害虫活动的定量信息。该系统也可用于大规模的作物有害生物监测。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Dynamic features extraction system of live pests in farmland

Monitoring of farmland pests is an important prerequisite to sprinkle agriculture in a timely and appropriate manner, which provide an important guarantee for agricultural production. This paper presents a method for obtaining the dynamic characteristics of pests in farmland based on machine vision. First, the pests and the background images are segmented by color feature and thresholding methods. Then, the shape features and the number of pests were obtained by Gaussian filtering. Finally, the quantity of pest motion is obtained by frame-to-frame differencing method. The experimental results show that the accuracy rate of the experimental sample is 99%. It can provide quantitative information of pest activity for plant protection personnel. This system can also be applied in large-scale crop pest monitoring.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2018 33rd Youth Academic Annual Conference of Chinese Association of Automation (YAC)

自引率

0.00%

发文量