• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International conference on artificial intelligence >Insects detection in maize by endoscopic video analysis
【24h】

Insects detection in maize by endoscopic video analysis

机译：内窥镜视频分析技术检测玉米中的昆虫

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Insects cause significant quantity and quality losses in stored grains. Producers are recommended to avoid excessive use of insecticides because they are harmful to living beings that consume the grains. Thus, it is of vital importance to early identify insects in grains to take control measures. Insects identification is usually done by collecting samples of grains from warehouses, followed by visual or laboratory analysis. However, this is a difficult and costly process. We propose to carry out this identification task automatically, using computational methods to perform endoscopic video analysis. The videos are recorded inside of grains warehouses by a endoscopic camera. As the classification process of moving objects in video depends fundamentally on precise segmentation of moving objets, we propose a new method of background subtraction and compared their results with the main methods of the literature according to a recent review. Experimental results show that the proposed method achieve more accurate results than state of art methods.
机译：昆虫在储存的谷物中造成大量的数量和质量损失。建议生产者避免过度使用杀虫剂，因为它们对食用谷物的生物有害。因此，早期发现谷物中的昆虫以采取控制措施至关重要。昆虫鉴定通常是通过从仓库收集谷物样品，然后进行目视或实验室分析来完成的。但是，这是一个困难且昂贵的过程。我们建议使用计算方法自动执行此识别任务，以执行内窥镜视频分析。这些视频通过内窥镜摄像机记录在谷物仓库内。由于视频中运动物体的分类过程从根本上取决于运动物体的精确分割，因此，我们提出了一种新的背景减影方法，并将其结果与文献中的主要方法进行了比较。实验结果表明，所提出的方法比现有方法具有更准确的结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号