首页> 外国专利> Devices and methods for identifying crops and weeds by learning neural networks

Devices and methods for identifying crops and weeds by learning neural networks

机译:通过学习神经网络识别农作物和杂草的设备和方法

摘要

The present invention relates to a technique for distinguishing between crops and weeds, which comprises the steps of: recognizing all plants between rows as weeds by recognizing a row of crops using a convolutional encoder-decoder (CED) neural network learning technique; and distinguishing weeds from crops by using an additional CED neural network with respect to a small number of weeds present on a crop row.
机译:本发明涉及一种区分作物和杂草的技术,该技术包括以下步骤:通过使用卷积编码器-解码器(CED)神经网络学习技术识别一行作物,将行之间的所有植物识别为杂草。通过针对作物行中存在的少量杂草使用附加的CED神经网络,将杂草与农作物区分开。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

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