Skip to content
naulon

Not checkedNot checked for notices yet.

Methods, hardware and software for monitoring crops condition on early stages of vegetation

I. V. Voronkov

Сельскохозяйственные машины и технологии · 2017

doi:10.22314/2073-7599-2017-5-33-37 (opens in a new tab)

We email you when a new notice or a question about this paper appears.

Abstract

Lately, in addition to traditional methods of screening or selective crops inspection, instrumental means of monitoring, namely installed on unmanned aerial vehicles (UAV) video and photo-cameras, started to be implemented. The main advantage of conducting monitoring via UAV is that it does not mechanically affects plants and maintains high productivity during the surveying. However, during screening inspection of large crops areas (tens of thousands of hectars), especially on the early stages of vegetation, a problem of receiving the surveying analysis results promptly emerges. To solve this problem it is necessary to develop automated methods of identification and geo-referencing of the problematic zones. To count the amount of shoots and measure distance between them it is necessary to use the methods of images recognition based on the plants’ spectral characteristics analysis. The methodology of plants signals selection is based on the comparison of measured values with specified values; after that compilation of series using algorithm of approximation of slopes. Basing on the gathered information, statistical indicators characterizing the qualities of completion of the work were estimated. Experimental researches of the hardware and software methodology development were conducted using maize crops in the Krasnodar Territory. Comparative assessment of the measurement in manual and automatic regime using the developed software for shoots recognition and counting was conducted. The results difference equals 3-5 percent.

Abstract licence: CC BY

Reads

Read by people on this page

None yet.

Checked or read by AI through naulon

None yet.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.

Are you an author?

Is this your paper?

Claim it to add your note and be paid when agents cite it. Free.