Rice yield estimation method based on unmanned aerial vehicle digital images

Abstract

The invention discloses a rice yield estimation method based on unmanned aerial vehicle digital images. The rice yield estimation method mainly comprises the following steps of: designing a test plot;photographing canopy images of rice in the test plot by means of a high-definition digital camera carried by an unmanned aerial vehicle; analyzing recognition capability of each channel or index of RGB and HSV color spaces on rice spikes by applying an optimal subset selection algorithm; and extracting seven characteristic parameters suitable for northern japonica rice spike image segmentation, constructing a rice spike segmentation model based on a BP neural network, performing connected domain analysis on rice spike images to obtain a number of rice spikes, and finally substituting the number of the rice spikes into a yield estimation formula to estimate the rice yield. The rice yield estimation method provided by the invention can quickly and accurately obtain the digital images of therice canopy and precisely estimate the yield of the rice.

Description

technical field [0001] The invention relates to the field of UAV remote sensing application technology, in particular to a method for estimating rice yield based on UAV digital images. Background technique [0002] The traditional rice yield estimation method is mainly satellite remote sensing yield estimation, but the resolution of satellite remote sensing yield estimation is low, and the accuracy cannot be guaranteed in areas with complex terrain and diverse farming systems, especially when assisted breeding is applied; moreover, satellite remote sensing Most of the yield estimation models established for yield estimation are statistical models, which have large errors in different regions and different years, lack of mechanism, and cannot be further popularized and applied; secondly, there is a lack of rice remote sensing yield estimation system for actual production applications. [0003] UAV remote sensing is a low-altitude remote sensing technology, which is less distu...

AI Technical Summary

Problems solved by technology

[0002] The traditional rice yield estimation method is mainly satellite remote sensing yield estimation, but the resolution of satellite remote sensing yield estimation is low, and the accuracy cannot be guaranteed in areas with complex terrain and diverse farming systems, especially when assisted breeding is applied; moreover, satellite remote sensing Most of the production estimation models established for production estimation are statistical models, which have large errors in different regions and different years, lack of mechanism, and cannot be further popularized and applied; secondly, there is a lack of rice remote sensing production estimation system for actual production applications

Images