Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Yield Estimation Using Unmanned Aerial Vehicle Low-altitude Imaging for Dense Planting Cotton Field

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan

Citation:  2018 ASABE Annual International Meeting  1800777.(doi:10.13031/aim.201800777)
Authors:   Kunlin Zou, Ruoyu Zhang, Yinglan Jiang
Keywords:   cotton yield estimation; UAV imaging system; machine learning; dense planting

Abstract. Cotton yield estimation is very important for cotton production. This paper presents a method for estimating the yield with UAV imaging system in dense planting cotton field. First of all, in the cotton field defined a number of sample areas. Then the images of the sample areas were obtained by UAV imaging system, and cotton boll pixels were extracted from the image by a machine learning algorithm and the cotton unit coverage (CUC) rate was calculated. All cotton balls in the sampling area were collected, and the cotton yield was calculated. The relationship between cotton unit coverage and cotton yield of each sample areas was explored, and a regression model of cotton unit coverage and cotton yield was obtained. Cotton yield was calculated based on this model. Our research team used this method to estimate the yield of a dense planting cotton field. The accuracy of estimating yield was 89.13%,and the efficiency of estimating was 133.33 m2 / min. The experimental results indicate that this method is suitable for cotton yield estimation.

(Download PDF)    (Export to EndNotes)