Estimating maize canopy cover percent by means of image processing algorithms

The progress of science and using remote sensing technologies could help farmers to finds valuable information from field such as crop health, determining of the area and type of cultivation, calculating crop growth rate and various indices. Canopy cover percent is one of the vital parameters for modeling and prediction of yield production. Field observation methods of estimating CCP are expensive and time consuming. Using drones for arial imaging at field scale and image processing algorism to estimate CCP are fast and accurate. At this study, 441 arial photos was taken at height of 30 m above ground surface via DJI drone (Mavic 2 pro) for estimating maize CCP. The field was located at Alvand city-Qazvin province. Two different methods of segmentation and classification were used for assessing CCP. Region of interest separability test and linear regression between calculated data were used for result evaluation. Results showed that, although the accuracy of both methods was high, on average the segmentation methods obtained CCP 10 percent lower that classification algorism. Also, the high R-square coefficient of 97% between the data showed that the accuracy of methods based on image processing, such as segmentation, is lower than classification methods, but in case of lack of access to the required software, that are based on artificial intelligence methods, it is easy to achieve a favorable result by implementing programming codes based on segmentation methods in high-level and open-source languages, including Python.