Automatic detection and evaluation of sugarcane planting rows in aerial images

Abstract

Sugarcane planting is an important and growing activity in Brazil. Thereupon, several techniques have been developed over the years to maximize crop productivity and profit, amongst them, processing of sugarcane field images. In this sense, this research aims to identify and analyze crop rows and measure their gaps from aerial images of sugarcane fields. For this, a small Remotely Piloted Aircraft captured the images, generating orthomosaics of the areas for analysis. Then, each orthomosaic is classified with the K-Nearest Neighbor algorithm to segment regions of interest. Planting row orientation is estimated using the RGB gradient filter. Morphological operations and computational geometry models are then used to detect and map rows and gaps along the planting row segment. To evaluate the results, crop rows are mapped and compared to manually taken measurements. Our technique obtained an error smaller than 2% when compared to gap length in crop rows from an orthomosaic with the area of 8.05 ha (ha). The proposed approach can map the positioning of the automatically generated row segments appropriately onto manually created segments. Moreover, our method also achieved similar results when confronted with a manual technique for differing growth stages (40 and 80 days after harvest) of the sugarcane crop. The proposed method presents a great potential to be adopted in sugarcane planting monitoring.