Automatic detection of curved and straight crop rows from images in maize fields. (April 2017)

• Record Type: Journal Article
• Authors: García-Santillán, Iván D.; Montalvo, Martín; Guerrero, José M.; Pajares, Gonzalo
• Is Part Of: Biosystems engineering. Volume 156(2017)
• Page Start: 61
• Page End: 79
• Publication Date: 2017-04
• Subjects: Automatic guidance -- Crop row detection -- Image segmentation -- Machine vision -- Hough transform; Bioengineering -- Periodicals; Agricultural engineering -- Periodicals; Biological systems -- Periodicals; Génie rural -- Périodiques; Systèmes biologiques -- Périodiques; 631
• DOI: 10.1016/j.biosystemseng.2017.01.013
• Languages: English
• ISSNs: 1537-5110

Abstract

Abstract : A new method for detecting curved and straight crop rows in images captured in maize fields during the initial growth stages of crop and weed plants is proposed. The images were obtained under perspective projection with a camera installed on board and conveniently arranged at the front part of a tractor. The final goal is the identification of the crop rows with two purposes: a) precise autonomous guidance; b) site-specific treatments, including weed removal, where weeds are identified as plants outside the crop rows. Image quality is affected by uncontrolled lighting conditions in outdoor agricultural environments and gaps along the crop rows due to lack of germination or defects during planting. Also, different crop and weed plant heights and volumes appear at different growth stages affecting the crop row detection process. The proposed method was designed with the required robustness to cope with the above situations and consists of three linked phases: (i) image segmentation, (ii) identification of starting points for determining the beginning of the crop rows and (iii) crop rows detection. The main contribution of the method is the ability to detect curved and straight crop rows having regular or irregular inter-row spacing, even when both row types coexist in the same field and image. The performance of the proposed approach was quantitatively compared against six existing strategies, achieving accuracies between 86.3% and 92.8%, depending on whether crop rows were straight/curved with regular or irregular spacing, with processing times less than 0.64 s per image. Highlights: New methodology for detecting curved and straight rows of early stage maize crop. Accuracies between 86.3% and 92.8% for straight and curved crop rows. Identification of crop rows with regular and irregular inter-crop row spacing. Method works under sunny, cloudy and partly cloudy daylight conditions. Tests performed with plants heights [100–300 mm], weed pressures and gaps (≤1.20 m).