A computer vision approach for weeds identification through Support Vector Machines

Abstract

Keywords: Support Vector Machines Machine vision Weed identification Image segmentation Decision makingThis paper outlines an automatic computer vision system for the identification of avena sterilis which is a special weed seed growing in cereal crops. The final goal is to reduce the quantity of herbicide to be sprayed as an important and necessary step for precision agriculture. So, only areas where the presence of weeds is important should be sprayed. The main problems for the identification of this kind of weed are its similar spectral signature with respect the crops and also its irregular distribution in the field. It has been designed a new strategy involving two processes: image segmentation and decision making. The image segmentation combines basic suitable image processing techniques in order to extract cells from the image as the low level units. Each cell is described by two area-based attributes measuring the relations among the crops and weeds. The decision making is based on the Support Vector Machines and determines if a cell must be sprayed. The main findings of this paper are reflected in the combination of the segmentation and the Support Vector Machines decision processes. Another important contribution of this approach is the minimum requirements of the system in terms of memory and computation power if compared with other previous works. The performance of the method is illustrated by comparative analysis against some existing strategies.

Selecting patterns and features for between- and within- crop-row weed mapping using UAV-imagery

“…In steps 3 and 4, black coloured pixels represent non-vegetation, white ones represent crop, and grey ones correspond to weed. machine learning methods and has been used for a wide range of applications concerning remote sensing (Mountrakis et al, 2011;Tellaeche et al, 2011).…”

“…In this sense, this paper studies the use of supervised machine learning methods for constructing a model for weed identification. This is one of the main novelties of this paper, because machine learning methods have been mostly used with the purpose of remote vegetation mapping in 55 on-ground studies (Tellaeche et al, 2011;Burgos-Artizzu et al, 2011) or using piloted platforms but have uniquely been used with UAV-imagery in two preliminary works which showed the great potential of these techniques (Hung et al, 2014;Pérez-Ortiz et al, 2015b). Our present work considers these previous results and tries to deal with some of the problems that have been identified 60 when using object-based image analysis (Blaschke, 2010) (OBIA), a strategy that have shown better performance than the pixel-based approach in preliminary results (Pérez-Ortiz et al, 2015b).…”

Targeted and Microdose Chemical Applications

“…Precision application of weed control treatments requires sensitive technology that can track, record, and compute information on leaf shape, color, surface, and edge features for separating a weed and a crop plant (Hearn 2009;Meyer et al 1998;Lati et al 2011;Slaughter et al 2008b;Tang et al 2003;Tellaeche et al 2011). The technology is still emerging and has a few challenges, including oc-cluded leaves, misshapen leaves, moving leaves, and dusty leaves (see Chapter 15).…”

Automatic expert system based on images for accuracy crop row detection in maize fields

“…It is required to determine the threshold required by the Hough transform to determine maximum peaks values (Jones, Gée, & Truchetet, 2009a, 2009b or predominant peaks (Rovira-Más, Zhang, Reid, & Will, 2005). Depending on the crop densities several lines could be feasible and a posterior merging process is applied to lines with similar parameters Tellaeche et al, 2011). Although intended for real-time, as mentioned before, in our images, where crop and weed plants contribute on the Hough parameter estimation, this method becomes computationally expensive (Ji, & Qi, 2011).…”