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

Abstract

This paper approaches the problem of weed mapping for precision agriculture, using imagery provided by Unmanned Aerial Vehicles (UAVs) from sun ower and maize crops. Precision agriculture referred to weed control is mainly based on the design of early post-emergence site-speci c control treatments according to weed coverage, where one of the most important challenges is the spectral similarity of crop and weed pixels in early growth stages. Our work tackles this problem in the context of object-based image analysis (OBIA) by means of supervised machine learning methods combined with pattern and feature selection techniques, devising a strategy for alleviating the user intervention in the system while not compromising the accuracy. This work rstly proposes a method for choosing a set of training patterns via clustering techniques so as to consider a representative set of the whole eld data spectrum for the classi cation method. Furthermore, a feature selection method is used to obtain the best discriminating features from a set of several statistics and measures of di erent nature. Results from this research show that the proposed method for pattern selection is suitable and leads to the construction of robust sets of data. The exploitation of di erent statistical, spatial and texture metrics represents a new avenue with huge potential for between and within crop-row weed mapping via UAV-imagery and shows good synergy when complemented with OBIA. Finally, there are some measures (specially those linked to vegetation indexes) that are of great in uence for weed mapping in both sun ower and maize crops