An Automatic Random Forest-OBIA Algorithm for Early Weed Mapping between and within Crop Rows Using UAV Imagery

被引:203
作者
de Castro, Ana I. [1 ]
Torres-Sanchez, Jorge [1 ]
Pena, Jose M. [2 ]
Jimenez-Brenes, Francisco M. [1 ]
Csillik, Ovidiu [3 ]
Lopez-Granados, Francisca [1 ]
机构
[1] CSIC, IAS, Dept Crop Protect, Cordoba 14004, Spain
[2] CSIC, Inst Agr Sci ICA, Dept Plant Protect, Madrid 28006, Spain
[3] Univ Salzburg, Dept Geoinformat Z GIS, A-5020 Salzburg, Austria
基金
奥地利科学基金会;
关键词
Digital Surface Model; segmentation; precision agriculture; in-season post-emergence site-specific weed control; plant height; UNMANNED AERIAL VEHICLE; LAND-COVER CLASSIFICATION; CRITICAL PERIOD; MANAGEMENT; THRESHOLD; MODELS; TIME; DISCRIMINATION; TECHNOLOGY; FEATURES;
D O I
10.3390/rs10020285
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Accurate and timely detection of weeds between and within crop rows in the early growth stage is considered one of the main challenges in site-specific weed management (SSWM). In this context, a robust and innovative automatic object-based image analysis (OBIA) algorithm was developed on Unmanned Aerial Vehicle (UAV) images to design early post-emergence prescription maps. This novel algorithm makes the major contribution. The OBIA algorithm combined Digital Surface Models (DSMs), orthomosaics and machine learning techniques (Random Forest, RF). OBIA-based plant heights were accurately estimated and used as a feature in the automatic sample selection by the RF classifier; this was the second research contribution. RF randomly selected a class balanced training set, obtained the optimum features values and classified the image, requiring no manual training, making this procedure time-efficient and more accurate, since it removes errors due to a subjective manual task. The ability to discriminate weeds was significantly affected by the imagery spatial resolution and weed density, making the use of higher spatial resolution images more suitable. Finally, prescription maps for in-season post-emergence SSWM were created based on the weed mapsthe third research contributionwhich could help farmers in decision-making to optimize crop management by rationalization of the herbicide application. The short time involved in the process (image capture and analysis) would allow timely weed control during critical periods, crucial for preventing yield loss.
引用
收藏
页数:21
相关论文
共 66 条
[1]  
AESA, AER WORK LEG FRAM
[2]   Weed discrimination using ultrasonic sensors [J].
Andujar, D. ;
Escola, A. ;
Dorado, J. ;
Fernandez-Quintanilla, C. .
WEED RESEARCH, 2011, 51 (06) :543-547
[3]  
Baatz M., 2000, Multiresolution Segmentation: an optimization approach for high quality multi-scale image segmentation, DOI DOI 10.1016/J.ISPRSJPRS.2003.10.002
[4]  
Barragan J., 2012, Proceedings of the 4th GEOBIA, P426
[5]  
Barreda J., 2009, THESIS
[6]   Random forest in remote sensing: A review of applications and future directions [J].
Belgiu, Mariana ;
Dragut, Lucian .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2016, 114 :24-31
[7]   Estimating Biomass of Barley Using Crop Surface Models (CSMs) Derived from UAV-Based RGB Imaging [J].
Bendig, Juliane ;
Bolten, Andreas ;
Bennertz, Simon ;
Broscheit, Janis ;
Eichfuss, Silas ;
Bareth, Georg .
REMOTE SENSING, 2014, 6 (11) :10395-10412
[8]   Geographic Object-Based Image Analysis - Towards a new paradigm [J].
Blaschke, Thomas ;
Hay, Geoffrey J. ;
Kelly, Maggi ;
Lang, Stefan ;
Hofmann, Peter ;
Addink, Elisabeth ;
Feitosa, Raul Queiroz ;
van der Meer, Freek ;
van der Werff, Harald ;
van Coillie, Frieke ;
Tiede, Dirk .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2014, 87 :180-191
[9]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[10]   Assessing the potential of images from unmanned aerial vehicles (UAV) to support herbicide patch spraying in maize [J].
Castaldi, F. ;
Pelosi, F. ;
Pascucci, S. ;
Casa, R. .
PRECISION AGRICULTURE, 2017, 18 (01) :76-94