Colour and shape analysis techniques for weed detection in cereal fields

Pérez, Amelia; López, Fernando; Benlloch, J.; Christensen, Svend

doi:10.1016/s0168-1699(99)00068-x

Cited by 332 publications

(149 citation statements)

References 10 publications

Supporting

Mentioning

142

Contrasting

Unclassified

Order By: Relevance

“…The results shown so far are based on a VI that is calculated in a similar manner as the NDVI but using information from the blue and green spectral range. Visible light VIs, such as the NGRDI, are often used to characterize vegetation if NIR information is lacking (Pérez et al 2000; Meyer and Neto 2008; Raymond et al 2005). Due to their low costs and low weight, consumer-grade true colour (RGB) digital cameras are particularly suitable for assessing green vegetation using UAS-based imaging systems (Torres-Sánchez et al 2014; Saberioon et al 2014; Hoffmann et al 2016a; Goodbody et al 2017; Jannoura et al 2015).…”

Section: Resultsmentioning

confidence: 99%

“…Thereto, two VIs were derived from the RGB orthomosaics. First, the Normalized Green-Red Difference Index (NGRDI) given in Equation (1) expresses the difference between the green and red bands divided by their sum (Pérez et al 2000). At our study site, the discrimination between living green and dried dead vegetation, which was used for the determination of the fraction of green vegetation ( f g ) in the TSEB model, was important since f g was very heterogeneous over the field and changed in between flights because farmers were mowing the fields.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Estimation of evapotranspiration of temperate grassland based on high-resolution thermal and visible range imagery from unmanned aerial systems

Brenner

Zeeman

Bernhardt

et al. 2018

International Journal of Remote Sensing

View full text Add to dashboard Cite

Spatially distributed high-resolution data of land surface temperature (LST) and evapotranspiration (ET) are important information for crop water management and other applications in the agricultural sector. While satellite data can provide LST high-resolution data of 100 m, the current development of unmanned aerial systems (UAS) and affordable low-weight thermal cameras allows LST and subsequent ET to be derived at resolutions down to centimetre scale.In this study, UAS-based images in the thermal infrared (TIR) and visible spectral range were collected over a managed temperate grassland in July 2016 at the Terrestrial Environmental Observatories Networks TERENO preAlpine observatory site at Fendt, Germany. The UAS set-up included a lightweight thermal camera (Optris Pi Lightweight) and a regular digital camera (Sony α 6000) that allowed for the acquisition of thermal and optical images with a ground resolution of 5 cm and 1 cm, respectively. Three TIR-based ET models of different complexity were applied and the resulting ET estimates were compared to the Eddy covariance (EC) observations of turbulent energy fluxes and also to the evaporative fraction. While the Deriving Atmosphere Turbulent Transport Useful To Dummies Using Temperature (DATTUTDUT) model and the Triangle Method belong to the group of simpler contextual models, the Two-Source Energy Balance (TSEB) model incorporates a more physically based formulation of the surface energy balance. In addition to the comparison of UAS-based estimates of latent heat fluxes to EC observations, the effect of the spatial resolution of the model imagery input on the modelled results was analysed by running the models with imagery from the native resolution of the acquired images to resolutions that were aggregated up to 30 m.The results show that both contextual models are sensitive to the input image resolution and that the agreement with the EC observations improves with increasing image resolution. The TSEB model assumes that LST pixels represent a mixed signal of the soil and canopy components, thus an image resolution coarse enough to ensure this assumption should be chosen. However, with the exception of the native image resolution of 5 cm, we found no effect of image resolution on the spatially weighted mean TSEB estimates.For the studied grassland, the comparison of model estimates with EC observations indicates that all three models are able to reproduce observed energy fluxes with comparable accuracy with mean absolute errors of ET between 20 and 40 W m−2. The TSEB model showed larger deviations from the reference observations under cloudy conditions with rapid fluctuations of LST within the 30 min averaging period for EC. The two contextual models yielded similar results for most of the flights. The good performance of the DATTUTDUT model, which had the lowest input requirements of the three models, is especially promising in view of the application of UAS for routine near-real-time ET monitoring.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Estimation of evapotranspiration of temperate grassland based on high-resolution thermal and visible range imagery from unmanned aerial systems

Brenner

Zeeman

Bernhardt

et al. 2018

International Journal of Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Machine vision is successfully used to recognize weeds from soil with the goal of eliminating weeds between the rows or between widely spaced individual crop plants (Perez et al, 2000;Tillett et al, 2001;Onyango and Marchant, 2003), but it is still a difficult task to recognize weeds within the rows, particularly in the case of carrots. Indeed carrots are densely sown, they do not follow a regular sowing pattern and present high variability in size and shape due to different development stages.…”

Section: Introductionmentioning

confidence: 99%

Selection of the most efficient wavelength bands for discriminating weeds from crop

Piron

Leemans

Kleynen

et al. 2008

Computers and Electronics in Agriculture

View full text Add to dashboard Cite

The aim of this study was to select the best combination of filters for detecting various weed species located within carrot rows. In-field images were taken under artificial lighting with a multispectral device consisting of a black and white camera coupled with a rotating wheel holding 22 interference filters in the VIS-NIR domain. Measurements were performed over a period of 19 days, starting 1 week after crop emergence (early weeding can increase yields) and seven different weeds species were considered. The selection of the best filter combination was based on a quadratic discriminant analysis. The best combination of filters included three interference filters, respectively centred on 450, 550 and 700 nm. With this combination, the overall classification accuracy (CA) was 72%. When using only two filters, a slight degradation of the CA was noticed. When the classification results were reported on field images, a systematic misclassification of carrot cotyledons appears. Better results were obtained with a more advanced growth stage.

show abstract

“…2D shape features have been used to detect broad-leaved weeds in cereal crops [16], to allow a rover to classify the shape and other geologic characteristics of rocks [9], to investigate the suitability of an imaging system to measure shape of particles [4] and for detection and classification of rocks [18]. A 3D feature called visibility ratio have been used to classify the visibility of rocks in piles [19].…”

Section: Feature Extractionmentioning

confidence: 99%

Visibility Classification of Pellets in Piles for Sizing without Overlapped Particle Error

Andersson¹,

Thurley²,

Marklund

2007

9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications (D

View full text Add to dashboard Cite

show abstract

Colour and shape analysis techniques for weed detection in cereal fields

Cited by 332 publications

References 10 publications

Estimation of evapotranspiration of temperate grassland based on high-resolution thermal and visible range imagery from unmanned aerial systems

Estimation of evapotranspiration of temperate grassland based on high-resolution thermal and visible range imagery from unmanned aerial systems

Selection of the most efficient wavelength bands for discriminating weeds from crop

Visibility Classification of Pellets in Piles for Sizing without Overlapped Particle Error

Contact Info

Product

Resources

About