The Use of Local Spectral Properties of Leaves as an Aid for Identifying Weed Seedlings in Digital Images

Franz, Elke; Gebhardt, M. R.; Unklesbay, K.

doi:10.13031/2013.31717

Cited by 82 publications

(32 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This might be an effect of the variation of spectral properties with the geometry of the scene, since the angle between the leaf and the camera optical axis varies from the periphery to the centre of the weed. On the other hand, cotyledons are nearly systematically misclassified, confirming previous studies revealing different spectral characteristic between cotyledons and leaves of the same plant (Franz et al, 1991;Gee et al, 2004). The impact of the misclassification of cotyledons on the classification accuracy is likely small since cotyledons have a small area compared to the rest of the carrot's leaves.…”

Section: Fig 4 -Same As Fig 3 For Wide Band Filters (80 or 100 Nm Fsupporting

confidence: 85%

“…This parameter is influenced by the interaction between the species and the growth stage (Franz et al, 1991;El-Faki et al, 2000;Zhao et al, 2005), by stresses such as water or nitrogen deficiency (Goel et al, 2003;Zhao et al, 2005), by the angle between the leaf and the camera optical axis (Franz et al, 1991;Haralson et al, 1997cited in Noble et al, 2002 and by the substrate nature (Noble and Crowe, 2001;Noble et al, 2002).…”

Section: Fig 1 -Picture Of a Typical Carrot Line (Horizontally In Tmentioning

confidence: 99%

“…Using a camera with a filter wheel holding four filters (RGB and infra-red), Franz et al (1991) took images of four weed species and soy leaves under controlled lighting. Using five statistical features of the leaf images, the classification rate was up to 94% with manually selected samples and taking into account the relative position of the plants and the lighting system.…”

Section: Fig 1 -Picture Of a Typical Carrot Line (Horizontally In Tmentioning

confidence: 99%

“…They may be attributed to particular conditions, such as crop regularly spaced in the field with no overlapping (Borregaard et al, 2000;Feyaerts and Van Gool, 2001), clearly different macrostructures of weeds and crops (Franz et al, 1991) or presence of a particular colour on certain plant stems (Zhang and Chaisattapagon, 1995;El-Faki et al, 2000).…”

Section: Fig 1 -Picture Of a Typical Carrot Line (Horizontally In Tmentioning

confidence: 99%

See 3 more Smart Citations

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

Section: Fig 4 -Same As Fig 3 For Wide Band Filters (80 or 100 Nm Fsupporting

confidence: 85%

Section: Fig 1 -Picture Of a Typical Carrot Line (Horizontally In Tmentioning

confidence: 99%

Section: Fig 1 -Picture Of a Typical Carrot Line (Horizontally In Tmentioning

confidence: 99%

Section: Fig 1 -Picture Of a Typical Carrot Line (Horizontally In Tmentioning

confidence: 99%

See 2 more Smart Citations

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

show abstract

“…Leaf orientation is also a major factor in discriminating between different plant species when HSI is used outdoors. Franz et al (1991) reported that accurate spectral discrimination is possible for controlled leaf orientations, but discrimination accuracy significantly decreases as soon as leaf orientation changes. Vigneau et al (2011) explored the effect of leaf orientation for building a predictive model for nitrogen content using HSI.…”

Section: Limitationsmentioning

confidence: 99%

Outdoor Applications of Hyperspectral Imaging Technology for Monitoring Agricultural Crops: A Review

Ahmed¹,

Yasmin²,

Mo³

et al. 2016

Journal of Biosystems Engineering

View full text Add to dashboard Cite

Background: Although hyperspectral imaging was originally introduced for military, remote sensing, and astrophysics applications, the use of analytical hyperspectral imaging techniques has been expanded to include monitoring of agricultural crops and commodities due to the broad range and highly specific and sensitive spectral information that can be acquired. Combining hyperspectral imaging with remote sensing expands the range of targets that can be analyzed. Results: Hyperspectral imaging technology can rapidly provide data suitable for monitoring a wide range of plant conditions such as plant stress, nitrogen status, infections, maturity index, and weed discrimination very rapidly, and its use in remote sensing allows for fast spatial coverage. Conclusions: This paper reviews current research on and potential applications of hyperspectral imaging and remote sensing for outdoor field monitoring of agricultural crops. The instrumentation and the fundamental concepts and approaches of hyperspectral imaging and remote sensing for agriculture are presented, along with more recent developments in agricultural monitoring applications. Also discussed are the challenges and limitations of outdoor applications of hyperspectral imaging technology such as illumination conditions and variations due to leaf and plant orientation.

show abstract

AE—Automation and Emerging Technologies

Yang¹,

Prasher²,

Landry³

et al. 2002

Biosystems Engineering

View full text Add to dashboard Cite

The Use of Local Spectral Properties of Leaves as an Aid for Identifying Weed Seedlings in Digital Images

Cited by 82 publications

References 0 publications

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

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

Outdoor Applications of Hyperspectral Imaging Technology for Monitoring Agricultural Crops: A Review

AE—Automation and Emerging Technologies

Contact Info

Product

Resources

About