Real-Time Segmentation of Plants and Weeds

Marchant, J.A.; Tillett, R.D.; Brivot, Renaud

doi:10.1006/rtim.1997.0086

Cited by 21 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Aside from the applied transformation indices (NDI vs. illumination invariant), the threshold segmentation, the size filter and region growing procedures were similar. We refer also to the many studies that have addressed light differences by means of an adjusted threshold (Marchant et al 1998;Rasmussen et al 2007;Reid and Searcy 1987;Shrestha et al 2004;Tellaeche et al 2008). However, variation in the spread and distribution of the hue values under different illumination conditions may blur the separation between object and background and lead to a mixture of plant and background classifications.…”

Section: Resultsmentioning

confidence: 99%

Robust Methods for Measurement of Leaf-Cover Area and Biomass from Image Data

2011

View full text Add to dashboard Cite

Leaf-cover area is a widely required plant development parameter for predictive models of weed growth and competition. Its assessment is performed either manually, which is labor intensive, or via visual inspection, which provides biased results. In contrast, digital image processing enables a high level of automation, thereby offering an attractive means for estimating vegetative leaf-cover area. Nonetheless, image-driven analysis is greatly affected by illumination conditions and camera position at the time of imaging and therefore may introduce bias into the analysis. Addressing both of these factors, this paper proposes an image-based model for leaf-cover area and biomass measurements. The proposed model transforms color images into an illumination-invariant representation, thus facilitating accurate leaf-cover detection under varying light conditions. To eliminate the need for fixed camera position, images are transformed into an object–space reference frame, enabling measurement in absolute metric units. Application of the proposed model shows stability in leaf-cover detection and measurement irrespective of camera position and external illumination conditions. When tested on purple nutsedge, one of the world's most troublesome weeds, a linear relation between measured leaf-cover area and plant biomass was obtained regardless of plant developmental stage. Data on the expansion of purple nutsedge leaf-cover area is essential for modeling its spatial growth. The proposed model offers the possibility of acquiring reliable and accurate biological data from digital images without extensive photogrammetric or image-processing expertise.

show abstract

Section: Resultsmentioning

confidence: 99%

Robust Methods for Measurement of Leaf-Cover Area and Biomass from Image Data

2011

View full text Add to dashboard Cite

show abstract

“…Fitting ASMs is also difficult in scenes where there is dense crop and weed growth. Early work by Marchant et al (1998) used monochrome, near-infrared cameras to obtain high contrast between vegetation and soil and vegetation outside the crop row was classified as weed. As the technological capabilities of image capture equipment improved, algorithms were developed which exploited other parts of the light spectrum.…”

Section: Introductionmentioning

confidence: 99%

Image Processing Performance Assessment Using Crop Weed Competition Models

Onyango

Marchant

Grundy³

et al. 2005

Precision Agric

View full text Add to dashboard Cite

Precision treatment of both crops and weeds requires the accurate identification of both types of plant. However both identification and treatment methods are subject to error and it is important to understand how misclassification errors affect crop yield. This paper describes the use of a conductance growth model to quantify the effect of misclassification errors caused by an image analysis system.Colour, morphology and knowledge about planting patterns have been combined, in an image analysis algorithm, to distinguish crop plants from weeds. As the crop growth stage advances, the algorithm is forced to trade improved crop recognition for reduced weed classification. Depending on the chosen method of weed removal, misclassification may result in inadvertent damage to the crop or even complete removal of crop plants and subsequent loss of yield. However incomplete removal of weeds might result in competition and subsequent yield reduction. The plant competition model allows prediction of final crop yield after weed or crop removal. The competition model also allows the investigation of the impact on yield of misclassification in the presence of both aggressive and benign weed types. The competition model and the image analysis algorithm have been linked successfully to investigate a range of misclassification scenarios in scenes containing cabbage plants.

show abstract

“…De nombreuses approches existent pour mesurer la couverture végétale. Parmi elles, les méthodes de seuillage ont l'avantage de la simplicité tout en fournissant de bons résultats, par exemple : seuillage dynamique (Reid, Searcy, 1987), seuillage d'Otsu (Meyer, Neto, 2008), seuillage par hystérésis (Marchant et al, 1998), seuillage qui maximise l'entropie (Aitkenhead et al, 2003) (Tellaeche et al, 2008). Pour cela, les recherches se sont orientées vers le calcul de différents types d'indices de végétation, comme par exemple le CIVE color index of vegetation extraction (Kataoka et al, 2003), l'ExG excess green index (Woebbecke et al, 1995), et l'ExGR excess green minus excess red (Neto et al, 2006).…”

Section: Introductionunclassified

Détection simultanée de l’ombre et de la végétation sur des images aériennes couleur en haute résolution

Ngo¹,

Collet²,

Mazet³

2015

Traitement du signal

View full text Add to dashboard Cite

Nous proposons une nouvelle méthode pour détecter simultanément les zones d'ombre et de végétation dans des images de télédétection. Plusieurs indices d'ombre et de végétation sont fusionnés grâce à la théorie de DS afin d'augmenter la fiabilité et la précision de la segmentation. La fusion de DS étant une méthode pixellique, elle est incorporée dans un contexte markovien pour obtenir une segmentation régularisée et plus optimale. Les évaluations sur des images aériennes montrent clairement que cette méthode est robuste et précise. ABSTRACT. We propose a new method to simultaneously detect shadows and vegetation in remote sensing images. Several shadow and vegetation indices are merged with the Dempster-Shafer (DS) theory so as to increase the reliability and accuracy of the segmentation. The per-pixel DS fusion is incorporated in a Markovian context to obtain an optimal and regularized segmentation result. Evaluation on aerial images clearly shows that this new method is robust and accurate.

show abstract

Real-Time Segmentation of Plants and Weeds

Cited by 21 publications

References 9 publications

Robust Methods for Measurement of Leaf-Cover Area and Biomass from Image Data

Robust Methods for Measurement of Leaf-Cover Area and Biomass from Image Data

Image Processing Performance Assessment Using Crop Weed Competition Models

Détection simultanée de l’ombre et de la végétation sur des images aériennes couleur en haute résolution

Contact Info

Product

Resources

About