Retrieval of leaf area index from top-of-canopy digital photography over agricultural crops

Liu, Jiangui; Pattey, E.

doi:10.1016/j.agrformet.2010.08.002

Cited by 135 publications

(118 citation statements)

References 19 publications

Supporting

Mentioning

113

Contrasting

Unclassified

Order By: Relevance

“…Green Crop Tracker is a histogram-based threshold method that was developed to differentiate gaps from plant tissues, in order to derive structural descriptors (Liu and Pattey, 2010;Liu and Pattey, 2013).…”

Section: Green Crop Trackermentioning

confidence: 99%

Estimating Crop Cover Fraction From Digital Color Images

Karakuş

Karabork

2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:The use of automated methods to estimate crop cover fraction from digital color images has increased in recent years. Crop cover fraction can determine accurate, fast and inexpensive with this methods. A digital color images was acquired over each of the 30 sample fields in 2014 year at 2-3 week intervals. Study area has 15 sunflower fields and 15 corn fields. Digital color images were collected during 4 months, namely over the course of the growing season from sowing until harvesting to determine crop cover fraction. We used two approach to estimate crop cover fraction. In first method, the images were transformed from the RGB (red, green, blue) color space to the HSI (hue, intensity, saturation) color space. We used an object-based image analysis approach to classify the images into green vegetation and the other materials. In the second method, The Green Crop Tracker is less labor and time intensive than the objectbased classification approach, is a viable alternative to ground-based methods. By comparing object-based classification method and Green Crop Tracker software 2014 growing season, results were obtained: There were high correlations between the estimations obtained by object-based classification method and Green Crop Tracker software (for 2014 R²=0.89). The relationship between two methods for 2014-23 sunflower field was calculated R²=0.97.

show abstract

Section: Green Crop Trackermentioning

confidence: 99%

Estimating Crop Cover Fraction From Digital Color Images

Karakuş

Karabork

2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Therefore, we proposed an image analysis procedure that objectively classified large gaps from the total estimated gap fraction. Images were first pre-processed by applying a simple transformation to generate a feature representing greenness from the three channels of RGB images; similar transformations of digital images were commonly experienced in the agricultural literature (e.g., Liu & Pattey 2010, Woebbecke et al 1995):…”

Section: Image Collection and Analysis Of Dcpmentioning

confidence: 99%

The estimation of canopy attributes from digital cover photography by two different image analysis methods

Chianucci¹,

Chiavetta²,

Cutini³

2014

iForest

View full text Add to dashboard Cite

“…Downward-looking cameras have already been used to extract LAI over short vegetation, such as agricultural crops, but are not often used for tall forest canopies until the tower-based webcam provides the possibility to extract forest LAI by near-surface remote sensing [27][28][29][30]. The series of acquired webcam images can be not only under overcast conditions, but also under clear-sky conditions with direct sunlight [16,17].…”

Section: Introductionmentioning

confidence: 99%

“…According to the theory of the geometric-optical (GO) model, the difference between the two types of illumination conditions for the images is that on overcast days there are two scene components: foliage and background, while on sunny days there are four scene components: sunlit foliage, sunlit background, shaded foliage, and shaded background [31][32][33]. The directional gap fraction model has been widely used on overcast days, while till now little research is dedicated to the extraction of LAI on sunny days [29,30].…”

Section: Introductionmentioning

confidence: 99%

“…The main challenge for the images acquired on sunny days is that it is difficult to discriminate the shaded foliage and shaded background from the shadows, where the signal variations in the three color channels are small [28][29][30]. Misclassification of shaded foliage as background on sunny days will lead to an overestimation of the gap fraction extraction [29], which may eventually result in the LAI estimation be outside the relative accuracy (20%) and absolute accuracy (0.5) requirement by the Global Climate Observation System (GCOS, http://www.wmo.int/pages/prog/gcos).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Extracting Leaf Area Index by Sunlit Foliage Component from Downward-Looking Digital Photography under Clear-Sky Conditions

Zeng

Liu

et al. 2015

Remote Sensing

View full text Add to dashboard Cite

Abstract:The development of near-surface remote sensing requires the accurate extraction of leaf area index (LAI) from networked digital cameras under all illumination conditions. The widely used directional gap fraction model is more suitable for overcast conditions due to the difficulty to discriminate the shaded foliage from the shadowed parts of images acquired on sunny days. In this study, a new LAI extraction method by the sunlit foliage component from downward-looking digital photography under clear-sky conditions is proposed. In this method, the sunlit foliage component was extracted by an automated image classification algorithm named LAB2, the clumping index was estimated by a path length distribution-based method, the LAD and G function were quantified by leveled digital images and, eventually, the LAI was obtained by introducing a geometric-optical (GO) model which can quantify the sunlit foliage proportion. The proposed method was OPEN ACCESSRemote Sens. 2015, 7 13411 evaluated at the YJP site, Canada, by the 3D realistic structural scene constructed based on the field measurements. Results suggest that the LAB2 algorithm makes it possible for the automated image processing and the accurate sunlit foliage extraction with the minimum overall accuracy of 91.4%. The widely-used finite-length method tends to underestimate the clumping index, while the path length distribution-based method can reduce the relative error (RE) from 7.8% to 6.6%. Using the directional gap fraction model under sunny conditions can lead to an underestimation of LAI by (1.61; 55.9%), which was significantly outside the accuracy requirement (0.5; 20%) by the Global Climate Observation System (GCOS). The proposed LAI extraction method has an RMSE of 0.35 and an RE of 11.4% under sunny conditions, which can meet the accuracy requirement of the GCOS. This method relaxes the required diffuse illumination conditions for the digital photography, and can be applied to extract LAI from downward-looking webcam images, which is expected for the regional to continental scale monitoring of vegetation dynamics and validation of satellite remote sensing products.

show abstract

Retrieval of leaf area index from top-of-canopy digital photography over agricultural crops

Cited by 135 publications

References 19 publications

Estimating Crop Cover Fraction From Digital Color Images

Estimating Crop Cover Fraction From Digital Color Images

The estimation of canopy attributes from digital cover photography by two different image analysis methods

Extracting Leaf Area Index by Sunlit Foliage Component from Downward-Looking Digital Photography under Clear-Sky Conditions

Contact Info

Product

Resources

About