Original papersAutomated computation of leaf area index from fruit trees using improved image processing algorithms applied to canopy cover digital photograpies
Graphical abstract
Proposed improvement of leaf area index estimation for fruit trees using a two-level automated segmentation to isolate non-leaf material from the analysis where: (a) is the original image; (b), (c) and (d) are the resulting images for the first segmentation level and (e), (f) and (g) are the resulting images for the second segmentation level.
Introduction
Leaf area index (LAI) is a dimensionless parameter that relates the total area of leaves in the canopy (one sided) with a specific area of soil (Jonckheere et al., 2004). This index is of high importance in plant physiology and plant modeling to up-scale other physiological parameters that are usually measured at the leaf scale. Therefore, an accurate LAI estimation will allow more precise values of physiological information at the whole-plant or whole-tree level. This index is also useful to quantify the level of plant vigor, canopy architecture and water demands at the whole-plant or tree level.
Direct or indirect methods can be used to quantify and estimate LAI (Bréda, 2003). The direct, or allometric, methods consider a partial or complete defoliation of the canopy to assess total leaf area of the plants or trees, which can be associated to a specific area of soil. The latter method offers an accurate measure of real leaf area (LA) and can be used to calibrate other indirect methods. The destructive nature of the direct methods does not allow resampling the same trees; therefore it is impossible to assess growing patterns within a season and between seasons. An alternative to destructive methods are the indirect methods based on mathematical algorithms that describe the transmission of light through the canopy to estimate total LA which is based on Beer’s Law (Bréda, 2003, Jonckheere et al., 2004, Vose et al., 1995, Weiss et al., 2004). These methods require estimates of the canopy light extinction coefficient (k) and corrections of leaf overlaps by assuming that foliage is randomly distributed in the canopy (Garrigues et al., 2008, Vose et al., 1995). However, instrumentation based on the latter principle could be cost prohibitive and requires high level of know-how to acquire and analyze the data. Examples of this instrumentation are Ceptometers (AccuPAR LP-80, Decagon Devices Inc., Pullman, WA, USA) and LI-Cor 2000 and 2200 (Licor Inc., Lincoln, Nebraska. USA). Furthermore, errors associated to this type of instrumentation are on the order of 10–40% underestimations (Bréda, 2003) compared to observed data, which could be associated to the scattering of blue light (Macfarlane et al., 2007). Due to the latter, it is recommended to use these instruments in cloudy conditions or close to dawn or dusk, which involves a practical complication for these methods (LI-Cor 2000-2200 Manual. Licor Inc., Lincoln, Nebraska. USA).
Other indirect methods are based on digital photography, such as digital hemispherical photography (DHP) or fish-eye and cover photography, which estimates LAI by analyzing the size of gaps within canopies and associating these with the level of light transmission through them (Duveiller and Defourny, 2010, Macfarlane et al., 2007, Martens et al., 1993). The fish-eye photographic method requires specific hardware (fish-eye lens) and makes use of non-automated image analysis software (Fuentes et al., 2008). Furthermore, results from fish-eye photography are similar to those found with cover photography for forests (Macfarlane et al., 2007), which does not require any extra hardware besides a common digital camera with medium pixel resolution (5 Megapixels) (Pekin and Macfarlane, 2009). Pekin and Macfarlane (2009) indicated the advantages of this method in comparison to the fish-eye method, arguing that digital images can be routinely obtained during normal working hours because sky luminance is more even, facilitating pixel classification. Additionally, common digital images are rectangular shaped providing higher resolution than DHP methods. Common digital images are less sensitive to photographic exposure providing more accurate measurements of the gap fraction at the zenith. Recently, Fuentes et al. (2008) developed an semi-automated method to analyze cover photography, in order to estimate LAI and other canopy architecture parameters. This method has been based on the cover photography method developed by Macfarlane et al. (2007) adding the automation by batch analyzing images to identify the big gaps within canopies. The application of this semi-automated method proposed resulted in good estimations of LAI for Australian forests compared to indirect methods and satellite methods (Fuentes et al., 2008), for apple trees compared to allometry and using a variable light extinction coefficient (Poblete-Echeverria et al., 2015) and for grapevines compared to allometry, high resolution satellite information and indirect methods (Fuentes et al., 2014).
The downside of the photographic methods is that they incorporate non-leaf material within images, such as trunks (in the case of trees), branches and fruits (in the case of fruit trees), wires and structures from training systems (in the case of grapevines). For this reason, Bréda (2003) proposed that results from the image analysis of cover photography should be called Plant Area Index (PAI) rather than LAI. In the case of forests with closed canopies, Macfarlane et al. (2007) and Fuentes et al. (2008) found that the inclusion of trunks and branches are not significant for the accuracy of estimated LAI. However, this effect could be relevant for horticultural crops and perennial fruit trees, especially in early stages of growth within a season. The effect has been demonstrated for grapevines ‘Merlot’, which presented an over-estimation of LAI of around 3% on average using the cover photography method compared to allometry from bud-burst until veraison. In the later stage, the canopy was big enough to cover branches and cordons, reducing significantly the estimation error (Fuentes et al., 2014). This error is seemingly non-significant for grapevines, which can be associated to the training system used (Vertical Shoot Positioning) and the architecture of canopies, which are highly managed (clumping index close to 1). However, for fruit trees with open canopies, such as apple, pear or cherry trees, the object segmentation method to isolate leaves from branches and stems has been not evaluated previously.
In the case of apple trees in Chile, the cover photography and analysis method proposed by Fuentes et al. (2014) obtained an error of 44.6% in the LAI estimation when using a common light extinction coefficient compared to allometric LAI. The LAI estimation improved, with an error of 17.5%, by using a k obtained from a model based on canopy cover for the same images. A further improvement on the estimation was achieved by measuring incident and below canopy photosynthetic active radiation (PAR) to obtain a proxy of k with an error of only 8.5% in comparison to allometric LAI (Poblete-Echeverria et al., 2015). The latter work makes evident that significant errors can be introduced in the estimation of LAI due to the complexity of fruit tree canopies and the sensitivity of the LAI algorithms to k. Reducing this error by incorporating further light interception measurements complicates measurements in field conditions.
Object segmentation is one of the most discussed problems in digital image processing. There are segmentation methods based on the application of simple operators such as the gradient (Gonzalez and Woods, 2008), iterative algorithms for automatically estimating thresholds (Otsu, 1979), and highly sophisticated methods such as Active Contours based on Variational Calculus (Chan and Vese, 2001). To address the trade-off between the precision level and economic and computational costs of the method implementation Occam’s razor is applicable, according to which under the same conditions, the simpler explanation is usually preferable. Following the Law of Parsimony, to estimate the leaf area index, a 2-level thresholding method is proposed. This method addresses the segmentation problem with low complexity techniques, allowing the use of conventional devices to capture and process images.
Based on the original cover photography code developed by Fuentes et al. (2008), this paper aims to automate filtration of non-leaf material from digital images using specific segmentation algorithms based on the combination of RGB and CIE Lab color model (CIE, 1976). The proposed method also allows the revision of pre-obtained images to improve the estimation of LAI and other canopy architecture parameters.
Section snippets
Theoretical background of color models
A color model is a three-dimensional space (if the model has 3 channels), and the colors are points or vectors within that space. Color models provide a way to represent colors and such representation must be unique, i.e. a color must be associated to a single vector. In literature, three types of color models are described (Gonzalez and Woods, 2008). The first type corresponds to color representations depending on hardware requirements. Among these models are the RGB (for computer screens) and
Location and plant material
This study was carried out in a commercial cherry orchard (Prunus avium) of eight hectares (ha) in size, located in Teno, Curicó Province, Maule Region, Chile (34.83° LS; 71.06° LW; 296 m. a. s. l.). All data was obtained in March 2013 with the aim to minimize interference with the production period. For this purpose, 20 trees were selected based on similar canopy architecture, production potential, trunk diameter, height and vigor. Of these trees, 10 corresponded to the cultivar ‘Bing’, which
Estimation of LAI using digital images
The estimation of LAI using cover digital images was based on the method proposed by Fuentes et al. (2008). The steps to analyze the images and to obtain the relevant parameters were: (i) image capture per quadrant as shown in Fig. 3(a); (ii) the image was transformed to a binary image through a selection of an appropriate threshold using the blue channel (B) from the RGB image (Fig. 3(b)). This channel was used since it allows a proper discrimination of leaf material from sky and clouds (Fuentes
Proposed improvement of LAI estimation
The method proposed by Fuentes et al. (2008) has been applied to forest trees, grapevines (Fuentes et al., 2014) and apple trees (Poblete-Echeverria et al., 2015) and it has been made available as a smartphone and tablet PC application (Fuentes et al., 2012). However, the method incorporates non-leaf material in the analysis, which can compromise accuracy in the estimation of LAI from fruit trees, especially if specific k values are not available. Automatic segmentation of non-leaf pixels such
Results and discussions
Results are first shown separately per cultivar and then combining all the data from both cultivars for a global comparison. Results of LAI estimations in the 20 evaluated trees are presented in Table 1, Table 2 for ‘Bing’ and ‘Sweetheart’, respectively. They summarize the averaged and standard deviations of LAI, considering all combinations of k and big gaps thresholds indicated previously in Section 3.
Conclusions
A modified method to analyze cover photography from cherry trees to obtain LAI has been presented. The reference method was proposed by Fuentes et al. (2008), which is a semi-automated batch process of conventional digital images from the tree canopy. The proposed improvement consisted in the automation of the image segmentation process based on a two-level thresholding stage, which eliminates the need to enter configuration parameters manually. The results presented herein suggest that this
Acknowledgments
The research leading to this report was supported by the Chilean government through the National Commission for Scientific and Technological Research – CONICYT (Proyecto Inserción de Capital Humano Avanzado en la Academia – PAI (2012) N° 7912010010). The following persons provided invaluable assistance in field measurements and data processing: Pablo Diaz, Enrique Cornejo, Karina Gonzalez, Margarita Parraguez, Jorge Jaramillo, Mario Moya, Victor Encalada, Miguel Oyarce and Alex Zuñiga. We also
References (21)
- et al.
Intercomparison and sensitivity analysis of leaf area index retrievals from LAI-2000, AccuPAR, and digital hemispherical photography over croplands
Agric. For. Meteorol.
(2008) - et al.
Review of methods for in situ leaf area index determination: Part I. Theories, sensors and hemispherical photography
Agric. For. Meteorol.
(2004) - et al.
Estimation of leaf area index in eucalypt forest using digital photography
Agric. For. Meteorol.
(2007) - et al.
Estimation of tree canopy leaf area index by gap fraction analysis
For. Ecol. Manage.
(1993) - et al.
Statistical validation
Ecol. Model.
(1993) - et al.
Review of methods for in situ leaf area index (LAI) determination: Part II. Estimation of LAI, errors and sampling
Agric. For. Meteorol.
(2004) Ground-based measurements of leaf area index: a review of methods, instruments and current controversies
J. Exp. Bot.
(2003)CIE Colorimetry – Part 4: 1976 L*a*b* Colour Space
- et al.
Active contours without edges
IEEE Trans. Image Process.
(2001) - Duveiller, G., Defourny, P., 2010. Batch processing of hemispherical photography using object-based image analysis to...
Cited by (47)
Accurate leaf area index estimation in sorghum using high-resolution UAV data and machine learning models
2024, Physics and Chemistry of the EarthInsights in mechanism of drying shrinkage by pore-scale modeling of heat-moisture and stress-strain distribution for high-moisture porous media
2023, International Journal of Thermal SciencesNon-destructive Leaf Area Index estimation via guided optical imaging for large scale greenhouse environments
2022, Computers and Electronics in AgricultureCitation Excerpt :In principle, there are two groups of measurement methods: active/destructive and passive/non-destructive LAI measurements, many of which have recently been summarized by Popović (2021). The most common and simplest method is active plant measurement by defoliation, which requires the grower to regularly remove all the leaves in a predetermined reference space and count the number of leafs and area (e.g., measuring the breadth and length of individual leaves) manually or by computer analysis, e.g., color (Easlon and Bloom, 2014; Patrignani and Ochsner, 2015; Mora et al., 2016) or otsu (Radzali et al., 2016; Fuentes et al., 2014) segmentation, etc. There are numerous non-destructive remote sensing approaches that depend on specific environmental conditions.
Remotely sensed real-time quantification of biophysical and biochemical traits of Citrus (Citrus sinensis L.) fruit orchards – A review
2021, Scientia HorticulturaeCitation Excerpt :The empirical approach based on VIs is preferred to estimate the citrus trees LAI. Since not any site-specific data required while the computation time is short (Mora et al., 2016). The sLAIDI vegetation index is proved successful in predicting LAI of Midknight Valencia orchard canopies.
Digital evaluation of leaf area of an individual tree canopy in the apple orchard using the LIDAR measurement system
2020, Computers and Electronics in Agriculture
- 1
Address: Laboratory of Technological Research on Pattern Recognition, Science and Technology Park, Universidad Católica del Maule, Talca 3480112, Chile. www.litrp.cl.