Case study: Estimation of sorghum biomass using digital image analysis with Canopeo

Chung, Yong Suk; Choi, Sang Chul; Silva, Renato Rodrigues; Kang, Ji Won; Eom, Ji Hee; Kim, Changsoo

doi:10.1016/j.biombioe.2017.06.027

Cited by 39 publications

(30 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…ImageJ was incapable of predicting alfalfa–tall wheatgrass biomass when tall wheatgrass was in the reproductive phrase, and ImageJ was ineffective in distinguishing alfalfa cover from grass cover because of similar deepness of the green hues of the two species (Baxter et al, 2017b). In analysis of vertical images of canopies using Canopeo‐app, Chung et al (2017) obtained predictions of sorghum biomass yield with higher correlations than we observed with OWB, which would be appropriate for an upright‐growing crop. Supplementing the overhead, two‐dimensional imagery in our study with vertical‐canopy imagery would have been impractical owing to the largely prostrate orientation of grazed canopies.…”

Section: Resultsmentioning

confidence: 42%

See 1 more Smart Citation

Digital Image Analysis of Old World Bluestem Cover to Estimate Canopy Development

Xiong¹,

West²,

Brown³

et al. 2019

Agronomy Journal

View full text Add to dashboard Cite

Digital image analysis (DIA) can potentially provide rapid, objective assessment of pasture canopy development. In pastures of 'WW-B.Dahl' Old World bluestem [Bothriochloa bladhii (Retz) Blake], we compared the DIA programs ImageJ and Canopeo for ground cover estimates, their ability to estimate canopy functions, and their time savings for vegetation analysis relative to a manual method. The DIA procedure involved processing overhead canopy images into two color groupings corresponding to green ground cover and non-green (dead) cover plus bare ground for ground cover calculation. ImageJ analysis of ground cover agreed with two types of Canopeo applications (r 2 values of 0.97 and 0.98). The prediction regression for percentage photosynthetically active radiation interception (PARI) using ImageJ, y = 0.94x − 2.91 (r 2 = 0.72), was not different from Canopeo. Predicted values of leaf area index (LAI) and biomass increased exponentially with ground cover, likely owing to overlapping leaf area in older canopies. Two-dimensional ground cover had limited power of estimating LAI and biomass when ground cover exceeded 60%, LAI exceeded 1.8, and biomass exceeded 1500 kg DM ha -1 . The time required for estimating PARI, LAI, and green biomass using ground cover from both DIA methods was reduced to 3.6% of manual methods. The use of DIA with ImageJ provided measurements of ground cover that are simple and conducive to large batch analyses. Regressions of ground cover were deemed useful for rapid estimations of PARI and LAI, but of lesser value for biomass, especially when canopies developed stems and seedheads.Dep. of Plant and Soil Science, Texas Tech Univ. 2911 15th St., Lubbock, TX 79409.

show abstract

Section: Resultsmentioning

confidence: 42%

“…They concluded that visual estimates usually understated actual ground cover as determined with Canopeo, especially at intermediate levels of ground cover of narrow‐leaved crops. Chung et al (2017) used Canopeo as a rapid measurement of biomass of sorghum ( Sorghum bicolor Moench.) plants by recording images of vertical growth rather than ground cover.…”

mentioning

confidence: 99%

Digital Image Analysis of Old World Bluestem Cover to Estimate Canopy Development

Xiong¹,

West²,

Brown³

et al. 2019

Agronomy Journal

View full text Add to dashboard Cite

show abstract

“…An experimental analysis with 100 random object detection results revealed that there are small but considerable differences between bounding box centers and object centers ( Figure 6). To address this issue, the location of an accurate object center was determined by applying the Canopeo algorithm to generate a binary canopy map, and by performing connected components analysis to calculate centroid of the canopy within the bounding box region [43,44]. A pixel-level classification using the Canopeo algorithm was adopted to classify canopy and non-canopy pixels (green vs. non-green) from raw RGB images [43].…”

Section: Fine-tuning Of Object Centermentioning

confidence: 99%

Plant Counting of Cotton from UAS Imagery Using Deep Learning-Based Object Detection Framework

Chang

Ashapure

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Assessing plant population of cotton is important to make replanting decisions in low plant density areas, prone to yielding penalties. Since the measurement of plant population in the field is labor intensive and subject to error, in this study, a new approach of image-based plant counting is proposed, using unmanned aircraft systems (UAS; DJI Mavic 2 Pro, Shenzhen, China) data. The previously developed image-based techniques required a priori information of geometry or statistical characteristics of plant canopy features, while also limiting the versatility of the methods in variable field conditions. In this regard, a deep learning-based plant counting algorithm was proposed to reduce the number of input variables, and to remove requirements for acquiring geometric or statistical information. The object detection model named You Only Look Once version 3 (YOLOv3) and photogrammetry were utilized to separate, locate, and count cotton plants in the seedling stage. The proposed algorithm was tested with four different UAS datasets, containing variability in plant size, overall illumination, and background brightness. Root mean square error (RMSE) and R2 values of the optimal plant count results ranged from 0.50 to 0.60 plants per linear meter of row (number of plants within 1 m distance along the planting row direction) and 0.96 to 0.97, respectively. The object detection algorithm, trained with variable plant size, ground wetness, and lighting conditions generally resulted in a lower detection error, unless an observable difference of developmental stages of cotton existed. The proposed plant counting algorithm performed well with 0–14 plants per linear meter of row, when cotton plants are generally separable in the seedling stage. This study is expected to provide an automated methodology for in situ evaluation of plant emergence using UAS data.

show abstract

“…For the Canopeo App., a tool for measuring the fractional green canopy cover of plants, a strong relationship between Canopeo images and light quantum sensors was observed when monitoring the canopy cover of soybean [41]. Additionally, Chung et al [42] embraced an innovative approach with the Canopeo App. ; by taking vertical images of the crop, they observed a strong correlation between plant height in-season measurements and biomass production.…”

Section: Introductionmentioning

confidence: 99%

Testing Proximal Optical Sensors on Quinoa Growth and Development

et al. 2020

View full text Add to dashboard Cite

Proximal optical sensors (POSs) are effective devices for monitoring the development of crops and the nitrogen (N) status of plants. POSs are both useful and necessary in facilitating the reduction of N losses into the environment and in attaining higher nitrogen use efficiency (NUE). To date, no comparison of these instruments has been made on quinoa. A field experiment conducted in Tuscany, Italy, with different POSs, has assessed the development of quinoa with respect to N status. Three sets of POSs were used (SPAD-502, GreenSeeker, and Canopeo App.) to monitor quinoa development and growth under different types of fertilizers (digestate and urea) and levels of N fertilization (100, 50, and 0 kg N ha−1). The present findings showed that in-season predictions of crop biomass at harvest by SPAD-502 and GreenSeeker optical sensors were successful in terms of the coefficient of determination (R2 = 0.68 and 0.82, respectively) and statistical significance (p < 0.05), while the Canopeo App. was suitable for monitoring the plant´s canopy expansion and senescence. The relative error (RE%) showed a remarkably high performance between observed and predicted values, 5.80% and 4.12% for GreenSeeker and SPAD-502, respectively. Overall, the POSs were effective devices for monitoring quinoa development during the growing season and for predicting dry biomass at harvest. However, abiotic stresses (e.g., heat-stress conditions at flowering) were shown to reduce POSs’ accuracy when estimating seed yields at harvest, and this problem will likely be overcome by advancing the sowing date.

show abstract

Case study: Estimation of sorghum biomass using digital image analysis with Canopeo

Cited by 39 publications

References 7 publications

Digital Image Analysis of Old World Bluestem Cover to Estimate Canopy Development

Digital Image Analysis of Old World Bluestem Cover to Estimate Canopy Development

Plant Counting of Cotton from UAS Imagery Using Deep Learning-Based Object Detection Framework

Testing Proximal Optical Sensors on Quinoa Growth and Development

Contact Info

Product

Resources

About