Cotton boll distribution and yield estimation using three‐dimensional point cloud data

Dube, Nothabo; Bryant, B.; Sari‐Sarraf, Hamed; Ritchie, Glen L.

doi:10.1002/agj2.20412

Cited by 9 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stevens et al (1992) observed that wheat stubble residue decreased the number of bolls formed on nodes 5-8 on cotton plants compared to a fallow control. As noted by Bauer and Busscher (1996), changes in boll distribution on plants may negatively affect lint yields and fiber quality due to changes in source-sink relationships and indeterminate flowering that results in less time for boll fill (Dube et al, 2020;Ritchie et al, 2009). Additionally, weed pressure has previously been associated with reductions in cotton yield, likely by making bolls develop higher on the plant or later into the season (Blaise, 2006;Elms et al, 2001).…”

Section: Core Ideasmentioning

confidence: 99%

Cover cropping history affects cotton boll distribution, lint yields, and fiber quality

Billman¹,

Campbell²

2023

Crop Science

View full text Add to dashboard Cite

There has been limited introduction of new cover crop species into cotton (Gossypium hirsutum L.) production within the last 30 years. Mounting evidence shows that traditional cover cropping species may be detrimental to cotton production, either by depleting soil fertility with crop removal, immobilizing minerals from high carbon residue, or excessive quantity of residue remaining at planting. The objective of this study was to determine the effects of growing a novel cover crop species, carinata (Brassica carinata A. Braun), as a winter annual cover crop for cotton rotation in the southeastern Coastal Plain. Over a 2‐year period, carinata, winter wheat (Triticum aestivum L.), and fallow covers were maintained over winter months, then rotated into cotton. Each year, seedcotton and lint yields were collected, along with subsamples for ginning and subsequent fiber quality analyses. Additionally, end‐of‐season plant mapping was conducted on plants from 1 m of row per plot to determine cover crop effects on boll formation, retention, and distribution, as well as canopy architecture. Results indicated that seedcotton and lint yield of cotton following carinata was greater than cotton following winter wheat, and lint yields of cotton following wheat were lower than cotton after fallow. Fiber quality was largely unaffected by preceding cover crop. End‐of‐season plant mapping indicated that cotton grown after carinata had more position 2 bolls, which correlated to greater lint yields. These results indicate that carinata can potentially serve as a new, more effective cover crop than winter wheat for cotton rotations in Coastal Plain soils.

show abstract

Section: Core Ideasmentioning

confidence: 99%

Cover cropping history affects cotton boll distribution, lint yields, and fiber quality

Billman¹,

Campbell²

2023

Crop Science

View full text Add to dashboard Cite

show abstract

“…Many scholars have tried to develop various ground-based sensing systems. For example, images obtained by a digital camera installed on a robot platform have been used to estimate the number of cotton bolls based on the images collected by either a 3D sensor system, the estimated value of cotton bolls, or the lint obtained from the point cloud [18] . With the calculation of the number of cotton bolls in the field, accurate cotton yield predictions can be provided [19] .…”

Section: Introductionmentioning

confidence: 99%

Yield Estimation of High-Density Cotton Fields Using Low-Altitude UAV Imaging and Deep Learning

Bai

Zhang

et al. 2022

Preprint

View full text Add to dashboard Cite

Background: Different from other parts of the world, China has its own cotton planting pattern. Cotton are densely planted in wide-narrow rows to increase yield in Xinjiang, China, causing the difficulty in the accurate evaluation of cotton yields using remote sensing in such field with branches occluded and overlapped. Results: In this study, low-altitude unmanned aerial vehicle (UAV) imaging and deep convolutional neural networks (DCNN) were used to estimate the yields of densely planted cotton. Images of cotton field were acquired by an UAV at the height of 5 m. Cotton bolls were manually harvested and weighted afterwards. Then, a modified DCNN model was developed by applying encoder-decoder recombination and dilated convolution for pixel-wise cotton boll segmentation termed CD-SegNet. Linear regression analysis was employed to build up the relationship between cotton boll pixels ratio and cotton yield. Yield estimations of four cotton fields were verified after machine harvest and weighting. The results showed that CD-SegNet outperformed the other tested models including SegNet, support vector machine (SVM), and random forest (RF). The average error of the estimated yield of the cotton fields was 6.2%. Conclusions: Overall, the yield estimation of densely planted cotton based on lowaltitude UAV imaging is feasible. This study provides a methodological reference for cotton yield estimation in China.

show abstract

“…Many scholars have tried to develop various ground-based sensing systems. For example, a digital camera installed on a robotic platform was used to estimate the number of cotton bolls based on images acquired by the 3D sensor system, boll estimates, or lint obtained from point clouds [ 19 ]. With the calculation of the number of cotton bolls in the field, accurate cotton yield prediction can be achieved [ 20 ].…”

Section: Introductionmentioning

confidence: 99%

Yield estimation of high-density cotton fields using low-altitude UAV imaging and deep learning

Bai

Zhang

et al. 2022

Plant Methods

View full text Add to dashboard Cite

Background China has a unique cotton planting pattern. Cotton is densely planted in alternating wide and narrow rows to increase yield in Xinjiang, China, causing the difficulty in the accurate estimation of cotton yield using remote sensing in such field with branches occluded and overlapped. Results In this study, unmanned aerial vehicle (UAV) imaging and deep convolutional neural networks (DCNN) were used to estimate densely planted cotton yield. Images of cotton fields were acquired by the UAV at an altitude of 5 m. Cotton bolls were manually harvested and weighed afterwards. Then, a modified DCNN model (CD-SegNet) was constructed for pixel-level segmentation of cotton boll images by reorganizing the encoder-decoder and adding dilated convolutions. Besides, linear regression analysis was employed to build up the relationship between cotton boll pixels ratio and cotton yield. Finally, the estimated yield for four cotton fields were verified by weighing harvested cotton. The results showed that CD-SegNet outperformed the other tested models, including SegNet, support vector machine (SVM), and random forest (RF). The average error in yield estimates of the cotton fields was as low as 6.2%. Conclusions Overall, the estimation of densely planted cotton yields based on low-altitude UAV imaging is feasible. This study provides a methodological reference for cotton yield estimation in China.

show abstract

Cotton boll distribution and yield estimation using three‐dimensional point cloud data

Cited by 9 publications

References 28 publications

Cover cropping history affects cotton boll distribution, lint yields, and fiber quality

Cover cropping history affects cotton boll distribution, lint yields, and fiber quality

Yield Estimation of High-Density Cotton Fields Using Low-Altitude UAV Imaging and Deep Learning

Yield estimation of high-density cotton fields using low-altitude UAV imaging and deep learning

Contact Info

Product

Resources

About