Sugarcane stem node detection and localization for cutting using deep learning

Wang, Weiwei; Li, Cheng; Wang, Kui; Tang, Lingling; Ndiluau, Pedro Final; Cao, Yuqing

doi:10.3389/fpls.2022.1089961

Cited by 7 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chen et al [ 24 ] introduced the YOLOv4 algorithm to study the recognition of sugarcane stem nodes in a natural environment and realize fast and accurate recognition of sugarcane stem nodes in a complex natural environment. Wang et al [ 25 ] proposed an algorithm aimed at enhancing YOLOv4-Tiny for sugarcane stem node recognition. This improved algorithm achieved remarkable results, including a mean accuracy precision of 99.11%, a detection accuracy of 97.07%, and a transmission frame per second (fps) rate of 30.…”

Section: Introductionmentioning

confidence: 99%

Sugarcane stem node identification algorithm based on improved YOLOv5

Xie,

Li,

Xiao

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

Identification of sugarcane stem nodes is generally dependent on high-performance recognition equipment in sugarcane seed pre-cutting machines and inefficient. Accordingly, this study proposes a novel lightweight architecture for the detection of sugarcane stem nodes based on the YOLOv5 framework, named G-YOLOv5s-SS. Firstly, the study removes the CBS and C3 structures at the end of the backbone network to fully utilize shallow-level feature information. This enhances the detection performance of sugarcane stem nodes. Simultaneously, it eliminates the 32 times down-sampled branches in the neck structure and the 20x20 detection heads at the prediction end, reducing model complexity. Secondly, a Ghost lightweight module is introduced to replace the conventional convolution module in the BottleNeck structure, further reducing the model’s complexity. Finally, the study incorporates the SimAM attention mechanism to enhance the extraction of sugarcane stem node features without introducing additional parameters. This improvement aims to enhance recognition accuracy, compensating for any loss in precision due to lightweight modifications. The experimental results showed that the average precision of the improved network for sugarcane stem node identification reached 97.6%, which was 0.6% higher than that of the YOLOv5 baseline network. Meanwhile, a model size of 2.6MB, 1,129,340 parameters, and 7.2G FLOPs, representing respective reductions of 82%, 84%, and 54.4%. Compared with mainstream one-stage target detection algorithms such as YOLOv4-tiny, YOLOv4, YOLOv5n, YOLOv6n, YOLOv6s, YOLOv7-tiny, and YOLOv7, G-YOLOv5s-SS achieved respective average precision improvements of 12.9%, 5.07%, 3.6%, 2.1%, 1.2%, 3%, and 0.4% in sugarcane stem nodes recognition. Meanwhile, the model size was compressed by 88.9%, 98.9%, 33.3%, 72%, 92.9%, 78.8% and 96.3%, respectively. Compared with similar studies, G-YOLOv5s-SS not only enhanced recognition accuracy but also considered model size, demonstrating an overall excellent performance that aligns with the requirements of sugarcane seed pre-cutting machines.

show abstract

Section: Introductionmentioning

confidence: 99%

Sugarcane stem node identification algorithm based on improved YOLOv5

Xie,

Li,

Xiao

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Low speeds impair operational performance and machines designed to harvest satisfactorily well above 3 km h −1 . Wang et al [6] showed that cut quality is a severe problem in sugarcane seed production. In this way, they applied machine learning to improve operation; this application can also improve the base cut harvesting operation, opening perspectives for future investigations.…”

Section: Resultsmentioning

confidence: 99%

“…Mechanized sugarcane harvesting brought several environmental benefits, reducing the need for labor and fires [1] and increasing agricultural performance [2]. However, mechanized harvesting also generates problems, such as increased raw impurities, field losses [3], lower cut quality [4][5][6][7] and ratoons with damage [8], resulting in fragmented stumps [9].…”

Section: Introductionmentioning

confidence: 99%

Continuous and Impact Cutting in Mechanized Sugarcane Harvest: Quality, Losses and Impurities

et al. 2023

View full text Add to dashboard Cite

Sugarcane harvesting requires improvements, particularly in cutting tools. Continuous cutting saws have been introduced as a solution to this issue. This study evaluates the performance of two basal sugarcane cutting systems in different fields: a traditional impact cut system (ICS) with knives and a continuous cut system (CCS) with saw blades. Tests were conducted during two crop cycles in three areas, using a 3 × 2 factorial design with two cutting devices and four replications per treatment. Cut quality indices and ratoon damage were analyzed using descriptive statistics. Raw material losses were subjected to the Shapiro–Wilk normality test, ANOVA, and Tukey’s test at 5% probability. Significant differences in cutting quality were found across different areas. The total crop productivity influenced sugarcane cut quality, with the CCS showing (0.8 Mg ha−1) visible losses in higher productivity areas, which is a 74% increase compared to the ICS. In lower productivity areas, the CCS demonstrated better loss performance (0.8 Mg ha−1). Additionally, the stumps damage rate for the CCS was lower than that for the ICS (0.15 and 0.28, respectively), indicating that saws can preserve cane fields and enhance longevity.

show abstract

“…Chen et al [27] studied the impact of data augmentation and varying lighting conditions on detecting sugarcane stem nodes, identifying YOLO v4 as the top performer with an average precision of 95.17%, compared to Faster R-CNN (78.87%), SSD300 (88.98%), RetinaNet (90.88%), and YOLO v3 (92.69%). Wang et al [28] improved an algorithm, resulting in a mean average precision (MAP) of 99.11% and a detection accuracy of 97.07%, surpassing the Faster-RCNN and YOLOv4 algorithms.…”

Section: Introductionmentioning

confidence: 99%

Data-Efficient Vision Transformer Models for Robust Classification of Sugarcane

Paçal,

Kunduracıoğlu

2024

J. Soft. Comput. Decis. Anal.

View full text Add to dashboard Cite

Sugar cane is an important agricultural product that provides 75% of the world's sugar production. As with all plant species, any disease affecting sugarcane can significantly impact yields and planning. Diagnosing diseases in sugarcane leaves using traditional methods is slow, inefficient, and often lacking in accuracy. This study presents a deep learning-based approach for accurate diagnosis of diseases in sugarcane leaves. Specifically, training and evaluation were conducted on the publicly available Sugarcane Leaf Dataset using leading ViT (Vision Transformer) architectures such as DeiT3-Small and DeiT-Tiny. This dataset includes 11 different disease classes and a total of 6748 images. Additionally, these models were compared with popular CNN models. The findings of the study show that there is no direct relationship between model complexity, depth, and accuracy for the 11-class sugarcane dataset. Among the 12 models tested, the DeiT3-Small model showed the highest performance with 93.79% accuracy, 91.27% precision, and 90.96% F1-score. These results highlight that rapid, accurate, and automatic disease diagnosis systems developed using deep learning techniques can significantly improve sugarcane disease management and contribute to increased yields.

show abstract

Sugarcane stem node detection and localization for cutting using deep learning

Cited by 7 publications

References 27 publications

Sugarcane stem node identification algorithm based on improved YOLOv5

Sugarcane stem node identification algorithm based on improved YOLOv5

Continuous and Impact Cutting in Mechanized Sugarcane Harvest: Quality, Losses and Impurities

Data-Efficient Vision Transformer Models for Robust Classification of Sugarcane

Contact Info

Product

Resources

About