Rice Ear Counting Based on Image Segmentation and Establishment of a Dataset

Shao, Hongmin; Tang, Rong; Yi, Lei; Mu, Jiong; Guan, Yan; Xiang, Ying

doi:10.3390/plants10081625

Cited by 10 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Estimating yield by deep learning is highly accurate and robust. Shao et al [ 7 ] used the LC-FCN model to detect and count rice ears, and Wu et al [ 8 ] used image processing techniques and deep learning to count the number of rice grains. Lu et al [ 9 ] proposed TasselNet to detect and count maize tassels.…”

Section: Introductionmentioning

confidence: 99%

YOLO POD: a fast and accurate multi-task model for dense Soybean Pod counting

xiang

Wang

et al. 2023

Plant Methods

View full text Add to dashboard Cite

Background The number of soybean pods is one of the most important indicators of soybean yield, pod counting is crucial for yield estimation, cultivation management, and variety breeding. Counting pods manually is slow and laborious. For crop counting, using object detection network is a common practice, but the scattered and overlapped pods make the detection and counting of the pods difficult. Results We propose an approach that we named YOLO POD, based on the YOLO X framework. On top of YOLO X, we added a block for predicting the number of pods, modified the loss function, thus constructing a multi-task model, and introduced the Convolutional Block Attention Module (CBAM). We achieve accurate identification and counting of pods without reducing the speed of inference. The results showed that the R2 between the number predicted by YOLO POD and the ground truth reached 0.967, which is improved by 0.049 compared to YOLO X, while the inference time only increased by 0.08 s. Moreover, MAE, MAPE, RMSE are only 4.18, 10.0%, 6.48 respectively, the deviation is very small. Conclusions We have achieved the first accurate counting of soybean pods and proposed a new solution for the detection and counting of dense objects.

show abstract

Section: Introductionmentioning

confidence: 99%

YOLO POD: a fast and accurate multi-task model for dense Soybean Pod counting

xiang

Wang

et al. 2023

Plant Methods

View full text Add to dashboard Cite

show abstract

“…In recent years, machine vision-based deep learning methods have provided advanced and efficient image processing solutions in agriculture. Deep learning methods, combined with machine vision technology, have been widely used in plant disease and pest classification, including the classification of fresh tobacco leaves of various maturity levels ( Chen et al., 2021 ); the classification of tobacco plant diseases ( Lin et al., 2022 ); the classification of wheat spike blast ( Fernández-Campos et al., 2021 ); the classification of rice pests and diseases ( Yang et al., 2021 ); the detection of plant parts such as tobacco leaves and stems ( Li et al., 2021 ); the detection of tomato diseases ( Liu et al., 2022 ); the detection of wheat head diseases ( Gong et al., 2020 ); the detection of brown planthoppers in rice ( He et al., 2020 ); plant image segmentation, such as tobacco planting areas segmentation ( Huang et al., 2021 ); field-grown wheat spikes segmentation ( Tan et al., 2020 ); rice ear segmentation ( Bai-yi et al., 2020 ; Shao et al., 2021 ); rice lodging segmentation ( Su et al., 2022 ); photosynthetic and non-photosynthetic vegetation segmentation ( He et al., 2022 ); weed and crop segmentation ( Hashemi-Beni et al., 2022 ); and wheat spike segmentation ( Wen et al., 2022 ). Deep learning methods combined with machine vision technology have been utilized in research focused on the classification of tobacco shred images.…”

Section: Introductionmentioning

confidence: 99%

Overlapped tobacco shred image segmentation and area computation using an improved Mask RCNN network and COT algorithm

Wang

Jia

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

IntroductionThe classification of the four tobacco shred varieties, tobacco silk, cut stem, expanded tobacco silk, and reconstituted tobacco shred, and the subsequent determination of tobacco shred components, are the primary tasks involved in calculating the tobacco shred blending ratio. The identification accuracy and subsequent component area calculation error directly affect the composition determination and quality of the tobacco shred. However, tiny tobacco shreds have complex physical and morphological characteristics; in particular, there is substantial similarity between the expanded tobacco silk and tobacco silk varieties, and this complicates their classification. There must be a certain amount of overlap and stacking in the distribution of tobacco shreds on the actual tobacco quality inspection line. There are 24 types of overlap alone, not to mention the stacking phenomenon. Self-winding does not make it easier to distinguish such varieties from the overlapped types, posing significant difficulties for machine vision-based tobacco shred classification and component area calculation tasks.MethodsThis study focuses on two significant challenges associated with identifying various types of overlapping tobacco shreds and acquiring overlapping regions to calculate overlapping areas. It develops a new segmentation model for tobacco shred images based on an improved Mask region-based convolutional neural network (RCNN). Mask RCNN is used as the segmentation network’s mainframe. Convolutional network and feature pyramid network (FPN) in the backbone are replaced with Densenet121 and U-FPN, respectively. The size and aspect ratios of anchors parameters in region proposal network (RPN) are optimized. An algorithm for the area calculation of the overlapped tobacco shred region (COT) is also proposed, which is applied to overlapped tobacco shred mask images to obtain overlapped regions and calculate the overlapped area.ResultsThe experimental results showed that the final segmentation accuracy and recall rates are 89.1% and 73.2%, respectively. The average area detection rate of 24 overlapped tobacco shred samples increases from 81.2% to 90%, achieving high segmentation accuracy and overlapped area calculation accuracy.DiscussionThis study provides a new implementation method for the type identification and component area calculation of overlapped tobacco shreds and a new approach for other similar overlapped image segmentation tasks.

show abstract

“…Yang et al (2020) used the FPN-Mask (feature pyramid network mask) method to segment rice panicles with an accuracy of 0.99; however, the effect of rice panicle type on segmentation accuracy was not considered. Shao et al (2021) proposed a localization-based FCN combined with a watershed algorithm for dense rice panicle recognition and counting, with an accuracy of 89.88%. The aforementioned study that uses image segmentation for the actual panicle detection counts, as well as for investigating the effect of spike type on panicle detection, has limitations.…”

Section: Introductionmentioning

confidence: 99%

“…(2020) used the FPN-Mask (feature pyramid network mask) method to segment rice panicles with an accuracy of 0.99; however, the effect of rice panicle type on segmentation accuracy was not considered. Shao et al. (2021) proposed a localization-based FCN combined with a watershed algorithm for dense rice panicle recognition and counting, with an accuracy of 89.88%.…”

Section: Introductionmentioning

confidence: 99%

Universal detection of curved rice panicles in complex environments using aerial images and improved YOLOv4 model

et al. 2022

View full text Add to dashboard Cite

Accurate and rapid identification of the effective number of panicles per unit area is crucial for the assessment of rice yield. As part of agricultural development, manual observation of effective panicles in the paddy field is being replaced by unmanned aerial vehicle (UAV) imaging combined with target detection modeling. However, UAV images of panicles of curved hybrid Indica rice in complex field environments are characterized by overlapping, blocking, and dense distribution, imposing challenges on rice panicle detection models. This paper proposes a universal curved panicle detection method by combining UAV images of different types of hybrid Indica rice panicles (leaf-above-spike, spike-above-leaf, and middle type) from four ecological sites using an improved You Only Look Once version 4 (YOLOv4) model. MobileNetv2 is used as the backbone feature extraction network based on a lightweight model in addition to a focal loss and convolutional block attention module for improved detection of curved rice panicles of different varieties. Moreover, soft non-maximum suppression is used to address rice panicle occlusion in the dataset. This model yields a single image detection rate of 44.46 FPS, and mean average precision, recall, and F1 values of 90.32%, 82.36%, and 0.89%, respectively. This represents an increase of 6.2%, 0.12%, and 16.24% from those of the original YOLOv4 model, respectively. The model exhibits superior performance in identifying different strain types in mixed and independent datasets, indicating its feasibility as a general model for detection of different types of rice panicles in the heading stage.

show abstract

Rice Ear Counting Based on Image Segmentation and Establishment of a Dataset

Cited by 10 publications

References 14 publications

YOLO POD: a fast and accurate multi-task model for dense Soybean Pod counting

YOLO POD: a fast and accurate multi-task model for dense Soybean Pod counting

Overlapped tobacco shred image segmentation and area computation using an improved Mask RCNN network and COT algorithm

Universal detection of curved rice panicles in complex environments using aerial images and improved YOLOv4 model

Contact Info

Product

Resources

About