RETRACTED: WDN: A One-Stage Detection Network for Wheat Heads with High Performance

Sun, Pengshuo; Cui, Jingyi; Hu, Xuefeng; Wang, Qing

doi:10.3390/info13030153

Cited by 5 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experimental results show that the method exhibits good accuracy and efficiency in the task of wheat sheaf detection in aerial wheat field images, providing a fast and feasible solution for wheat sheaf detection in aerial UAV wheat fields. ( Sun et al., 2022b ) introduced a high-performance wheat ears detection method based on WDN (one-stage detection network), by adding an attention module and a feature fusion module to the structural backbone network, the authors realized a high-precision detection of wheat ears, and the mAP metrics of the WDN model outperformed the other models, reaching 90.3%. ( Dong et al., 2022 ) utilized lightweight backbone network with asymmetric convolution for feature extraction, after which SPSA attention was used to select the focusing location and generate more discriminative feature representations.…”

Section: Introductionmentioning

confidence: 99%

A density map-based method for counting wheat ears

Zhang,

Wang,

Liu

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

IntroductionField wheat ear counting is an important step in wheat yield estimation, and how to solve the problem of rapid and effective wheat ear counting in a field environment to ensure the stability of food supply and provide more reliable data support for agricultural management and policy making is a key concern in the current agricultural field.MethodsThere are still some bottlenecks and challenges in solving the dense wheat counting problem with the currently available methods. To address these issues, we propose a new method based on the YOLACT framework that aims to improve the accuracy and efficiency of dense wheat counting. Replacing the pooling layer in the CBAM module with a GeM pooling layer, and then introducing the density map into the FPN, these improvements together make our method better able to cope with the challenges in dense scenarios.ResultsExperiments show our model improves wheat ear counting performance in complex backgrounds. The improved attention mechanism reduces the RMSE from 1.75 to 1.57. Based on the improved CBAM, the R2 increases from 0.9615 to 0.9798 through pixel-level density estimation, the density map mechanism accurately discerns overlapping count targets, which can provide more granular information.DiscussionThe findings demonstrate the practical potential of our framework for intelligent agriculture applications.

show abstract

Section: Introductionmentioning

confidence: 99%

A density map-based method for counting wheat ears

Zhang,

Wang,

Liu

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…In recent years, many researchers have in-depth research on phenotypic measurement techniques for different crop species and crop traits and have made some progress. Sun et al [21] proposed the wheat detection network (WDN) model for wheat head detection and counting, avoiding the timeconsuming and error-prone problem of manual identification and statistics, and developed a smart wheat head counting system for iOS, which meets the requirements of displaying the number of wheat heads in a crop photo per second, achieving real-time performance. Constantino et al [22] studied a system based on image segmentation technology to automatically measure rice crop phenotypic information, using tracking and conversion to measure the height of rice crops.…”

Section: Introductionmentioning

confidence: 99%

Real-time phenotyping measurement system for vegetable leaves

Huang,

Liu,

Cheng

et al. 2024

Preprint

View full text Add to dashboard Cite

In the process of vegetable growth, leaf area phenotypic information measurement is an effective means to evaluate the growth status of vegetables. Due to the irregular leaf shape, the accuracy of leaf area measurement is low, and real-time field measurement is difficult to achieve. According to the field situation, a real-time phenotypic measurement system for vegetable leaves was designed. The vegetable leaves are collected in real-time by the detection vehicle, and the YOLACT segmentation model is used to realize the real-time measurement of vegetable leaves. By introducing the Res2Net module after adding the ECA attention mechanism into the model backbone network Resnet50, the network receptive field is expanded and the segmentation performance of the network on the leaves is improved. In the field experiment, the segmentation accuracy and detection accuracy of vegetable leaves reached 41.51% and 39.39%, respectively, and the segmentation speed was 23.10 frame/s. The results show that the designed real-time phenotypic measurement system of vegetable leaves not only meets the accurate area measurement of irregular vegetable leaves, but also realizes the real-time requirement of vegetable leaf area measurement, and improves the reliability of leaf phenotypic information to evaluate the growth status of vegetables.

show abstract

“…Besides that, Khaki et al [ 19 ] designed a lightweight wheat spike detection and counting network WheatNet using MobileNetv2 as the backbone. Based on the single-stage network framework, Sun et al [ 67 ] proposed a lightweight WDN model for wheat heading detection and counting. Nonetheless, their generalization ability is likely to be limited, and they may have limitations in capturing complex patterns and expressing complex relationships in the data.…”

Section: Introductionmentioning

confidence: 99%

WheatLFANet: in-field detection and counting of wheat heads with high-real-time global regression network

Ye,

Yu,

Wang

et al. 2023

Plant Methods

View full text Add to dashboard Cite

Background Detection and counting of wheat heads are of crucial importance in the field of plant science, as they can be used for crop field management, yield prediction, and phenotype analysis. With the widespread application of computer vision technology in plant science, monitoring of automated high-throughput plant phenotyping platforms has become possible. Currently, many innovative methods and new technologies have been proposed that have made significant progress in the accuracy and robustness of wheat head recognition. Nevertheless, these methods are often built on high-performance computing devices and lack practicality. In resource-limited situations, these methods may not be effectively applied and deployed, thereby failing to meet the needs of practical applications. Results In our recent research on maize tassels, we proposed TasselLFANet, the most advanced neural network for detecting and counting maize tassels. Building on this work, we have now developed a high-real-time lightweight neural network called WheatLFANet for wheat head detection. WheatLFANet features a more compact encoder-decoder structure and an effective multi-dimensional information mapping fusion strategy, allowing it to run efficiently on low-end devices while maintaining high accuracy and practicality. According to the evaluation report on the global wheat head detection dataset, WheatLFANet outperforms other state-of-the-art methods with an average precision AP of 0.900 and an R2 value of 0.949 between predicted values and ground truth values. Moreover, it runs significantly faster than all other methods by an order of magnitude (TasselLFANet: FPS: 61). Conclusions Extensive experiments have shown that WheatLFANet exhibits better generalization ability than other state-of-the-art methods, and achieved a speed increase of an order of magnitude while maintaining accuracy. The success of this study demonstrates the feasibility of achieving real-time, lightweight detection of wheat heads on low-end devices, and also indicates the usefulness of simple yet powerful neural network designs.

show abstract

RETRACTED: WDN: A One-Stage Detection Network for Wheat Heads with High Performance

Cited by 5 publications

References 35 publications

A density map-based method for counting wheat ears

A density map-based method for counting wheat ears

Real-time phenotyping measurement system for vegetable leaves

WheatLFANet: in-field detection and counting of wheat heads with high-real-time global regression network

Contact Info

Product

Resources

About