2023
DOI: 10.3390/plants12051191
|View full text |Cite
|
Sign up to set email alerts
|

A High Performance Wheat Disease Detection Based on Position Information

Abstract: Protecting wheat yield is a top priority in agricultural production, and one of the important measures to preserve yield is the control of wheat diseases. With the maturity of computer vision technology, more possibilities have been provided to achieve plant disease detection. In this study, we propose the position attention block, which can effectively extract the position information from the feature map and construct the attention map to improve the feature extraction ability of the model for the region of … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
6
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 21 publications
(9 citation statements)
references
References 25 publications
0
6
0
Order By: Relevance
“…CA is an attention mechanism that can efficiently obtain inter-channel information and position information at the same time. The CA module encodes channel relationships and longrange dependencies with precise location information [21], thereby helping the network locate objects of interest more accurately. Additionally, we replaced the CIoU in the original network with the more advanced EIoU for the loss function, enhancing the aspect ratio loss by considering the difference between the prediction and the minimum bounding box size.…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…CA is an attention mechanism that can efficiently obtain inter-channel information and position information at the same time. The CA module encodes channel relationships and longrange dependencies with precise location information [21], thereby helping the network locate objects of interest more accurately. Additionally, we replaced the CIoU in the original network with the more advanced EIoU for the loss function, enhancing the aspect ratio loss by considering the difference between the prediction and the minimum bounding box size.…”
Section: Discussionmentioning
confidence: 99%
“…Reference [20] proposed a method that redesigns the feature extractor, utilizes a multi-scale object proposal network (MS-OPN) for object-like region generation, and employs an accurate object detection network (AODN) for object detection based on fused feature maps. [21] Reference [22] introduced the CSand-Glass module to replace the residual module in the backbone feature extraction network of YOLOv5, achieving higher accuracy and speed in remote sensing images. Liu et al proposed the YOLO-extract algorithm [23], which optimizes the model structure of YOLOv5 in two main ways.…”
Section: Remote Sensing Object Detection Based On Deep Learningmentioning
confidence: 99%
“…where N Q is the number of peaks in the query spectrum and N BO is the number of peaks in the query and reference spectra, respectively; 15,16 In recent years, CNNs have been able to efficiently process these complex MS data by automatically learning the features in mass spectra. During the training process, CNNs can learn how to recognize and distinguish target compounds from other irrelevant compounds, and this ability makes CNNs a powerful tool for MS data analysis.…”
Section: Mass Spectral Similaritymentioning
confidence: 99%
“…This introduction resulted in highly accurate predictions of crop diseases. Cheng et al. (2023) proposed a Position Attention Block that effectively extracts positional information from feature maps and constructs attention maps to bolster the feature extraction ability.…”
Section: Related Workmentioning
confidence: 99%