2023
DOI: 10.1049/ipr2.12788
|View full text |Cite
|
Sign up to set email alerts
|

A lightweight network of near cotton‐coloured impurity detection method in raw cotton based on weighted feature fusion

Abstract: The objective is to improve the recognition rate of white and near cotton-coloured impurities in raw cotton against a single white visible light source background. A lightweight detection network model without anchor boxes based on improved YOLO v4-tiny is proposed in this paper based on weighted feature fusion (WFF). The WFF strategy was used to improve the detection accuracy of the improved YOLO v4-tiny algorithm. Meanwhile, to address the disadvantage that the anchor boxes obtained by the K-means algorithm … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
3
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
4

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(5 citation statements)
references
References 33 publications
0
3
0
Order By: Relevance
“…Various researchers have undertaken investigations into cotton impurity detection. For instance, Xu et al (2023) FIGURE 7 Loss curves with different activation functions. employed machine vision to classify impurities in lint cotton, achieving an accuracy of 98%.…”
Section: Discussionmentioning
confidence: 99%
See 2 more Smart Citations
“…Various researchers have undertaken investigations into cotton impurity detection. For instance, Xu et al (2023) FIGURE 7 Loss curves with different activation functions. employed machine vision to classify impurities in lint cotton, achieving an accuracy of 98%.…”
Section: Discussionmentioning
confidence: 99%
“…These investigations have predominantly harnessed technical tools such as machine vision and spectroscopy techniques. Xu et al. (2023) employed machine vision in conjunction with the lightweight YOLOV4 algorithm to achieve impurity detection in lint cotton, yielding an impressive detection accuracy of 98.00%.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…They also developed an estimation model for the impurity ratio based on segmented volume and estimated mass and utilized a multithread technique to shorten the processing time, achieving a 43.65% reduction compared to that of a single thread. To improve the recognition accuracy of white and near-cotton-colored impurities in raw cotton, Xu et al (2023) proposed a weighted feature fusion module and a decoupled detection strategy to enhance the detection head of YOLOv4-tiny. The proposed method decreased computation during the inference process, boosted the speed of inference, and enhanced the accuracy of cotton impurity localization.…”
Section: Introductionmentioning
confidence: 99%
“…Image classificationbased approaches (Momin et al, 2017;Guedes and Pereira, 2019;Shen et al, 2019;Aparatana et al, 2020;Chen et al, 2020;Guedes et al, 2020;Dos Santos et al, 2021; cannot capture pixel-level information for subsequent construction of a mass-pixel fitting model. Object detection can be utilized for real-time classification and localization of crops and impurities (Zhang et al, 2022;Xu et al, 2023;, but they still cannot support subsequent mass estimation based on pixels of detected objects. Semantic segmentation, on the other hand, enables pixel-wise classification of an image and facilitates the precise determination of the number of pixels and their respective categories in a specific region.…”
Section: Introductionmentioning
confidence: 99%