Abstract
Cotton is a major industrial crop and a primary raw material for textiles worldwide. Intelligently detecting pests and diseases is crucial for automating cotton cultivation management. This study proposed a cross-platform detection method for cotton pests and diseases using unmanned aerial vehicle (UAV) and smartphone imaging. The method employed a self-built improved YOLO, namely CPD-YOLO. The bidirectional feature pyramid network with the reparameterization vision transformer was constructed to achieve an optimal balance between multi-scale feature fusion and inference efficiency. Secondly, the head network, featuring four dynamic detection heads, was designed to enhance the multi-dimensional dynamic awareness capability. Finally, the Inner-Shape intersection over union was proposed as the bounding box regression loss function, which can improve positioning accuracy and accelerate convergence. The improvement strategy significantly improved the detection accuracy of multi-scale objects in cross-platform scenarios. Compared with the original model, the F1-score and mean average precision (mAP) were increased by 7.44 % and 7.08 %, respectively. The CPD-YOLO also outperformed typical object detection models, with an F1-score of 88.86 % and a mAP of 90.42 %. Moreover, the CPD-YOLO model had superior generalization capability, with a 1.30 % decrease in F1-score and a 0.55 % decrease in mAP. Furthermore, a mobile application named Doctor Cotton, utilizing the CPD-YOLO, was developed. It promises to be a new farming tool for the real-time and accurate detection of cotton pests and diseases. These findings provide a valuable reference for the cross-platform application of consumer-grade UAVs and smartphones in detecting other crop pests and diseases.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by-nc-nd. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 8
Claim · model-written summary
The improvement strategy improved multi-scale object detection accuracy in cross-platform scenarios.
- Taxon
- cotton
Gossypium hirsutumt0 - Outcome
- detection accuracy of multi-scale objectse0
- Direction
- improvede0
- Comparator
- cross-platform scenariose0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“The improvement strategy significantly improved the detection accuracy of multi-scale objects in cross-platform scenarios.”
t0“cotton pests and diseases”
Claim · model-written summary
CPD-YOLO increased F1-score by 7.44 % versus the original model.
- Taxon
- cottonGossypium hirsutumt0
- Outcome
- F1-scoree0
- Direction
- increasede0
- Value
- 7.44 %e0
- Comparator
- original modele0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Compared with the original model, the F1-score and mean average precision (mAP) were increased by 7.44 % and 7.08 %, respectively.”
t0“cotton pests and diseases”
Claim · model-written summary
CPD-YOLO increased mAP by 7.08 % versus the original model.
- Taxon
- cottonGossypium hirsutumt0
- Outcome
- mean average precision (mAP)e0
- Direction
- increasede0
- Value
- 7.08 %e0
- Comparator
- original modele0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Compared with the original model, the F1-score and mean average precision (mAP) were increased by 7.44 % and 7.08 %, respectively.”
t0“cotton pests and diseases”
Claim · model-written summary
CPD-YOLO outperformed typical detectors with an F1-score of 88.86 %.
- Taxon
- cottonGossypium hirsutumt0
- Outcome
- F1-scoree0
- Direction
- outperformede0
- Value
- 88.86 %e0
- Comparator
- typical object detection modelse0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“The CPD-YOLO also outperformed typical object detection models, with an F1-score of 88.86 % and a mAP of 90.42 %.”
t0“cotton pests and diseases”
Claim · model-written summary
CPD-YOLO outperformed typical detectors with mAP of 90.42 %.
- Taxon
- cottonGossypium hirsutumt0
- Outcome
- mAPe0
- Direction
- outperformede0
- Value
- 90.42 %e0
- Comparator
- typical object detection modelse0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“The CPD-YOLO also outperformed typical object detection models, with an F1-score of 88.86 % and a mAP of 90.42 %.”
t0“cotton pests and diseases”
Claim · model-written summary
CPD-YOLO generalization showed a 1.30 % F1-score decrease.
- Taxon
- cottonGossypium hirsutumt0
- Outcome
- F1-scoree0
- Direction
- decreasee0
- Value
- 1.30 %e0
Not reportedComparator
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“the CPD-YOLO model had superior generalization capability, with a 1.30 % decrease in F1-score and a 0.55 % decrease in mAP.”
t0“cotton pests and diseases”
Claim · model-written summary
CPD-YOLO generalization showed a 0.55 % mAP decrease.
- Taxon
- cottonGossypium hirsutumt0
- Outcome
- mAPe0
- Direction
- decreasee0
- Value
- 0.55 %e0
Not reportedComparator
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“the CPD-YOLO model had superior generalization capability, with a 1.30 % decrease in F1-score and a 0.55 % decrease in mAP.”
t0“cotton pests and diseases”
Claim · model-written summary
A mobile application named Doctor Cotton using CPD-YOLO was developed.
- Taxon
- cottonGossypium hirsutumt0
- Outcome
- Doctor Cottone0
Not reportedComparatorValue
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“a mobile application named Doctor Cotton, utilizing the CPD-YOLO, was developed.”
t0“cotton pests and diseases”