Abstract
The high cost of manual weed control and the overuse of herbicides restrict the yield and quality of soybean. Intelligent mechanical weeding and precise application of pesticides can be used as effective alternatives for weed control in the field, and these require accurate distinction between crops and weeds. In this paper, images of soybean seedlings and weeds in different growth areas are used as datasets. In the aspect of soybean recognition, this paper designs a YOLOv8nGP algorithm with a backbone network optimisation based on GhostNet and an unconstrained pruning method with a 60% pruning rate. Compared with the original YOLOv8n, the YOLOv8nGP improves the Precision (P), Recall (R), and F1 metrics by 1.1% each, reduces the model size by 3.6 mb, and the inference time was 2.2 ms, which could meet the real-time requirements of field operations. In terms of weed recognition, this study utilises an image segmentation method based on the Normalized Excess Green Index (NExG). After filtering the soybean seedlings, the green parts of the image are extracted for weed recognition, which reduces the dependence on the diversity of the weed datasets. This study combines deep learning with traditional algorithms, which provides a new solution for weed recognition of soybean seedlings.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. 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 6
Claim · model-written summary
YOLOv8nGP improved soybean recognition precision by 1.1% over YOLOv8n.
- Taxon
- soybean
Glycine maxt0 - Outcome
- Precision (P)e0
- Direction
- improvese0
- Value
- 1.1%e0
- Comparator
- original YOLOv8ne0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Compared with the original YOLOv8n, the YOLOv8nGP improves the Precision (P), Recall (R), and F1 metrics by 1.1% each”
t0“Soybean”
Claim · model-written summary
YOLOv8nGP improved soybean recognition recall by 1.1% over YOLOv8n.
- Taxon
- soybeanGlycine maxt0
- Outcome
- Recall (R)e0
- Direction
- improvese0
- Value
- 1.1%e0
- Comparator
- original YOLOv8ne0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Compared with the original YOLOv8n, the YOLOv8nGP improves the Precision (P), Recall (R), and F1 metrics by 1.1% each”
t0“Soybean”
Claim · model-written summary
YOLOv8nGP improved soybean recognition F1 by 1.1% over YOLOv8n.
- Taxon
- soybeanGlycine maxt0
- Outcome
- F1 metricse0
- Direction
- improvese0
- Value
- 1.1%e0
- Comparator
- original YOLOv8ne0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Compared with the original YOLOv8n, the YOLOv8nGP improves the Precision (P), Recall (R), and F1 metrics by 1.1% each”
t0“Soybean”
Claim · model-written summary
YOLOv8nGP reduced model size by 3.6 mb.
Not reportedTaxon
Verbatim
e0“reduces the model size by 3.6 mb”
t0“Soybean”
Claim · model-written summary
YOLOv8nGP inference time was 2.2 ms.
Not reportedTaxon
Verbatim
e0“the inference time was 2.2 ms”
t0“Soybean”
Claim · model-written summary
The segmentation method reduced dependence on weed dataset diversity.
Not reportedTaxonComparator
Verbatim
e0“which reduces the dependence on the diversity of the weed datasets”
t0“Soybean”