Abstract
In this paper, we present an approach to create spatio-temporal maps using deep learning to visualize cotton bloom appearance over time. Specifically, we manually annotate cotton flower image data and train three state-of-the-art fast deep neural network models to count cotton blooms and their frequency over time prior to harvesting. We use the detection results of the best performing model combined with traditional pixel-based image analysis methods to create a map of where past and future blooms grow on a mid-stage cotton plant. The training results of our best model show a visual understanding of how many cotton flowers grow with high F1 Score of more than 0.95, a true positive rate of 98%, false negative and false positive rates both under 10%, and millisecond-scale inference time for real-time processing.
Abstract from the paper’s OpenAlex record, shown for indexing and research. Copyright remains with the authors or the publisher. 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 4
Claim · model-written summary
The best model counted cotton flowers with F1 score above 0.95.
- Taxon
- Cotton
Gossypium hirsutumt0 - Outcome
- F1 Scoree0
- Value
- more than 0.95e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“The training results of our best model show a visual understanding of how many cotton flowers grow with high F1 Score of more than 0.95, a true positive rate of 98%, false negative and false positive rates both under 10%, and millisecond-scale inference time for real-time processing”
t0“Cotton”
Claim · model-written summary
The model had a 98% true positive rate.
- Taxon
- CottonGossypium hirsutumt0
- Outcome
- true positive ratee0
- Value
- 98%e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“a true positive rate of 98%”
t0“Cotton”
Claim · model-written summary
False negative and false positive rates were both under 10%.
- Taxon
- CottonGossypium hirsutumt0
- Outcome
- false negative and false positive ratese0
- Value
- under 10%e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“false negative and false positive rates both under 10%”
t0“Cotton”
Claim · model-written summary
Inference time was on a millisecond scale.
- Taxon
- CottonGossypium hirsutumt0
- Outcome
- inference timee0
- Value
- millisecond-scalee0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“millisecond-scale inference time for real-time processing”
t0“Cotton”