Abstract
Fast and accurate object detection is an important and challenging task in the context of automated apple harvesting. However, the current object detection models have relatively large network parameters. In this work, improvements have been made to the object detection algorithm based on YOLOv5s, by replacing the original model’s backbone network with the ShuffleNetV2 lightweight network structure. To compensate for the reduction in model parameters, this paper introduces the ECA mechanism and SPPF module after the ShuffleNetV2 modules to improve the model’s accuracy. Experimental results demonstrate that the improved lightweight YOLOv5s network reduces the parameter count by 85.6%, decreases computational load by 87.3%, and achieves a detection accuracy mAP@0.5 of 97.0% for apple detection, which is 0.4% higher than the original YOLOv5s model. The detection frame rate has also improved by 15 FPS compared to the original model, making it suitable for practical apple detection in real-world environments.
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 5
Claim · model-written summary
The improved detector reduced parameter count by 85.6%.
- Taxon
- apple
Malus domesticat0 - Outcome
- parameter counte0
- Direction
- reducese0
- Value
- 85.6%e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“improved lightweight YOLOv5s network reduces the parameter count by 85.6%”
t0“Apple”
Claim · model-written summary
The improved detector reduced computational load by 87.3%.
- Taxon
- appleMalus domesticat0
- Outcome
- computational loade0
- Direction
- decreasese0
- Value
- 87.3%e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“improved lightweight YOLOv5s network reduces the parameter count by 85.6%, decreases computational load by 87.3%”
t0“Apple”
Claim · model-written summary
Apple detection accuracy reached mAP@0.5 of 97.0%.
- Taxon
- appleMalus domesticae0
- Outcome
- detection accuracy mAP@0.5e0
- Value
- 97.0%e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“achieves a detection accuracy mAP@0.5 of 97.0% for apple detection”
Claim · model-written summary
Detection accuracy was 0.4% higher than the original YOLOv5s.
- Taxon
- appleMalus domesticae0
- Outcome
- apple detectione0
- Direction
- highere0
- Value
- 0.4%e0
- Comparator
- original YOLOv5s modele0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“apple detection, which is 0.4% higher than the original YOLOv5s model”
Claim · model-written summary
Detection frame rate improved by 15 FPS relative to the original model.
- Taxon
- appleMalus domesticat0
- Outcome
- detection frame ratee0
- Direction
- improvede0
- Value
- 15 FPSe0
- Comparator
- original modele0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“The detection frame rate has also improved by 15 FPS compared to the original model”
t0“Apple”