Abstract
Efficient and accurate apple detection is crucial for the operation of apple-picking robots. To improve detection accuracy and speed, we propose a lightweight apple-detection model based on the YOLOv8n framework. The proposed model introduces a novel Self-Calibrated Coordinate (SCC) attention module, which enhances feature extraction, especially for partially occluded apples, by effectively capturing spatial and channel information. Additionally, we replace the C2f module within the YOLOv8n neck with a Partial Convolution Module improved with Reparameterization (PCMR), which accelerates detection, reduces redundant computations, and minimizes both parameter count and memory access during inference. To further optimize the model, we fuse multi-scale features from the second and third pyramid levels of the backbone architecture, achieving a lightweight design suitable for real-time detection. To address missed detections and misclassifications, Polynomial Loss (PolyLoss) is integrated, enhancing class discrimination for different apple subcategories. Compared to the original YOLOv8n, the improved model increases the mAP by 2.90% to 88.90% and improves the detection speed to 220 FPS, which is 30.55% faster. Additionally, it reduces the parameter count by 89.36% and the FLOPs by 2.47%. Experimental results demonstrate that the proposed model outperforms mainstream object-detection algorithms, including Faster R-CNN, RetinaNet, SSD, RT-DETR-R18, RT-DETR-R34, YOLOv5n, YOLOv6-N, YOLOv7-tiny, YOLOv8n, YOLOv9-T and YOLOv11n, in both mAP and detection speed. Notably, the improved model has been used to develop an Android application deployed on the iQOO Neo6 SE smartphone, achieving a 40 FPS detection speed, a 26.93% improvement over the corresponding deployment of YOLOv8n, enabling real-time apple detection. This study provides a valuable reference for designing efficient and lightweight detection models for resource-constrained apple-picking robots.
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
The improved model raised apple detection mAP by 2.90% to 88.90% versus YOLOv8n.
- Taxon
- Apple
Malus domesticat0 - Outcome
- mAPe0
- Direction
- increasese0
- Value
- 2.90%e0
- Qualifier
- 88.90%e0
- Comparator
- original YOLOv8ne0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Compared to the original YOLOv8n, the improved model increases the mAP by 2.90% to 88.90%”
t0“Apple Detection”
Claim · model-written summary
Detection speed reached 220 FPS, 30.55% faster than YOLOv8n.
- Taxon
- AppleMalus domesticat0
- Outcome
- detection speede0
- Direction
- fastere0
- Value
- 220 FPSe0
- Qualifier
- 30.55%e0
- Comparator
- original YOLOv8ne1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“improves the detection speed to 220 FPS, which is 30.55% faster”
e1“Compared to the original YOLOv8n”
t0“Apple Detection”
Claim · model-written summary
The model reduced parameter count by 89.36%.
- Taxon
- AppleMalus domesticat0
- Outcome
- parameter counte0
- Direction
- reducese0
- Value
- 89.36%e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“reduces the parameter count by 89.36%”
t0“Apple Detection”
Claim · model-written summary
The model reduced FLOPs by 2.47%.
- Taxon
- AppleMalus domesticat0
- Outcome
- FLOPse0
- Value
- 2.47%e0
Not reportedDirection
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“the FLOPs by 2.47%”
e1“reduces the parameter count by 89.36% and the FLOPs by 2.47%”
t0“Apple Detection”
Claim · model-written summary
The model outperformed the listed object detection algorithms in mAP and speed.
- Taxon
- AppleMalus domesticat0
- Outcome
- mAP and detection speede0
- Direction
- outperformse0
- Comparator
- mainstream object-detection algorithmse0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“the proposed model outperforms mainstream object-detection algorithms, including Faster R-CNN, RetinaNet, SSD, RT-DETR-R18, RT-DETR-R34, YOLOv5n, YOLOv6-N, YOLOv7-tiny, YOLOv8n, YOLOv9-T and YOLOv11n, in both mAP and detection speed”
t0“Apple Detection”
Claim · model-written summary
Smartphone deployment achieved 40 FPS, a 26.93% gain over YOLOv8n deployment.
- Taxon
- AppleMalus domesticat0
- Outcome
- detection speede0
- Direction
- improvemente0
- Value
- 40 FPSe0
- Qualifier
- 26.93%e0
- Comparator
- corresponding deployment of YOLOv8ne0
- Setting
- iQOO Neo6 SE smartphonee0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“iQOO Neo6 SE smartphone, achieving a 40 FPS detection speed, a 26.93% improvement over the corresponding deployment of YOLOv8n”
t0“Apple Detection”