UCA-YOLOv8n: a real-time and efficient fruit chunks detection algorithm for meal-assistance robot

Background The advancement of assistive technologies for individuals with disabilities has increased the demand for efficient and accurate object detection algorithms, particularly in meal-assistance robots designed to identify and handle food items such as fruit chunks. However, existing algorithms...

Full description

Saved in:
Bibliographic Details
Main Authors: Fei Liu, Mingyue Hu
Format: Article
Language:English
Published: PeerJ Inc. 2025-04-01
Series:PeerJ Computer Science
Subjects:
Online Access:https://peerj.com/articles/cs-2832.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849698588132638720
author Fei Liu
Mingyue Hu
author_facet Fei Liu
Mingyue Hu
author_sort Fei Liu
collection DOAJ
description Background The advancement of assistive technologies for individuals with disabilities has increased the demand for efficient and accurate object detection algorithms, particularly in meal-assistance robots designed to identify and handle food items such as fruit chunks. However, existing algorithms for fruit chunk detection often suffer from prolonged inference times and insufficient accuracy. Methods We propose an improved YOLOv8n algorithm optimized for real-time, high-accuracy fruit chunk detection. The Universal Inverted Bottleneck (UIB) module has been integrated into the original C2f structure, significantly reducing the model’s parameter count while preserving detection accuracy. Furthermore, the coordinate attention (CA) mechanism has been incorporated into the detection head to enhance the focus on fruit chunk regions within complex backgrounds while suppressing irrelevant features, thus improving detection performance. Additionally, the ADown module from YOLOv9 has been embedded into the YOLOv8 backbone network, further increasing accuracy and reducing the number of parameters. Results Experimental results indicate that these enhancements substantially improve detection accuracy while reducing model size. Specifically, the optimized model achieves a 1.9 MB reduction in size, a decrease of 2.5 GFLOPs in parameter count, and an increase in mAP50 and mAP50-95 by 2.1% and 3.3%, respectively. The improved algorithm (UCA-YOLOv8n) enables real-time, accurate detection of various fruit chunks. Comparative analyses with other mainstream object detection algorithms further demonstrate the superiority and effectiveness of the proposed method.
format Article
id doaj-art-766cd4fb4d404285a78417c4d7de7a4e
institution DOAJ
issn 2376-5992
language English
publishDate 2025-04-01
publisher PeerJ Inc.
record_format Article
series PeerJ Computer Science
spelling doaj-art-766cd4fb4d404285a78417c4d7de7a4e2025-08-20T03:18:52ZengPeerJ Inc.PeerJ Computer Science2376-59922025-04-0111e283210.7717/peerj-cs.2832UCA-YOLOv8n: a real-time and efficient fruit chunks detection algorithm for meal-assistance robotFei LiuMingyue HuBackground The advancement of assistive technologies for individuals with disabilities has increased the demand for efficient and accurate object detection algorithms, particularly in meal-assistance robots designed to identify and handle food items such as fruit chunks. However, existing algorithms for fruit chunk detection often suffer from prolonged inference times and insufficient accuracy. Methods We propose an improved YOLOv8n algorithm optimized for real-time, high-accuracy fruit chunk detection. The Universal Inverted Bottleneck (UIB) module has been integrated into the original C2f structure, significantly reducing the model’s parameter count while preserving detection accuracy. Furthermore, the coordinate attention (CA) mechanism has been incorporated into the detection head to enhance the focus on fruit chunk regions within complex backgrounds while suppressing irrelevant features, thus improving detection performance. Additionally, the ADown module from YOLOv9 has been embedded into the YOLOv8 backbone network, further increasing accuracy and reducing the number of parameters. Results Experimental results indicate that these enhancements substantially improve detection accuracy while reducing model size. Specifically, the optimized model achieves a 1.9 MB reduction in size, a decrease of 2.5 GFLOPs in parameter count, and an increase in mAP50 and mAP50-95 by 2.1% and 3.3%, respectively. The improved algorithm (UCA-YOLOv8n) enables real-time, accurate detection of various fruit chunks. Comparative analyses with other mainstream object detection algorithms further demonstrate the superiority and effectiveness of the proposed method.https://peerj.com/articles/cs-2832.pdfFruit chunks detectionYOLOv8 algorithmUniversal inverted bottleneckCoordinate attentionADown
spellingShingle Fei Liu
Mingyue Hu
UCA-YOLOv8n: a real-time and efficient fruit chunks detection algorithm for meal-assistance robot
PeerJ Computer Science
Fruit chunks detection
YOLOv8 algorithm
Universal inverted bottleneck
Coordinate attention
ADown
title UCA-YOLOv8n: a real-time and efficient fruit chunks detection algorithm for meal-assistance robot
title_full UCA-YOLOv8n: a real-time and efficient fruit chunks detection algorithm for meal-assistance robot
title_fullStr UCA-YOLOv8n: a real-time and efficient fruit chunks detection algorithm for meal-assistance robot
title_full_unstemmed UCA-YOLOv8n: a real-time and efficient fruit chunks detection algorithm for meal-assistance robot
title_short UCA-YOLOv8n: a real-time and efficient fruit chunks detection algorithm for meal-assistance robot
title_sort uca yolov8n a real time and efficient fruit chunks detection algorithm for meal assistance robot
topic Fruit chunks detection
YOLOv8 algorithm
Universal inverted bottleneck
Coordinate attention
ADown
url https://peerj.com/articles/cs-2832.pdf
work_keys_str_mv AT feiliu ucayolov8narealtimeandefficientfruitchunksdetectionalgorithmformealassistancerobot
AT mingyuehu ucayolov8narealtimeandefficientfruitchunksdetectionalgorithmformealassistancerobot