YOLOv8-MSP-PD: A Lightweight YOLOv8-Based Detection Method for Jinxiu Malus Fruit in Field Conditions

YOLOv8-MSP-PD: A Lightweight YOLOv8-Based Detection Method for Jinxiu Malus Fruit in Field Conditions

Accurate detection of Jinxiu Malus fruits in unstructured orchard environments is hampered by frequent overlap, occlusion, and variable illumination. To address these challenges, we propose YOLOv8-MSP-PD (YOLOv8 with Multi-Scale Pyramid Fusion and Proportional Distance IoU), a lightweight model buil...

Full description

Saved in:
Bibliographic Details
Main Authors: Yi Liu, Xiang Han, Hongjian Zhang, Shuangxi Liu, Wei Ma, Yinfa Yan, Linlin Sun, Linlong Jing, Yongxian Wang, Jinxing Wang
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Agronomy
Subjects:
Jinxiu Malus fruit
YOLOv8
lightweight
multi-scale feature fusion
object detection
Online Access:https://www.mdpi.com/2073-4395/15/7/1581
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Accurate detection of Jinxiu Malus fruits in unstructured orchard environments is hampered by frequent overlap, occlusion, and variable illumination. To address these challenges, we propose YOLOv8-MSP-PD (YOLOv8 with Multi-Scale Pyramid Fusion and Proportional Distance IoU), a lightweight model built on an enhanced YOLOv8 architecture. We replace the backbone with MobileNetV4, incorporating unified inverted bottleneck (UIB) modules and depth-wise separable convolutions for efficient feature extraction. We introduce a spatial pyramid pooling fast cross-stage partial connections (SPPFCSPC) module for multi-scale feature fusion and a modified proportional distance IoU (MPD-IoU) loss to optimize bounding-box regression. Finally, layer-adaptive magnitude pruning (LAMP) combined with knowledge distillation compresses the model while retaining performance. On our custom Jinxiu Malus dataset, YOLOv8-MSP-PD achieves a mean average precision (mAP) of 92.2% (1.6% gain over baseline), reduces floating-point operations (FLOPs) by 59.9%, and shrinks to 2.2 MB. Five-fold cross-validation confirms stability, and comparisons with Faster R-CNN and SSD demonstrate superior accuracy and efficiency. This work offers a practical vision solution for agricultural robots and guidance for lightweight detection in precision agriculture.
ISSN:2073-4395

Similar Items