Lightweight visual detection approach for apple ripeness perception in intelligent orchard harvesting scenarios
4 affiliations
- 1Modern Agricultural Engineering Key Laboratory at Universities of Education Department of Xinjiang Uygur Autonomous Region, Tarim University
- 2Key Laboratory of Tarim Oasis Agriculture (Tarim University), Ministry of Education, Tarim University
- 3Xinjiang Production and Construction Corps Key Laboratory of Utilization and Equipment of Special Agricultural and Forestry Products in Southern Xinjiang, Tarim University
- 4College of Biological and Agricultural Engineering, Jilin University
Abstract
Apple ripeness detection in complex orchard scenarios is plagued by fruit occlusion, overlapping, intense illumination interference, and subtle maturity feature differences among similar fruits. Conventional lightweight detection models also suffer from low accuracy and severe feature loss in field environments. To address these problems, this paper proposes a real-time lightweight method for apple ripeness detection with optimized multi-dimensional network structures, which balances lightweight deployment and feature perception capability for complex orchard backgrounds. Specifically, depthwise convolutions replace standard convolutions at the backbone tail to reduce redundant computation. A parameter-free SimAM attention mechanism is integrated into the C2PSA module to enhance valid feature extraction of apples under complex backgrounds. Additionally, adaptive downsampling (ADown) is adopted in the neck network to replace traditional downsampling structures, preserving fruit texture and color details and mitigating feature degradation. A multi-category orchard dataset containing red, green, and red-green striped apples is constructed, covering variable illumination, fruit occlusion, and dense stacking conditions. Ablation, comparative, and generalization experiments are conducted to verify model performance. The results show that compared with YOLOv11n, the proposed method achieves 8.6%, 9.5%, 8.9%, 10.9%, and 24.4% improvements in precision, recall, F1-score, mAP50, and mAP50-95, respectively. Its parameters and computational complexity are reduced by 12.8% (2.25 M) and 25.4% (4.7 GFLOPs), with an inference speed of 109 FPS. As a zero-cost feature optimization module, SimAM effectively eliminates classification confusion caused by apples with similar color and appearance. The optimized model presents superior illumination robustness, generalization ability, and convergence performance. It achieves a favorable trade-off between detection accuracy, model size, and inference speed, enabling real-time edge deployment in field orchards. This study provides technical support for intelligent ripeness detection and automatic grading of orchard fruits.
Related
- Multi-scale lodging in rice and wheat: bridging biomechanical traits, phenotypic detection, and intelligent harvesting systems
- Deep learning-based detection of construction waste in complex scenarios with an improved lightweight algorithm
- DTL-YOLO: a lightweight model for real-time tobacco leaf damage detection and mechanical harvesting quality assessment
- A lightweight edge-deployable detection method for sugarcane stem nodes in intelligent seed cane cutting equipment
- Robotic Fruit Harvesting Systems: Integration of Perception, Manipulation, and Detachment for Autonomous Harvesting
BibTeX
@article{wu2026lightweight,
title = {{Lightweight visual detection approach for apple ripeness perception in intelligent orchard harvesting scenarios}},
author = {Mingqing Wu and Jianglei Xiao and Yanjun Chen and Yuxin Xia and Guangjian Ying and Yichuan He and Feng Han},
journal = {Frontiers in Plant Science},
year = {2026},
month = oct,
doi = {10.3389/fpls.2026.1956031},
url = {https://www.frontiersin.org/articles/10.3389/fpls.2026.1956031/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Lightweight visual detection approach for apple ripeness perception in intelligent orchard harvesting scenarios
AU - Mingqing Wu
AU - Jianglei Xiao
AU - Yanjun Chen
AU - Yuxin Xia
AU - Guangjian Ying
AU - Yichuan He
AU - Feng Han
PY - 2026
DA - 2026/10/05
JO - Frontiers in Plant Science
DO - 10.3389/fpls.2026.1956031
UR - https://www.frontiersin.org/articles/10.3389/fpls.2026.1956031/full
AB - Apple ripeness detection in complex orchard scenarios is plagued by fruit occlusion, overlapping, intense illumination interference, and subtle maturity feature differences among similar fruits. Conventional lightweight detection models also suffer from low accuracy and severe feature loss in field environments. To address these problems, this paper proposes a real-time lightweight method for apple ripeness detection with optimized multi-dimensional network structures, which balances lightweight deployment and feature perception capability for complex orchard backgrounds. Specifically, depthwise convolutions replace standard convolutions at the backbone tail to reduce redundant computation. A parameter-free SimAM attention mechanism is integrated into the C2PSA module to enhance valid feature extraction of apples under complex backgrounds. Additionally, adaptive downsampling (ADown) is adopted in the neck network to replace traditional downsampling structures, preserving fruit texture and color details and mitigating feature degradation. A multi-category orchard dataset containing red, green, and red-green striped apples is constructed, covering variable illumination, fruit occlusion, and dense stacking conditions. Ablation, comparative, and generalization experiments are conducted to verify model performance. The results show that compared with YOLOv11n, the proposed method achieves 8.6%, 9.5%, 8.9%, 10.9%, and 24.4% improvements in precision, recall, F1-score, mAP50, and mAP50-95, respectively. Its parameters and computational complexity are reduced by 12.8% (2.25 M) and 25.4% (4.7 GFLOPs), with an inference speed of 109 FPS. As a zero-cost feature optimization module, SimAM effectively eliminates classification confusion caused by apples with similar color and appearance. The optimized model presents superior illumination robustness, generalization ability, and convergence performance. It achieves a favorable trade-off between detection accuracy, model size, and inference speed, enabling real-time edge deployment in field orchards. This study provides technical support for intelligent ripeness detection and automatic grading of orchard fruits.
SN - 1664-462X
ER -