A scalable multi-modal learning fruit detection algorithm for dynamic environments
Frontiers in Neurorobotics · 07.02.2025 · 18
DOI: 10.3389/fnbot.2024.1518878 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Neurorobotics, online erschienen am 07.02.2025. Verfasst von Liang Mao und 5 weiteren Autor:innen. Beteiligte Einrichtung: Guangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence Application Technology Research Institute, Shenzhen Polytechnic University, Shenzh…. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
To enhance the detection of litchi fruits in natural scenes, address challenges such as dense occlusion and small target identification, this paper proposes a novel multimodal target detection method, denoted as YOLOv5-Litchi.
Methods
Initially, the Neck layer network of YOLOv5s is simplified by changing its FPN+PAN structure to an FPN structure and increasing the number of detection heads from 3 to 5. Additionally, the detection heads with resolutions of 80 × 80 pixels and 160 × 160 pixels are replaced by TSCD detection heads to enhance the model's ability to detect small targets. Subsequently, the positioning loss function is replaced with the EIoU loss function, and the confidence loss is substituted by VFLoss to further improve the accuracy of the detection bounding box and reduce the missed detection rate in occluded targets. A sliding slice method is then employed to predict image targets, thereby reducing the miss rate of small targets.
Results
Experimental results demonstrate that the proposed model improves accuracy, recall, and mean average precision (mAP) by 9.5, 0.9, and 12.3 percentage points, respectively, compared to the original YOLOv5s model. When benchmarked against other models such as YOLOx, YOLOv6, and YOLOv8, the proposed model's AP value increases by 4.0, 6.3, and 3.7 percentage points, respectively.
Discussion
The improved network exhibits distinct improvements, primarily focusing on enhancing the recall rate and AP value, thereby reducing the missed detection rate which exhibiting a reduced number of missed targets and a more accurate prediction frame, indicating its suitability for litchi fruit detection. Therefore, this method significantly enhances the detection accuracy of mature litchi fruits and effectively addresses the challenges of dense occlusion and small target detection, providing crucial technical support for subsequent litchi yield estimation.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Guangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence Application Technology Research Institute, Shenzhen Polytechnic University, Shenzhen, China.
- School of Computer Science and Software Engineering, University of Science and Technology Liaoning, Anshan, China.
Zitieren
APA
Mao, L., Guo, Z., Liu, M., Li, Y., Wang, L., & Li, J. (2025). A scalable multi-modal learning fruit detection algorithm for dynamic environments. Frontiers in Neurorobotics, 18. https://doi.org/10.3389/fnbot.2024.1518878
Vancouver
Mao L, Guo Z, Liu M, Li Y, Wang L, Li J. A scalable multi-modal learning fruit detection algorithm for dynamic environments. Frontiers in Neurorobotics. 2025;18. doi:10.3389/fnbot.2024.1518878
BibTeX
@article{Mao2025,
author = {Mao, Liang and Guo, Zihao and Liu, Mingzhe and Li, Yue and Wang, Linlin and Li, Jie},
title = {A scalable multi-modal learning fruit detection algorithm for dynamic environments},
journal = {Frontiers in Neurorobotics},
year = {2025},
volume = {18},
doi = {10.3389/fnbot.2024.1518878}
}
EUVIMED