Yu Longzhen

Mr. Yu Longzhen


Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 May 2026 in Agriculture
Verified
Journal Article
Open access
PDF file
YLYu Longzhen
Yu Longzhen
雨谢雨莎 谢
雨莎 谢
KZKai Zhang
Kai Zhang
ZLZhiwei Li
Zhiwei Li
GHGuogang Huang
Guogang Huang
Changyu LiuChangyu Liu
Changyu Liu
This study focuses on developing a lightweight litchi maturity detection model for complex orchard environments. Maturity detection in orchards remains challenging due to variable illumination, dense fruit clustering, and subtle visual differences among maturity stages. Moreover, many existing approaches rely on heavyweight architectures with high computational costs, limiting deployment on resource-constrained edge devices in agriculture. To address these issues, we propose EMSC-YOLO, a lightweight and efficient detector for litchi maturity detection. The model incorporates a novel Efficient Multi-Scale Convolution (EMSConv) module to enhance multi-scale feature representation while reducing redundant computation and parameters. In addition, the standard C2f module is redesigned as C2f-EMSC to improve feature reuse and cross-channel interaction within a compact architecture, enabling effective detection of densely distributed litchi fruits. Experiments on the Complex Orchard Environments Oriented Litchi Maturity (COEOLM) dataset demonstrate the effectiveness of the proposed approach. Compared with YOLOv10n on the COEOLM test set, EMSC-YOLO achieves a precision of 87.7% and reduces the number of parameters by 15.5% to only 4.02 M. EMSC-YOLO improves mAP@0.5 by 2.81 percentage points and 1.48 percentage points over YOLOv10n and YOLO11, respectively. Meanwhile, EMSC-YOLO maintains a high inference speed of 129.32 FPS, with only a 3.69% relative decrease in FPS compared with the baseline YOLOv10n whose FPS is 134.28, satisfying the real-time detection requirements of orchard edge scenarios. Overall, the proposed method provides a deployable solution for real-time litchi maturity detection in complex orchard environments and can be extended to maturity detection tasks for other clustered fruit crops.

14 February 2026 in Horticulturae
Verified
Journal Article
Open access
PDF file
ZLZhiwei Li
Zhiwei Li
雨谢雨莎 谢
雨莎 谢
JWJingjie Wang
Jingjie Wang
GHGuogang Huang
Guogang Huang
YLYu Longzhen
Yu Longzhen
Changyu LiuChangyu Liu
Changyu Liu
Wampee (Clausena lansium) harvesting currently relies heavily on manual labor, but automation is significantly hindered by clustered fruit growth patterns, small fruit sizes, and complex orchard backgrounds, which make accurate detection highly challenging. This study proposes Wampee-YOLO, a lightweight and high-precision model based on the YOLO11n architecture, specifically designed for real-time wampee detection in natural orchard environments. The proposed model integrates several architectural enhancements: the RFEMAConv module for expanded receptive fields, an AIFI module for improved small target interaction, and a C2PSA-MSCADYT structure to boost multi-scale adaptability. Additionally, a Triplet Attention mechanism strengthens multi-dimensional feature representation, while an AFPN-Pro2345 neck structure optimizes cross-scale feature fusion. Experimental results demonstrate that Wampee-YOLO achieves an mAP50 of 90.3%, a precision of 92.1%, and F1 score of 87%. This represents a significant 3.4% mAP50 improvement over the YOLO11n baseline, with a slight increase to 3.28 M parameters. Ablation studies further confirm that the AFPN-Pro2345 module provides the most substantial performance gain, increasing mAP50 by 2.4%. The model effectively balances computational efficiency with detection accuracy. These findings indicate that Wampee-YOLO offers a robust and efficient visual detection solution suitable for deployment on resource-constrained edge devices in smart orchard applications.