Hongwen Yan

Prof. Dr. Hongwen Yan


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
28 August 2024 in Plants
Verified
Journal Article
Open access
PDF file
NMna ma
na ma
YWYulong Wu
Yulong Wu
YBYifan Bo
Yifan Bo
HYHongwen Yan
Hongwen Yan
In response to the low accuracy and slow detection speed of chili recognition in natural environments, this study proposes a chili pepper object detection method based on the improved YOLOv8n. Evaluations were conducted among YOLOv5n, YOLOv6n, YOLOv7-tiny, YOLOv8n, YOLOv9, and YOLOv10 to select the optimal model. YOLOv8n was chosen as the baseline and improved as follows: (1) Replacing the YOLOv8 backbone with the improved HGNetV2 model to reduce floating-point operations and computational load during convolution. (2) Integrating the SEAM (spatially enhanced attention module) into the YOLOv8 detection head to enhance feature extraction capability under chili fruit occlusion. (3) Optimizing feature fusion using the dilated reparam block module in certain C2f (CSP bottleneck with two convolutions). (4) Substituting the traditional upsample operator with the CARAFE(content-aware reassembly of features) upsampling operator to further enhance network feature fusion capability and improve detection performance. On a custom-built chili dataset, the F0.5-score, mAP0.5, and mAP0.5:0.95 metrics improved by 1.98, 2, and 5.2 percentage points, respectively, over the original model, achieving 96.47%, 96.3%, and 79.4%. The improved model reduced parameter count and GFLOPs by 29.5% and 28.4% respectively, with a final model size of 4.6 MB. Thus, this method effectively enhances chili target detection, providing a technical foundation for intelligent chili harvesting processes.

26 April 2023 in Plants
Verified
Journal Article
Open access
PDF file
HYHongwen Yan
Hongwen Yan
CSCai Songrui
Cai Songrui
QLQiangsheng Li
Qiangsheng Li
FTFeng Tian
Feng Tian
SKSitong Kan
Sitong Kan
MWMeimeng Wang
Meimeng Wang
Intelligent detection is vital for achieving the intelligent picking operation of daylily, but complex field environments pose challenges due to branch occlusion, overlapping plants, and uneven lighting. To address these challenges, this study selected an intelligent detection model based on YOLOv5s for daylily, the depth and width parameters of the YOLOv5s network were optimized, with Ghost, Transformer, and MobileNetv3 lightweight networks used to optimize the CSPDarknet backbone network of YOLOv5s, continuously improving the model’s performance. The experimental results show that the original YOLOv5s model increased mean average precision (mAP) by 49%, 44%, and 24.9% compared to YOLOv4, SSD, and Faster R-CNN models, optimizing the depth and width parameters of the network increased the mAP of the original YOLOv5s model by 7.7%, and the YOLOv5s model with Transformer as the backbone network increased the mAP by 0.2% and the inference speed by 69% compared to the model after network parameter optimization. The optimized YOLOv5s model provided precision, recall rate, mAP, and inference speed of 81.4%, 74.4%, 78.1%, and 93 frames per second (FPS), which can achieve accurate and fast detection of daylily in complex field environments. The research results can provide data and experimental references for developing intelligent picking equipment for daylily.

18 April 2025 in Agronomy
Verified
Journal Article
Open access
PDF file
YHYukuan Han
Yukuan Han
GRGaifeng Ren
Gaifeng Ren
ZJZhang Jiarui
Zhang Jiarui
YDYuxin Du
Yuxin Du
BGBao guoqiang Bao guoqiang
Bao guoqiang Bao guoqiang
HYHongwen Yan
Hongwen Yan
In this paper, a lightweight detection model DSW-YOLO based on improved YOLOv10n is proposed. After comparing mainstream lightweight models (YOLOv5n, YOLOv6n, YOLOv8n, YOLOv9t and YOLOv10n), YOLOv10n with the best performance was selected as the baseline. The DWRR block was then designed and integrated with the C2f module to form C2f-DWRR, replacing the original C2f blocks in the backbone. Consequently, the model’s P, R, mAP50, and mAP50-95 increased by 2.3%, 2.1%, 1.8%, and 3.4%, respectively, while the parameter count dropped by 0.16 M and the model size was reduced by 0.25 MB. A SimAM parameter-free attention mechanism was added to the last layer of the backbone, boosting P, R, mAP50, and mAP50-95 to 90.6%, 84.0%, 91.8%, and 68.5%, and reducing average detection time to 1.1 ms. The CIOU function was replaced with WIOUv3 to accelerate convergence, decrease loss, and significantly enhance detection performance. Experimental results show that on a custom green pepper dataset, DSW-YOLO outperformed the baseline by achieving gains of 2.9%, 2.7%, 2.2%, and 3.4% in P, R, mAP50, and mAP50-95, reducing parameters by 1.6 M, cutting inference time by 0.7 ms, and shrinking the model size to 5.31 MB. DSW-YOLO efficiently and accurately detects green peppers in complex field conditions, significantly improving detection accuracy while remaining lightweight, and provides theoretical and technical support for designing and optimizing pepper-picking robot vision systems.