Zhao Wang

Mr. Zhao Wang


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
26 July 2025 in Agriculture
Verified
Journal Article
Open access
PDF file
JLJin Lu
Jin Lu
ZCZhongji Cao
Zhongji Cao
JWJin Wang
Jin Wang
ZWZhao Wang
Zhao Wang
JZJia Zhao
Jia Zhao
敏张敏杰 张
敏杰 张
During the automated picking of table grapes, the automatic recognition and segmentation of grape pedicels, along with the positioning of picking points, are vital components for all the following operations of the harvesting robot. In the actual scene of a grape plantation, however, it is extremely difficult to accurately and efficiently identify and segment grape pedicels and then reliably locate the picking points. This is attributable to the low distinguishability between grape pedicels and the surrounding environment such as branches, as well as the impacts of other conditions like weather, lighting, and occlusion, which are coupled with the requirements for model deployment on edge devices with limited computing resources. To address these issues, this study proposes a novel picking point localization method for table grapes based on an instance segmentation network called Progressive Global-Local Structure-Sensitive Segmentation (PGSS-YOLOv11s) and a simple combination strategy of morphological operators. More specifically, the network PGSS-YOLOv11s is composed of an original backbone of the YOLOv11s-seg, a spatial feature aggregation module (SFAM), an adaptive feature fusion module (AFFM), and a detail-enhanced convolutional shared detection head (DE-SCSH). And the PGSS-YOLOv11s have been trained with a new grape segmentation dataset called Grape-⊥, which includes 4455 grape pixel-level instances with the annotation of ⊥-shaped regions. After the PGSS-YOLOv11s segments the ⊥-shaped regions of grapes, some morphological operations such as erosion, dilation, and skeletonization are combined to effectively extract grape pedicels and locate picking points. Finally, several experiments have been conducted to confirm the validity, effectiveness, and superiority of the proposed method. Compared with the other state-of-the-art models, the main metrics F1 score and mask mAP@0.5 of the PGSS-YOLOv11s reached 94.6% and 95.2% on the Grape-⊥ dataset, as well as 85.4% and 90.0% on the Winegrape dataset. Multi-scenario tests indicated that the success rate of positioning the picking points reached up to 89.44%. In orchards, real-time tests on the edge device demonstrated the practical performance of our method. Nevertheless, for grapes with short pedicels or occluded pedicels, the designed morphological algorithm exhibited the loss of picking point calculations. In future work, we will enrich the grape dataset by collecting images under different lighting conditions, from various shooting angles, and including more grape varieties to improve the method’s generalization performance.

28 January 2026 in Agriculture
Verified
Journal Article
Open access
PDF file
JLJin Lu
Jin Lu
ZWZhao Wang
Zhao Wang
JWJin Wang
Jin Wang
ZCZhongji Cao
Zhongji Cao
JZJia Zhao
Jia Zhao
敏张敏杰 张
敏杰 张
In intelligent unmanned agricultural machinery research, navigation line extraction in natural field/orchard environments is critical for autonomous operation. Existing methods still face two prominent challenges: (1) Dynamic shooting perspective shifts caused by natural environmental interference lead to geometric distortion of image features, making it difficult to acquire high-precision navigation features; (2) Symmetric distribution of crop row boundaries hinders traditional algorithms from accurately extracting effective navigation trajectories, resulting in insufficient accuracy and reliability. To address these issues, this paper proposes an environment-adaptive navigation path extraction method for multi-type agricultural scenarios, consisting of two core components: an Attention-Feature-Enhanced U-Net (AFU-Net) for semantic segmentation of navigation feature regions, and a key-point constraint-based adaptive navigation line extraction algorithm. AFU-Net improves the U-Net framework by embedding Efficient Channel Attention (ECA) modules at the ends of Encoders 1–3 to enhance feature expression, and replacing Encoder 4 with a cascaded Semantic Aware Multi-scale Enhancement (SAME) module. Trained and tested on both our KVW dataset and Yu’s field dataset, our method achieves outstanding performance: On the KVW dataset, AFU-Net attains a Mean Intersection over Union (MIoU) of 97.55% and a real-time inference speed of 32.60 FPS with only 3.95 M Params, outperforming state-of-the-art models. On Yu’s field dataset, it maintains an MIoU of 95.20% and 16.30 FPS. Additionally, compared with traditional navigation line extraction algorithms, the proposed adaptive algorithm reduces the mean absolute yaw angle error (mAYAE) to 2.06° in complex scenarios. This research exhibits strong adaptability and robustness, providing reliable technical support for the precise navigation of intelligent agricultural machinery across multiple agricultural scenarios.