tao zhang

Mr. tao zhang

orcid

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
16 April 2023 in Horticulturae
Verified
Journal Article
Open access
PDF file
TZtao zhang
tao zhang
FWFengyun WU
Fengyun WU
MWMei Wang
Mei Wang
ZCZhaoyi Chen
Zhaoyi Chen
LLLanyun Li
Lanyun Li
Xiangjun ZouXiangjun Zou
Xiangjun Zou
Due to the short fruit axis, many leaves, and complex background of grapes, most grape cluster axes are blocked from view, which increases robot positioning difficulty in harvesting. This study discussed the location method for picking points in the case of partial occlusion and proposed a grape cluster-detection algorithm “You Only Look Once v5-GAP” based on “You Only Look Once v5”. First, the Conv layer of the first layer of the YOLOv5 algorithm Backbone was changed to the Focus layer, then a convolution attention operation was performed on the first three C3 structures, the C3 structure layer was changed, and the Transformer in the Bottleneck module of the last layer of the C3 structure was used to reduce the computational amount and execute a better extraction of global feature information. Second, on the basis of bidirectional feature fusion, jump links were added and variable weights were used to strengthen the fusion of feature information for different resolutions. Then, the adaptive activation function was used to learn and decide whether neurons needed to be activated, such that the dynamic control of the network nonlinear degree was realized. Finally, the combination of a digital image processing algorithm and mathematical geometry was used to segment grape bunches identified by YOLOv5-GAP, and picking points were determined after finding centroid coordinates. Experimental results showed that the average precision of YOLOv5-GAP was 95.13%, which was 16.13%, 4.34%, and 2.35% higher than YOLOv4, YOLOv5, and YOLOv7 algorithms, respectively. The average positioning pixel error of the point was 6.3 pixels, which verified that the algorithm effectively detected grapes quickly and accurately.