Wenbo Zhu

Dr. Wenbo Zhu

Foshan University
orcid

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
12 November 2021 in Horticulturae
Verified
Journal Article
Open access
PDF file
JWJinhai Wang
Jinhai Wang
ZZZongyin Zhang
Zongyin Zhang
LLLuo Lufeng
Luo Lufeng
WZWenbo Zhu
Wenbo Zhu
JCJianwen Chen
Jianwen Chen
伟王伟 王
伟 王
Accurate recognition of fruits in the orchard is an important step for robot picking in the natural environment, since many CNN models have a low recognition rate when dealing with irregularly shaped and very dense fruits, such as a grape bunch. It is a new trend to use a transformer structure and apply it to a computer vision domain for image processing. This paper provides Swin Transformer and DETR models to achieve grape bunch detection. Additionally, they are compared with traditional CNN models, such as Faster-RCNN, SSD, and YOLO. In addition, the optimal number of stages for a Swin Transformer through experiments is selected. Furthermore, the latest YOLOX model is also used to make a comparison with the Swin Transformer, and the experimental results show that YOLOX has higher accuracy and better detection effect. The above models are trained under red grape datasets collected under natural light. In addition, the dataset is expanded through image data augmentation to achieve a better training effect. After 200 epochs of training, SwinGD obtained an exciting mAP value of 94% when IoU = 0.5. In case of overexposure, overdarkness, and occlusion, SwinGD can recognize more accurately and robustly compared with other models. At the same time, SwinGD still has a better effect when dealing with dense grape bunches. Furthermore, 100 pictures of grapes containing 655 grape bunches are downloaded from Baidu pictures to detect the effect. The Swin Transformer has an accuracy of 91.5%. In order to verify the universality of SwinGD, we conducted a test under green grape images. The experimental results show that SwinGD has a good effect in practical application. The success of SwinGD provides a new solution for precision harvesting in agriculture.

1 October 2014 in Signal Processing
Verified
Journal Article
Closed access
KCKan Chen
Kan Chen
BLBin Li
Bin Li
LTLian-Fang Tian
Lian-Fang Tian
WZWenbo Zhu
Wenbo Zhu
YBYing-Han Bao
Ying-Han Bao

15 December 2022 in Nanomaterials
Verified
Journal Article
Open access
PDF file
XCXinrui Chen
Xinrui Chen
WZWenbo Zhu
Wenbo Zhu
JCJianwen Chen
Jianwen Chen
QCQing Cao
Qing Cao
YCYingxi Chen
Yingxi Chen
DHDengyan Hu
Dengyan Hu
With the development of electronic technology, there is an increasing demand for high-temperature dielectric energy storage devices based on polyimides for a wide range of applications. However, the current nanofillers/PI nanocomposites are used for energy harvesting at no more than 200 °C, which does not satisfy the applications in the oil and gas, aerospace, and power transmission industries that require an operating temperature of 250–300 °C. Therefore, we introduced a nanocomposite based on nonsolid TiO2 nanoparticles and polyimide (PI) with high energy storage performance at an ultrahigh temperature of 300 °C. The synergy of excellent dielectric properties and a high breakdown strength endowed the nanocomposite with a low loading content of 1 wt% and a high energy storage density of 5.09 J cm−3. Furthermore, we found that the nanocomposite could stably operate at 300 °C with an outstanding energy storage capability (2.20 J cm−3). Additionally, finite element simulations demonstrated that the partially hollow nanostructures of the nanofillers avoided the evolution of breakdown paths, which optimized the breakdown strength and energy storage performance of the related nanocomposites. This paper provides an avenue to broaden the application areas of PI-based nanocomposites as ultrahigh-temperature energy-storage devices.

Verified
Journal Article
Open access
PDF file
ZLZhenming Li
Zhenming Li
BZBing Zheng
Bing Zheng
DCDong Chao
Dong Chao
WZWenbo Zhu
Wenbo Zhu
HLHaibing Li
Haibing Li
YZYunzhi Zhang
Yunzhi Zhang
Underwater object detection is critical for marine ecological monitoring and biodiversity research, yet existing algorithms struggle in detecting densely packed objects of varying sizes, particularly in occluded and complex underwater environments. This study introduces Underwater-Yolo, a novel detection network that enhances performance in these challenging scenarios by integrating a dual-branch occlusion-handling attention mechanism (GLOAM) and a Cross-Stage Partial Dilated Deformable Convolution (CSP-DDC) backbone. The dilated deformable convolutions (DDCs) in the backbone and neck expand the receptive field, thereby improving the detection of small objects, while the deformable convolutions enhance the model’s adaptive feature extraction capabilities for unstructured objects. Additionally, the CARAFE up-sampling operator in the neck aggregates contextual information across a broader spatial domain. The GLOAM, consisting of a global branch (using a Vision Transformer to capture global features and object–background relationships) and a local branch (enhancing the detection of occluded objects through depthwise–pointwise convolutions), further optimizes performance. By incorporating these innovations, the model effectively addresses the challenges of detecting small and occluded objects in dense underwater environments. The evaluation on the CLfish-V1 dataset shows significant improvements over state-of-the-art algorithms, with an AP50 of 93.8%, an AP75 of 88.9%, and an AP-small of 76.4%, marking gains of 4.7%, 16.7%, and 6%, respectively. These results demonstrate the model’s effectiveness in complex underwater scenarios.

22 February 2019
Verified
Conference Paper
Open access
PDF file
WZWenbo Zhu
Wenbo Zhu
WYWeichang Yeh
Weichang Yeh
JCJianwen Chen
Jianwen Chen
DCDafeng Chen
Dafeng Chen
ALAiyuan Li
Aiyuan Li
YLYangyang Lin
Yangyang Lin

23 June 2022 in Polymer Composites
Verified
Journal Article
Closed access
YCYingxi Chen
Yingxi Chen
WZWenbo Zhu
Wenbo Zhu
XWXiucai Wang
Xiucai Wang
WCWenjun Chen
Wenjun Chen
WCWeiqiang Cai
Weiqiang Cai
JCJianwen Chen
Jianwen Chen