Fengqiang Gao

Fengqiang Gao

Auto-generated profile, based on publicly available information

Fengqiang Gao

School of Mechanical and Electrical Engineering Automation, Tan Kah Kee College,Xiamen,China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
17 February 2022 in IEEE Access
Verified
Journal Article
Open access
YGYijing Guo
Yijing Guo
YZYixin Zeng
Yixin Zeng
FGFengqiang Gao
Fengqiang Gao
YQYi Qiu
Yi Qiu
XZXuqiang Zhou
Xuqiang Zhou
CZChou-Jun Zhan
Chou-Jun Zhan
Bamboo surface defect detection provides quality assurance for bamboo product manufacture in industrial scenarios, an integral part of the overall manufacturing process. Currently, bamboo defect inspection predominantly relies on manual operation, but manual inspection is very time-consuming as well as labor-intensive, and the quality of inspection is not guaranteed. A few visual inspection systems based on traditional image processing have been deployed in some factories in recent years. However, traditional machine vision algorithms extract features in tedious steps and have poor performance along with poor adaptability in the face of complex defects. Accordingly, many scholars are committed to seeking deep learning methods to accomplish surface defect detection. However, existing deep learning object detectors struggle with specific industrial defects when directly applied to industrial defect detection, such as sliver defects, especially for ones with extreme aspect ratios. To this end, this paper proposes an improved algorithm based on the advanced object detector YOLOV4-CSP, which introduces asymmetric convolution and attention mechanism. The introduction of asymmetric convolution enhances the feature extraction in the horizontal direction of the bamboo strip surface, improving the performance in detecting sliver defects. In addition, convolutional block attention module(CBAM), a hybrid attention module, which combines channel attention with spatial attention, is utilized to promote the representation ability of the model by increasing the weights of crucial channels and regions. The proposed model achieves outstanding performance in the general categories and excels in the hard-to-detect categories. Some enterprise’s bamboo strip dataset experiments verify that the model can reach 96.74% mAP for the typical six surface defects. Meanwhile, we also observe significant improvements when extending our model to aluminum datasets with similar characteristics.

26 August 2020 in IEEE Access
Verified
Journal Article
Open access
GSGuifang Shao
Guifang Shao
MHMeng Huang
Meng Huang
FGFengqiang Gao
Fengqiang Gao
TLTundong Liu
Tundong Liu
LLLiduan Li
Liduan Li
With the appearance of Generative Adversarial Network (GAN), image-to-image translation based on a new unified framework has attracted growing interests. As a new technique, it can generate synthesizing images for various requirements in both computer vision and image processing. However, the cycle consistent structure adopted in some common models, such as cycle generative adversarial network (CycleGAN), is usually unable to learn more abundant image features. In this work, we developed a novel model based on GAN, named as dual capsule generative adversarial network (DuCaGAN), by utilizing the distinctive characteristic of view angle invariance and rotation equivariance in capsule network. Firstly, two capsule networks were introduced into the traditional CycleGAN model as discriminators to form our proposed model with six agents. To improve the feature capturing performance, we modified the full objective by combining the margin loss and the original adversarial loss. Furthermore, the Routing Algorithm in the capsule network was optimized by changing its compression function. Finally, experimental results on conventional visual tasks with paired and unpaired datasets demonstrated the superiority and effectiveness of the proposed approach compared to both deep convolutional generative adversarial network (DCGAN) and CycleGAN methods. More importantly, the proposed DuCaGAN was applied for the first time to augment the surface defect data from the real industrial field, and exhibited better performance than those methods available.

6 May 2024 in Physica A: Statistical Mechanics and its Applications
Verified
Journal Article
Closed access
TLTundong Liu
Tundong Liu
FGFengqiang Gao
Fengqiang Gao
WZWeihong Zhou
Weihong Zhou
YYYuyue Yan
Yuyue Yan

14 May 2023
Verified
Book Chapter
Closed access
PDF file
GSGuifang Shao
Guifang Shao
QSQiao Sun
Qiao Sun
FGFengqiang Gao
Fengqiang Gao
TLTundong Liu
Tundong Liu
JLJincai Luo
Jincai Luo
YWYubin Wei
Yubin Wei

16 May 2025
Verified
Conference Paper
Closed access
GSGuifang Shao
Guifang Shao
XYXinyue Yu
Xinyue Yu
FGFengqiang Gao
Fengqiang Gao
YYYing Yu
Ying Yu
QZQingyuan Zhu
Qingyuan Zhu
YGYunlong Gao
Yunlong Gao
Evacuation simulations are crucial for predicting potential evacuation scenarios before disasters and for assessing the effectiveness of various control strategies. However, traditional evacuation models typically focus on physical factors such as speed, density, and the number of exits, often neglecting the complex psychological and behavioral interactions among pedestrians. In particular, the impact of panic and cooperative behaviors on evacuation efficiency in emergency situations is frequently neglected. To address this gap, this paper proposes a game-theoretic approach integrated with a force-driven cellular automata model, which incorporates cooperative behaviors during evacuation. To enhance the utilization of each exit and reduce congestion, we design an evacuation guidance assistant based on density control. Moreover, to quantify the cooperative and competitive dynamics between pedestrians, the proposed model incorporates panic degree and conflict cost into the game-theoretic framework. Experimental results reveal that panic significantly hinders the formation of cooperative behaviors, with its impact on evacuation efficiency being most pronounced in the initial stages of the evacuation. While moderate levels of panic can enhance evacuation efficiency, excessively high panic levels have a detrimental effect, slowing down the process. Furthermore, the density control algorithm proposed in this study effectively alleviates the ‘arch phenomenon’ observed in evacuation scenarios, reducing evacuation time and improving overall efficiency.