Congqing Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Congqing Wang has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
Yang Liu
5 shared publications- Huipeng Li
Nanjing University of Aeronautics and Astronautics
4 shared publications Xuewei Wu
College of Automation Engineering, Nanjing University of Aeronautics and Astronautics Nanjing 210016 People's Republic of China
3 shared publicationsBin Xu
College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, 211106, China
2 shared publicationsShaoyang Hua
College of Automation Engineering, Nanjing University of Aeronautics and Astronautics Nanjing 210016 People's Republic of China
2 shared publicationsYongjun Zhou
Near-Surface Detection Laboratory of Science and Technology, Wuxi 214000, China
2 shared publications
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33, 3801-3805
Aircraft Skin Defect Detection Based on Dual-Domain Wavelet Feature Enhancement
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33, 3801-3805
Aircraft Skin Defect Detection Based on Dual-Domain Wavelet Feature Enhancement
- 8 December 2025
- Published by Elsevier in Measurement
- Vol. 262
A review of automated aircraft skin defects detection
- 8 December 2025
- Published by Elsevier in Measurement
- Vol. 262
A review of automated aircraft skin defects detection
- 5 January 2025
- Published by Elsevier in Measurement
- Vol. 245
Aircraft skin defect detection based on Fourier GAN data augmentation under limited samples
- 5 January 2025
- Published by Elsevier in Measurement
- Vol. 245
Aircraft skin defect detection based on Fourier GAN data augmentation under limited samples
- 28 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-12
A High-Quality GAN With Data Augmentation for Aircraft Skin Defect Detection Under Limited Data
Aircraft skin defect detection is one of the crucial steps in the regular maintenance. However, the performance of defect detection algorithms is limited by insufficient data, which makes a challenge for automated defect detection of aircraft skin. Although image generation techniques relieve the problem of insufficient defect data, they are not effective under the condition of limited original data. To tackle this issue, this paper proposes an image generation method that can obtain high-quality images of aircraft skin defects under limited data. Firstly, high-frequency skip connection (HSC) is performed in the generator to enhance the utilization of frequency information. Moreover, high-frequency features fusion blocks (HFFB) are utilized to effectively improve the high-frequency awareness of the discriminator. Meanwhile, adaptive high-dimensional diffusion (AHD) is introduced into the discriminator, which can automatically adjust the diffusion intensity according to the degree of discriminator overfitting. Finally, an aircraft skin defect dataset is constructed and a Generation-Poisson blending data augmentation method is proposed. The mAP of YOLOX trained using the augmentation dataset can reach 78.55%, which is 5.27% higher than the original data. The proposed method is capable of generating realistic and diverse images of aircraft skin defects, which significantly enhances the precision of defect detection networks in various scenes.
- 28 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-12
A High-Quality GAN With Data Augmentation for Aircraft Skin Defect Detection Under Limited Data
Aircraft skin defect detection is one of the crucial steps in the regular maintenance. However, the performance of defect detection algorithms is limited by insufficient data, which makes a challenge for automated defect detection of aircraft skin. Although image generation techniques relieve the problem of insufficient defect data, they are not effective under the condition of limited original data. To tackle this issue, this paper proposes an image generation method that can obtain high-quality images of aircraft skin defects under limited data. Firstly, high-frequency skip connection (HSC) is performed in the generator to enhance the utilization of frequency information. Moreover, high-frequency features fusion blocks (HFFB) are utilized to effectively improve the high-frequency awareness of the discriminator. Meanwhile, adaptive high-dimensional diffusion (AHD) is introduced into the discriminator, which can automatically adjust the diffusion intensity according to the degree of discriminator overfitting. Finally, an aircraft skin defect dataset is constructed and a Generation-Poisson blending data augmentation method is proposed. The mAP of YOLOX trained using the augmentation dataset can reach 78.55%, which is 5.27% higher than the original data. The proposed method is capable of generating realistic and diverse images of aircraft skin defects, which significantly enhances the precision of defect detection networks in various scenes.
- 31 January 2024
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 18 (4) , 3197-3211
YOLO-FDD: efficient defect detection network of aircraft skin fastener
- 31 January 2024
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 18 (4) , 3197-3211
YOLO-FDD: efficient defect detection network of aircraft skin fastener
- 1 November 2023
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 32 (06) , 063018-18
Aerial tracking of camouflaged people in woodlands
With the remarkable advances of unmanned aerial vehicles (UAVs) and machine vision, aerial tracking has attracted wide attention from scholars. Previous tracking methods were mostly implemented in clean and well-lit environments, making it challenging to track camouflaged people rapidly and accurately in woodlands. We develop a framework for camouflaged people aerial tracking (CPAT) based on transformer. Specifically, a camouflaged people discovery strategy is proposed to rapidly generate training samples from the unlabeled videos captured by the UAV. Dynamic programming is also employed to filter noises to generate smooth candidate frames. To exploit multilevel feature information, a transformer fusion framework is designed to integrate shallow spatial information and in-depth semantic features. For reducing computing consumption, the spatial attention reduction mechanism is embedded in the multihead attention for fast tracking. Further, we build a dataset for evaluating the effect of camouflaged people tracking called Cam235, which consists of 85 manually labeled test sequences and more than 100k frames of the unlabeled training set. Exhaustive experiments on Cam235-test and popular tracking datasets prove that the CPAT is superior to other trackers for practical application. Under the most challenging condition of camouflaged people tracking, the CPAT achieves the precision of 67.9%, surpassing the state-of-the-art trackers by large margins.
- 1 November 2023
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 32 (06) , 063018-18
Aerial tracking of camouflaged people in woodlands
With the remarkable advances of unmanned aerial vehicles (UAVs) and machine vision, aerial tracking has attracted wide attention from scholars. Previous tracking methods were mostly implemented in clean and well-lit environments, making it challenging to track camouflaged people rapidly and accurately in woodlands. We develop a framework for camouflaged people aerial tracking (CPAT) based on transformer. Specifically, a camouflaged people discovery strategy is proposed to rapidly generate training samples from the unlabeled videos captured by the UAV. Dynamic programming is also employed to filter noises to generate smooth candidate frames. To exploit multilevel feature information, a transformer fusion framework is designed to integrate shallow spatial information and in-depth semantic features. For reducing computing consumption, the spatial attention reduction mechanism is embedded in the multihead attention for fast tracking. Further, we build a dataset for evaluating the effect of camouflaged people tracking called Cam235, which consists of 85 manually labeled test sequences and more than 100k frames of the unlabeled training set. Exhaustive experiments on Cam235-test and popular tracking datasets prove that the CPAT is superior to other trackers for practical application. Under the most challenging condition of camouflaged people tracking, the CPAT achieves the precision of 67.9%, surpassing the state-of-the-art trackers by large margins.
- Open Access
- 24 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Fuzzy PID coordinated turn control method for unmanned helicopters based on improved particle swarm optimization algorithm
Due to the characteristics of nonlinearity and strong coupling, the control system for unmanned helicopters is challenging to design. Coordinated turn is a basic mode for unmanned helicopters to complete complex actions autonomously. To achieve higher control performance, this paper proposes a fuzzy PID coordinated turn control method based on improved particle swarm optimization (PSO) algorithm. Firstly, the mathematical model of an unmanned helicopter is established, and the control strategy of coordinated turn mode is analysed. Then, the attitude and altitude controllers based on fuzzy PID for coordinated turn are designed. In order to compensate for the shortcoming that quantization factors and proportional factors of fuzzy PID controllers depend too much on experience, the differential evolution (DE) method, local convergence judgement, and linearly decreasing inertia weight are presented as improvements to the PSO algorithm to optimize factors. Finally, the results of the simulation demonstrate that the position, speed and attitude of the unmanned helicopter can react quickly and the corresponding output value is accurate and stable in coordinated turn mode. So the coordinated turn control method for unmanned helicopters is proven to be feasible and effective.
- 24 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessFuzzy PID coordinated turn control method for unmanned helicopters based on improved particle swarm optimization algorithm
Due to the characteristics of nonlinearity and strong coupling, the control system for unmanned helicopters is challenging to design. Coordinated turn is a basic mode for unmanned helicopters to complete complex actions autonomously. To achieve higher control performance, this paper proposes a fuzzy PID coordinated turn control method based on improved particle swarm optimization (PSO) algorithm. Firstly, the mathematical model of an unmanned helicopter is established, and the control strategy of coordinated turn mode is analysed. Then, the attitude and altitude controllers based on fuzzy PID for coordinated turn are designed. In order to compensate for the shortcoming that quantization factors and proportional factors of fuzzy PID controllers depend too much on experience, the differential evolution (DE) method, local convergence judgement, and linearly decreasing inertia weight are presented as improvements to the PSO algorithm to optimize factors. Finally, the results of the simulation demonstrate that the position, speed and attitude of the unmanned helicopter can react quickly and the corresponding output value is accurate and stable in coordinated turn mode. So the coordinated turn control method for unmanned helicopters is proven to be feasible and effective.
- Open Access
- 1 June 2023
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 2478 (6) , 062017
Lightweight-YOLOv5s for the camouflaged personnel detection in the woodland
Unmanned aerial vehicles(UAVs) technology and target detection technology are increasingly integrated. However, the target detection networks are cumbersome and complex, and it is hard to directly deploy these networks on the UAVs. To address this problem, a Lightweight-YOLOv5s which can be applied to the UAVs is proposed to detect the camouflaged personnel in the woodland. Depthwise separable convolutions are added to the YOLOv5s for reducing the parameters and computational effort. Then a new channel pruning method based on Batch Normalization(BN) layer scaling factor with adaptive sparsity training is proposed for network compression, which can balance the compression ratio and accuracy of the detection. The pruned network is then fine-tuned to detect the camouflaged personnel. In addition, a special dataset is built for the camouflaged personnel detection in the woodland. The quantitative results on this dataset prove that the proposed Lightweight-YOLOv5s greatly improve the YOLOv5s. Parameters from 7.06M to 1.86M, floating point operations from 16.4G to 9.9G and inference time from 8.16ms to 7.06ms. Besides, mAP of the Lightweight-YOLOv5s is 0.83, which shows the excellent detection performance of the proposed method.
- 1 June 2023
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 2478 (6) , 062017
Open AccessLightweight-YOLOv5s for the camouflaged personnel detection in the woodland
Unmanned aerial vehicles(UAVs) technology and target detection technology are increasingly integrated. However, the target detection networks are cumbersome and complex, and it is hard to directly deploy these networks on the UAVs. To address this problem, a Lightweight-YOLOv5s which can be applied to the UAVs is proposed to detect the camouflaged personnel in the woodland. Depthwise separable convolutions are added to the YOLOv5s for reducing the parameters and computational effort. Then a new channel pruning method based on Batch Normalization(BN) layer scaling factor with adaptive sparsity training is proposed for network compression, which can balance the compression ratio and accuracy of the detection. The pruned network is then fine-tuned to detect the camouflaged personnel. In addition, a special dataset is built for the camouflaged personnel detection in the woodland. The quantitative results on this dataset prove that the proposed Lightweight-YOLOv5s greatly improve the YOLOv5s. Parameters from 7.06M to 1.86M, floating point operations from 16.4G to 9.9G and inference time from 8.16ms to 7.06ms. Besides, mAP of the Lightweight-YOLOv5s is 0.83, which shows the excellent detection performance of the proposed method.
- 26 May 2023
- Published by Springer Nature in The Visual Computer
- Vol. 40 (3) , 1659-1671
An anchor-based convolutional network for the near-surface camouflaged personnel detection of UAVs
- 26 May 2023
- Published by Springer Nature in The Visual Computer
- Vol. 40 (3) , 1659-1671
An anchor-based convolutional network for the near-surface camouflaged personnel detection of UAVs
- 28 January 2021
- Published by Wiley in International Journal of Robust and Nonlinear Control
- Vol. 31 (7) , 2593-2613
Event‐driven adaptive near‐optimal tracking control of the robot in aircraft skin inspection
- 28 January 2021
- Published by Wiley in International Journal of Robust and Nonlinear Control
- Vol. 31 (7) , 2593-2613
Event‐driven adaptive near‐optimal tracking control of the robot in aircraft skin inspection