Chuanzhi Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chuanzhi Chen has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
Jinbao Chen
4 shared publications- Jinbao Chen
College of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
4 shared publications Fei Lin
Jiujiang University, Jiujiang, China
2 shared publicationsZhicheng Song
Nanjing Univ Aeronaut & Astronaut, Minist Ind & Informat Technol, Key Lab Explorat Mech Deep Space Planet Surface, Nanjing 210016, Peoples R China
2 shared publications- Ziang Ma
National Key Laboratory of Aerospace Mechanism, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
2 shared publications - Chao Wang
National Key Laboratory of Aerospace Mechanism, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
1 shared publication
Latest Publications
- 30 September 2026
- Published by Elsevier in Acta Astronautica
- Vol. 251, 93-104
Three-phase decoupling identification of actuator faults and diagonal inertia uncertainty for spacecraft attitude dynamics
- 30 September 2026
- Published by Elsevier in Acta Astronautica
- Vol. 251, 93-104
Three-phase decoupling identification of actuator faults and diagonal inertia uncertainty for spacecraft attitude dynamics
- Open Access
- 20 January 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (2) , 1062
STC-SORT: A Dynamic Spatio-Temporal Consistency Framework for Multi-Object Tracking in UAV Videos
Multi-object tracking (MOT) in videos captured by Unmanned Aerial Vehicles (UAVs) is critically challenged by significant camera ego-motion, frequent occlusions, and complex object interactions. To address the limitations of conventional trackers that depend on static, rule-based association strategies, this paper introduces STC-SORT, a novel tracking framework whose core is a two-level reasoning architecture for data association. First, a Spatio-Temporal Consistency Graph Network (STC-GN) models inter-object relationships via graph attention to learn adaptive weights for fusing motion, appearance, and geometric cues. Second, these dynamic weights are integrated into a 4D association cost volume, enabling globally optimal matching across a temporal window. When integrated with an enhanced AEE-YOLO detector, STC-SORT achieves significant and statistically robust improvements on major UAV tracking benchmarks. It elevates MOTA by 13.0% on UAVDT and 6.5% on VisDrone, while boosting IDF1 by 9.7% and 9.9%, respectively. The framework also maintains real-time inference speed (75.5 FPS) and demonstrates substantial reductions in identity switches. These results validate STC-SORT as having strong potential for robust multi-object tracking in challenging UAV scenarios.
- 20 January 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (2) , 1062
Open AccessSTC-SORT: A Dynamic Spatio-Temporal Consistency Framework for Multi-Object Tracking in UAV Videos
Multi-object tracking (MOT) in videos captured by Unmanned Aerial Vehicles (UAVs) is critically challenged by significant camera ego-motion, frequent occlusions, and complex object interactions. To address the limitations of conventional trackers that depend on static, rule-based association strategies, this paper introduces STC-SORT, a novel tracking framework whose core is a two-level reasoning architecture for data association. First, a Spatio-Temporal Consistency Graph Network (STC-GN) models inter-object relationships via graph attention to learn adaptive weights for fusing motion, appearance, and geometric cues. Second, these dynamic weights are integrated into a 4D association cost volume, enabling globally optimal matching across a temporal window. When integrated with an enhanced AEE-YOLO detector, STC-SORT achieves significant and statistically robust improvements on major UAV tracking benchmarks. It elevates MOTA by 13.0% on UAVDT and 6.5% on VisDrone, while boosting IDF1 by 9.7% and 9.9%, respectively. The framework also maintains real-time inference speed (75.5 FPS) and demonstrates substantial reductions in identity switches. These results validate STC-SORT as having strong potential for robust multi-object tracking in challenging UAV scenarios.
- Open Access
DDF-YOLO: A Small Target Detection Model Using Multi-Scale Dynamic Feature Fusion for UAV Aerial Photography
Unmanned aerial vehicle (UAV)-based object detection shows promising potential in intelligent transportation and disaster response. However, detecting small targets remains challenging due to inherent limitations (long-distance and low-resolution imaging) and environmental interference (complex backgrounds and occlusions). To address these issues, this paper proposes an enhanced small target detection model, DDF-YOLO, which achieves higher detection performance. First, a dynamic feature extraction module (C2f-DCNv4) employs deformable convolutions to effectively capture features from irregularly shaped objects. In addition, a dynamic upsampling module (DySample) optimizes multi-scale feature fusion by combining shallow spatial details with deep semantic features, preserving critical low-level information while enhancing generalization across scales. Finally, to balance rapid convergence with precise localization, an adaptive Focaler-ECIoU loss function dynamically adjusts training weights based on sample quality during bounding box regression. Extensive experiments on VisDrone2019 and UAVDT benchmarks demonstrate DDF-YOLO’s superiority. Compared to YOLOv8n, our model achieves gains of 8.6% and 4.8% in mAP50, along with improvements of 5.0% and 3.3% in mAP50-95, respectively. Furthermore, it exhibits superior efficiency, requiring only 7.3 GFLOPs and attaining an inference speed of 179 FPS. These results validate the model’s robustness for UAV-based detection, particularly in small-object scenarios.
Open AccessDDF-YOLO: A Small Target Detection Model Using Multi-Scale Dynamic Feature Fusion for UAV Aerial Photography
Unmanned aerial vehicle (UAV)-based object detection shows promising potential in intelligent transportation and disaster response. However, detecting small targets remains challenging due to inherent limitations (long-distance and low-resolution imaging) and environmental interference (complex backgrounds and occlusions). To address these issues, this paper proposes an enhanced small target detection model, DDF-YOLO, which achieves higher detection performance. First, a dynamic feature extraction module (C2f-DCNv4) employs deformable convolutions to effectively capture features from irregularly shaped objects. In addition, a dynamic upsampling module (DySample) optimizes multi-scale feature fusion by combining shallow spatial details with deep semantic features, preserving critical low-level information while enhancing generalization across scales. Finally, to balance rapid convergence with precise localization, an adaptive Focaler-ECIoU loss function dynamically adjusts training weights based on sample quality during bounding box regression. Extensive experiments on VisDrone2019 and UAVDT benchmarks demonstrate DDF-YOLO’s superiority. Compared to YOLOv8n, our model achieves gains of 8.6% and 4.8% in mAP50, along with improvements of 5.0% and 3.3% in mAP50-95, respectively. Furthermore, it exhibits superior efficiency, requiring only 7.3 GFLOPs and attaining an inference speed of 179 FPS. These results validate the model’s robustness for UAV-based detection, particularly in small-object scenarios.
- Open Access
Form-Finding Analysis of Mesh Reflector of Large Parabolic Cylindrical Antenna
In this study, a hybrid iteration force density method (HIFDM) was proposed to ensure both tension uniformity and accuracy of an antenna mesh reflector. Based on a genetic algorithm (GA), the boundary cable tension of the antenna reflector net was optimized, which further improved the precision of the antenna mesh reflector. The static model of the large deployable structure was established using the finite element method (FEM), and thus, an iterative strategy for form-finding of the antenna reflector net was proposed, which considered the influence of the elastic deformation of the deployable structure. The results showed that the HIFDM was effective for the form-finding of the antenna mesh reflector, and the shape precision was improved by further optimization using the GA. Finally, it was noted that the elastic deformation of the deployable structure will reduce the uniformity of cable tension and affect the precision of antenna reflectors. Due to the large-scale and soft stiffness, the large deployable structure had a high sensitivity to cable pretension, and it is important to design a reasonable cable pretension to ensure the accurate shape of antenna mesh reflectors.
Open AccessForm-Finding Analysis of Mesh Reflector of Large Parabolic Cylindrical Antenna
In this study, a hybrid iteration force density method (HIFDM) was proposed to ensure both tension uniformity and accuracy of an antenna mesh reflector. Based on a genetic algorithm (GA), the boundary cable tension of the antenna reflector net was optimized, which further improved the precision of the antenna mesh reflector. The static model of the large deployable structure was established using the finite element method (FEM), and thus, an iterative strategy for form-finding of the antenna reflector net was proposed, which considered the influence of the elastic deformation of the deployable structure. The results showed that the HIFDM was effective for the form-finding of the antenna mesh reflector, and the shape precision was improved by further optimization using the GA. Finally, it was noted that the elastic deformation of the deployable structure will reduce the uniformity of cable tension and affect the precision of antenna reflectors. Due to the large-scale and soft stiffness, the large deployable structure had a high sensitivity to cable pretension, and it is important to design a reasonable cable pretension to ensure the accurate shape of antenna mesh reflectors.
- Open Access
- 1 January 2021
- Published by American Institute of Mathematical Sciences (AIMS) in Mathematical Biosciences and Engineering
- Vol. 18 (4) , 4603-4627
Application of discrete shape function in absolute nodal coordinate formulation
To solve integrals in the absolute nodal coordinate method and address the difficulty in applying it to an arbitrary-section beam, this paper focuses on two methods involving single integrals:the invariant matrix method and the Gerstmayr method, with cross-section characteristics by applying the interpolation of a discrete function. Such single integrals demonstrate that the nodal coordinate method can be applied to an arbitrary-section beam. The Euler–Bernoulli beam used in engineering structures is characterised by a symmetrical cross-section, small section size, zero odd integrals and negligible high-order even integrals, which simplifies the single integrals of the two methods. Finally, the Gaussian integration is adopted to improve the solving efficiency of elastic force and force Jacobian.
- 1 January 2021
- Published by American Institute of Mathematical Sciences (AIMS) in Mathematical Biosciences and Engineering
- Vol. 18 (4) , 4603-4627
Open AccessApplication of discrete shape function in absolute nodal coordinate formulation
To solve integrals in the absolute nodal coordinate method and address the difficulty in applying it to an arbitrary-section beam, this paper focuses on two methods involving single integrals:the invariant matrix method and the Gerstmayr method, with cross-section characteristics by applying the interpolation of a discrete function. Such single integrals demonstrate that the nodal coordinate method can be applied to an arbitrary-section beam. The Euler–Bernoulli beam used in engineering structures is characterised by a symmetrical cross-section, small section size, zero odd integrals and negligible high-order even integrals, which simplifies the single integrals of the two methods. Finally, the Gaussian integration is adopted to improve the solving efficiency of elastic force and force Jacobian.
- 16 June 2020
- Published by Springer Nature in Microgravity Science and Technology
- Vol. 32 (5) , 773-785
Optimization Analysis of Microgravity Experimental Facility for the Deployable Structures Based on Force Balance Method
- 16 June 2020
- Published by Springer Nature in Microgravity Science and Technology
- Vol. 32 (5) , 773-785
Optimization Analysis of Microgravity Experimental Facility for the Deployable Structures Based on Force Balance Method
- 3 March 2020
- Published by Springer Nature in Journal of Mechanical Science and Technology
- Vol. 34 (3) , 987-1003
Accuracy analysis of spatial multi-loop mechanism effected by paired bearings support joint clearance
- 3 March 2020
- Published by Springer Nature in Journal of Mechanical Science and Technology
- Vol. 34 (3) , 987-1003
Accuracy analysis of spatial multi-loop mechanism effected by paired bearings support joint clearance
- 26 November 2019
- Published by Springer Nature in International Journal of Aeronautical and Space Sciences
- Vol. 21 (2) , 404-417
Dimensional Synthesis of Antenna-Deployable Support Structure
- 26 November 2019
- Published by Springer Nature in International Journal of Aeronautical and Space Sciences
- Vol. 21 (2) , 404-417
Dimensional Synthesis of Antenna-Deployable Support Structure