Tianqi Qin
Research Subjects
Tianqi Qin has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Zhengzhou Li
College of Microelectronics and Communication Engineering, Chongqing University, Chongqing, China
3 shared publications Wenhao Chen
Sichuan Institute of Aerospace Electronic Equipment, Chengdu, China
2 shared publicationsZhiquan Ding
Sichuan Institute of Aerospace Electronic Equipment, Chengdu, China
2 shared publications- Abdullah Azeem
School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, China
1 shared publication Aoran Li
School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, China
1 shared publicationHaibo Wang
China Aerodynamics Research and Development Center, Computational Aerodynamics Institute, Mianyang, Sichuan, China
1 shared publication
Latest Publications
- 26 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (5) , 7394-7407
Maritime Radar Target Multifeature Detection Optimization Method Under Capability Lower Bound Constraint
Multi-feature detection algorithm has demonstrated promising performance in low-RCS radar target detection. However, the multi-feature detection method without capability lower bound constraint usually leads to uncertainty in detection result and inefficient allocation of sensing resource in practical applications. To cope with this problem, a radar target multi-feature detection optimization method under capability lower bound constraint is proposed to enhance the robustness and real-time performance of maritime radar target detection in this paper. Without loss of generality, signal-clutter-noise ratio (SCNR) is employed as a representative metric to characterize the distinction between target and clutter, serving as the proxy for the capability lower bound. Firstly, a surrogate model is established to map the relationship between SCNR and detection results by means of the measured radar data. Secondly, an improved average tail margin (ATM) algorithm combined with feature importance analysis is applied to accurately estimate the lower bound, which is adopted to estimate an adaptive detection threshold for suppressing a large amount of background clutter. Finally, the multi-feature detection algorithm finely discriminates target from background clutter. Extensive experiments are carried out both public radar dataset provided by Radar Journal and our measurement radar dataset captured at outfield. The experimental results show that the proposed method not only reduces computational complex with superior real-time detection performance, but also can enhance the robustness without sacrificing detection accuracy, outperforming baseline multi-feature methods including conventional CFAR. This work enhances the reliability and the practical applicability of sea-surface radar target detection, and it demonstrates strong generalization ability under complex maritime environment.
- 26 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (5) , 7394-7407
Maritime Radar Target Multifeature Detection Optimization Method Under Capability Lower Bound Constraint
Multi-feature detection algorithm has demonstrated promising performance in low-RCS radar target detection. However, the multi-feature detection method without capability lower bound constraint usually leads to uncertainty in detection result and inefficient allocation of sensing resource in practical applications. To cope with this problem, a radar target multi-feature detection optimization method under capability lower bound constraint is proposed to enhance the robustness and real-time performance of maritime radar target detection in this paper. Without loss of generality, signal-clutter-noise ratio (SCNR) is employed as a representative metric to characterize the distinction between target and clutter, serving as the proxy for the capability lower bound. Firstly, a surrogate model is established to map the relationship between SCNR and detection results by means of the measured radar data. Secondly, an improved average tail margin (ATM) algorithm combined with feature importance analysis is applied to accurately estimate the lower bound, which is adopted to estimate an adaptive detection threshold for suppressing a large amount of background clutter. Finally, the multi-feature detection algorithm finely discriminates target from background clutter. Extensive experiments are carried out both public radar dataset provided by Radar Journal and our measurement radar dataset captured at outfield. The experimental results show that the proposed method not only reduces computational complex with superior real-time detection performance, but also can enhance the robustness without sacrificing detection accuracy, outperforming baseline multi-feature methods including conventional CFAR. This work enhances the reliability and the practical applicability of sea-surface radar target detection, and it demonstrates strong generalization ability under complex maritime environment.
- 18 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (11) , 19896-19908
Training Sample Selection Method Based on Model-Data-Driven Maritime Radar Target Detection
Multidimensional feature extraction and fusion algorithms are widely utilized to improve the performance of radar maritime target detection. However, these methods often suffer from underfitting and overfitting issues due to the uneven distribution of training samples. To enhance the performance of maritime target detection while mitigating the issues of underfitting and overfitting, an effective approach is to improve the comprehensiveness of training samples. This study proposes a novel training sample selection method based on model-data-driven maritime radar target detection. A surrogate equation is constructed in this study using existing empirical models and measured data. Subsequently, it dynamically selects training samples exhibiting strong coverage and compactness, guided by the global and local variation characteristics of this surrogate equation. Experimental results show that, when using the same feature and classifier conditions, the feature classifiers formed by the proposed method outperform those built using traditional sample selection approaches (such as random assignment, expert knowledge, and statistical methods). This superiority is evident across various target types, including daily vessels, small fishing boats, and marine buoys, as well as under diverse sea conditions and observation parameters like incidence angles. This approach not only enhances the performance of maritime target detection, but also ensures the generalization ability of the method.
- 18 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (11) , 19896-19908
Training Sample Selection Method Based on Model-Data-Driven Maritime Radar Target Detection
Multidimensional feature extraction and fusion algorithms are widely utilized to improve the performance of radar maritime target detection. However, these methods often suffer from underfitting and overfitting issues due to the uneven distribution of training samples. To enhance the performance of maritime target detection while mitigating the issues of underfitting and overfitting, an effective approach is to improve the comprehensiveness of training samples. This study proposes a novel training sample selection method based on model-data-driven maritime radar target detection. A surrogate equation is constructed in this study using existing empirical models and measured data. Subsequently, it dynamically selects training samples exhibiting strong coverage and compactness, guided by the global and local variation characteristics of this surrogate equation. Experimental results show that, when using the same feature and classifier conditions, the feature classifiers formed by the proposed method outperform those built using traditional sample selection approaches (such as random assignment, expert knowledge, and statistical methods). This superiority is evident across various target types, including daily vessels, small fishing boats, and marine buoys, as well as under diverse sea conditions and observation parameters like incidence angles. This approach not only enhances the performance of maritime target detection, but also ensures the generalization ability of the method.
- Open Access
- 2 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 44798-44820
Automatic Infrared Ship Target Segmentation Based on Structure Tensor and Maximum Histogram Entropy
- 2 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 44798-44820
Open AccessAutomatic Infrared Ship Target Segmentation Based on Structure Tensor and Maximum Histogram Entropy