Changshun Yuan

Dr. Changshun Yuan

Hangzhou Innovation Institute, Beihang University

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
6 March 2026 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
Fei GaoFei Gao
Fei Gao
WMWeiru Ma
Weiru Ma
CYChangshun Yuan
Changshun Yuan
JWJun Wang
Jun Wang
JSJinping Sun
Jinping Sun
AHAmir Hussain
Amir Hussain
In the field of synthetic aperture radar (SAR) target recognition, leveraging computer-generated labeled simulated SAR data to aid in the recognition of unlabeled real SAR data has garnered significant attention. However, the domain shift between the simulated and real domain contravenes the assumption of independent and identically distributed in deep learning. Moreover, the categories of real SAR data may not align precisely with those of the simulated SAR data, and the prior knowledge of the label shift typically remains unavailable. To align the common category samples and identify target-private unknown category samples in the presence of both domain shift and potential label shift, we introduce a two-stage universal domain adaptation (UniDA) method for simulation-assisted SAR target recognition based on adversarial uncertainty and neighbor relation (AUNR). The proposed AUNR introduces Dirichlet distribution-based evidential deep learning, which not only performs classification tasks but also characterizes decision uncertainty, enabling the model to express the concept of “Unknow”. In the first stage, alongside supervised learning, we leverage data augmentation-based contrastive learning to achieve robust feature representation. In the second stage, adversarial learning based on model and data uncertainty is employed to separate common and unknown class samples, and contrastive learning based on neighbor relation aligns samples in two domains according to their geometric relationships. To the best of our knowledge, this is the first study on UniDA for SAR target recognition. Experimental results demonstrate that our method outperforms previous state of-the-art methods in various label shift scenarios, which indicates the effectiveness of the proposed method.

4 January 2021 in Photonics
Verified
Journal Article
Open access
PDF file
Fulong YanFulong Yan
Fulong Yan
CYChangshun Yuan
Changshun Yuan
CLChao Li
Chao Li
Xiong DengXiong Deng
Xiong Deng
Interconnecting networks adopting Fast Optical Switches (FOS) can achieve high bandwidth, low latency, and low power consumption. We propose and demonstrate a novel interconnecting topology based on FOS (FOSquare) with distributed fast flow control which is suitable for HPC infrastructures. We also present an Optimized Mapping (OPM) algorithm that maps the most communication-related processes inside a rack. We numerically investigate and compare the network performance of FOSquare with Leaf-Spine under real traffic traces collected by running multiple applications (CG, MG, MILC, and MINI_MD) in an HPC infrastructure. The numerical results show that the FOSquare can reduce >10% latency with respect to Leaf-Spine under the scenario of 16 available cores.

4 December 2015 in Sensors
Verified
Journal Article
Open access
PDF file
CYChangshun Yuan
Changshun Yuan
JWJun Wang
Jun Wang
PLPeng Lei
Peng Lei
YBYanxian Bi
Yanxian Bi
ZSZhongsheng Sun
Zhongsheng Sun
Knowledge of the clutter rate is of critical importance in multi-target Bayesian tracking. However, estimating the clutter rate is a difficult problem in practice. In this paper, an improved multi-Bernoulli filter based on random finite sets for multi-target Bayesian tracking accommodating non-linear dynamic and measurement models, as well as unknown clutter rate, is proposed for radar sensors. The proposed filter incorporates the amplitude information into the state and measurement spaces to improve discrimination between actual targets and clutters, while adaptively generating the new-born object random finite sets using the measurements to eliminate reliance on prior random finite sets. A sequential Monte-Carlo implementation of the proposed filter is presented, and simulations are used to demonstrate the proposed filter’s improvements in estimation accuracy of the target number and corresponding multi-target states, as well as the clutter rate.

11 January 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YWYuzhan Wu
Yuzhan Wu
CLChenlong Li
Chenlong Li
CYChangshun Yuan
Changshun Yuan
MLMeng Li
Meng Li
HLHao Li
Hao Li
Tracking control of Small Unmanned Ground Vehicles (SUGVs) is easily affected by the nonlinearity and time-varying characteristics. An improved predictive control scheme based on the multi-dimensional Taylor network (MTN) is proposed for tracking control of SUGVs. First, a MTN model is used as a predictive model to construct a SUGV model and back propagation (BP) is taken as its learning algorithm. Second, the predictive control law is designed and the traditional objective function is improved to obtain a predictive objective function with a differential term. The optimal control quantity is given in real time through iterative optimization. Meanwhile, the stability of the closed-loop system is proved by the Lyapunov stability theorem. Finally, a tracking control experiment on the SUGV model is used to verify the effectiveness of the proposed scheme. For comparison, traditional MTN and Radial Basis Function (RBF) predictive control schemes are introduced. Moreover, a noise disturbance is considered. Experimental results show that the proposed scheme is effective, which ensures that the vehicle can quickly and accurately track the desired yaw velocity signal with good real-time, robustness, and convergence performance, and is superior to other comparison schemes.

21 May 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
WWWenguang Wang
Wenguang Wang
JZJinshuo Zhao
Jinshuo Zhao
CYChangshun Yuan
Changshun Yuan
HWHaoran Wang
Haoran Wang
To address the issue where conventional initial registration methods combined with the Iterative Closest Point (ICP) algorithm are highly sensitive to initial parameters such as point cloud density and pose—often resulting in degraded accuracy or even misregistration—this paper proposes a Lidar point cloud registration method integrating triangular mesh features. First, Crust Triangulation is employed to construct a triangular mesh from the input point cloud. Then, the keypoint extraction based on triangular meshes, termed KE-TM, is introduced. Subsequently, a Triangle Feature Histogram (TFH) is constructed as the feature descriptor. Based on this, an initial alignment method grounded in triangular meshes, referred to as TM-IA, is developed to achieve coarse registration of point clouds. Finally, the ICP algorithm is applied to refine the alignment. Comparative experiments conducted on incomplete Bunny point clouds demonstrate that the proposed KE-TM maintains a higher keypoint repeatability under reduced point cloud density. The combined TM-IA and ICP registration method can achieve rotation errors within 1° and translation errors within 1 mm under small initial pose deviations, while also maintaining robust performance under larger initial misalignments. Compared with traditional methods, the proposed method significantly reduces sensitivity to initial parameters and improves the accuracy. This method has certain practical significance for the precise alignment of 3D point clouds.

22 April 2026 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
YLYaxin Li
Yaxin Li
JWJun Wang
Jun Wang
CYChangshun Yuan
Changshun Yuan
XYXiaoming Yuan
Xiaoming Yuan
YLYuquan Luo
Yuquan Luo
SLSong Liang
Song Liang
Millimeter-wave (mmWave) radar has emerged as a promising sensing modality for 3D human pose estimation in ubiquitous Internet of Things (IoT) applications, owing to its privacy-preserving nature and robustness under challenging illumination conditions. However, accurate skeletal reconstruction remains difficult due to the inherent sparsity, non-uniform distribution, and instability of radar point clouds. To address these challenges, this paper proposes MS-STPoseNet, a unified multi-scale spatio-temporal learning framework for robust mmWavebased human pose estimation. For spatial representation, MS-STPoseNet employs a hierarchical multi-scale spatial encoder built upon PointNet++, which leverages multi-scale grouping to effectively capture body structures across different spatial resolutions, from fine-grained joint regions to limb- and torso-level configurations, under irregular radar observations. For temporal modeling, a multi-branch Temporal Convolutional Network (TCN) with different dilation rates is introduced to model multi-rate motion dynamics, enabling effective representation of both rapid limb movements and smoother torso motions. An attention mechanism is further incorporated to enhance informative temporal features while suppressing noise. The entire framework is trained end-to-end to estimate per-frame 3D poses by exploiting short-term temporal context, thereby improving robustness under noisy sensing conditions. Extensive experiments conducted on a self-collected dataset and two public benchmarks demonstrate that MS-STPoseNet consistently outperforms state-of-the-art methods in terms of pose estimation accuracy and cross-subject generalization, achieving an MPJPE of 3.08 cm on the self-collected dataset. In addition, the proposed framework exhibits favorable computational efficiency and a compact model size, highlighting its potential applicability to practical IoT sensing systems.