Huiyan Han

Dr. Huiyan Han


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
3 July 2024 in Scientific Reports
Verified
Journal Article
Open access
PDF file
HHHuiyan Han
Huiyan Han
HZHongwei Zeng
Hongwei Zeng
LKLiqun Kuang
Liqun Kuang
XHXie Han
Xie Han
HXHongxin Xue
Hongxin Xue
Human activity recognition has a wide range of applications in various fields, such as video surveillance, virtual reality and human–computer intelligent interaction. It has emerged as a significant research area in computer vision. GCN (Graph Convolutional networks) have recently been widely used in these fields and have made great performance. However, there are still some challenges including over-smoothing problem caused by stack graph convolutions and deficient semantics correlation to capture the large movements between time sequences. Vision Transformer (ViT) is utilized in many 2D and 3D image fields and has surprised results. In our work, we propose a novel human activity recognition method based on ViT (HAR-ViT). We integrate enhanced AGCL (eAGCL) in 2s-AGCN to ViT to make it process spatio-temporal data (3D skeleton) and make full use of spatial features. The position encoder module orders the non-sequenced information while the transformer encoder efficiently compresses sequence data features to enhance calculation speed. Human activity recognition is accomplished through multi-layer perceptron (MLP) classifier. Experimental results demonstrate that the proposed method achieves SOTA performance on three extensively used datasets, NTU RGB+D 60, NTU RGB+D 120 and Kinetics-Skeleton 400.

15 June 2023 in Sensors
Verified
Journal Article
Open access
PDF file
HHHuiyan Han
Huiyan Han
JWJiaqi Wang
Jiaqi Wang
LKLiqun Kuang
Liqun Kuang
XHXie Han
Xie Han
HXHongxin Xue
Hongxin Xue
With the advancement of robotics, the field of path planning is currently experiencing a period of prosperity. Researchers strive to address this nonlinear problem and have achieved remarkable results through the implementation of the Deep Reinforcement Learning (DRL) algorithm DQN (Deep Q-Network). However, persistent challenges remain, including the curse of dimensionality, difficulties of model convergence and sparsity in rewards. To tackle these problems, this paper proposes an enhanced DDQN (Double DQN) path planning approach, in which the information after dimensionality reduction is fed into a two-branch network that incorporates expert knowledge and an optimized reward function to guide the training process. The data generated during the training phase are initially discretized into corresponding low-dimensional spaces. An “expert experience” module is introduced to facilitate the model’s early-stage training acceleration in the Epsilon–Greedy algorithm. To tackle navigation and obstacle avoidance separately, a dual-branch network structure is presented. We further optimize the reward function enabling intelligent agents to receive prompt feedback from the environment after performing each action. Experiments conducted in both virtual and real-world environments have demonstrated that the enhanced algorithm can accelerate model convergence, improve training stability and generate a smooth, shorter and collision-free path.

23 April 2025 in Electronics
Verified
Journal Article
Open access
PDF file
HSHang Sui
Hang Sui
HHHuiyan Han
Huiyan Han
YCYuzhu Cui
Yuzhu Cui
MYMenglong Yang
Menglong Yang
BPBinwei Pei
Binwei Pei
Pedestrian detection technology refers to identifying pedestrians within the field of view and is widely used in smart cities, public safety surveillance, and other scenarios. However, in real-world complex scenes, challenges such as high pedestrian density, occlusion, and low lighting conditions lead to blurred image boundaries, which significantly impact accuracy of pedestrian detection. To address these challenges, we propose a novel pedestrian detection algorithm, FA-YOLO. First, to address issues of limited effective information extraction in backbone network and insufficient feature map representation, we propose a feature enhancement module (FEM) that integrates both global and local features of the feature map, thereby enhancing the network’s feature representation capability. Then, to reduce redundant information and improve adaptability to complex scenes, an adaptive sparse self-attention (ASSA) module is designed to suppress noise interactions in irrelevant regions and eliminate feature redundancy across both spatial and channel dimensions. Finally, to further enhance the model’s focus on target features, we propose cross stage partial with adaptive sparse self-attention (C3ASSA), which improves overall detection performance by reinforcing the importance of target features during the final detection stage. Additionally, a scalable intersection over union (SIoU) loss function is introduced to address the vector angle differences between predicted and ground-truth bounding boxes. Extensive experiments on the WiderPerson and RTTS datasets demonstrate that FA-YOLO achieves State-of-the-Art performance, with a precision improvement of 3.5% on the WiderPerson and 3.0% on RTTS compared to YOLOv11.

7 February 2024 in Research Square
Verified
Preprint
Open access
PDF file
HHHuiyan Han
Huiyan Han
HZHongwei Zeng
Hongwei Zeng
LKLiqun Kuang
Liqun Kuang
XHXie Han
Xie Han
HXHongxin Xue
Hongxin Xue
Human activity recognition has a wide range of applications in various fields, such as video surveillance, virtual reality, and human-computer intelligent interaction. It has emerged as a significant research area in computer vision. Key algorithms utilized include P-LSTM (partial sensing LSTM), ST-GCN (Spatiotemporal graph convolutional networks), and 2s-AGCN (two-flow adaptive graph convolutional networks). Despite the remarkable achievements made by these algorithms, there are still some challenges to address, including unsatisfactory recognition accuracy, convergence difficulties, and limited generalization ability. To tackle these issues, this paper proposes HAR-ViT - a human activity recognition method based on Vision Transformer architecture. The enhanced AGCN (eAGCN) map filter is employed to assign weights to human skeleton data, highlighting key nodes and promoting model convergence. The position encoder module captures precise timing information while the transformer encoder efficiently compresses sequence data features to enhance calculation speed. Human activity recognition is accomplished through multi-layer perceptron (MLP) classifiers. Experimental results demonstrate that the proposed method achieves an accuracy of 91.06% for cross-subject and 96.73% for cross-view human behavior recognition on the NTU60 dataset respectively; similarly achieving accuracies of 87.61% and 89.02% on the NTU120 dataset for the same task respectively compared to state-of-the-art algorithms with an improved accuracy of approximately 1%, while reducing total parameter count by 57.24%.

22 July 2026 in Sensors
Verified
Journal Article
Open access
PDF file
YLYufeng Li
Yufeng Li
ETErming Tian
Erming Tian
FYFuhe Yang
Fuhe Yang
HHHuiyan Han
Huiyan Han
XZXinya Zhang
Xinya Zhang
To enhance unmanned ground vehicle (UGV) intelligence in smart cities, disaster rescue, and infrastructure inspection, this paper investigates the collaborative optimization of multimodal fusion end-to-end architectures. Through dynamic alignment of heterogeneous features, a multi-head distillation attention mechanism, and parallel decision-planning, a high-precision, low-latency closed-loop autonomous navigation framework is constructed. A Multi-Head Distillation Attention-based Trajectory Prediction (MDA-TP) method is proposed, combining a BEVFormer-based multimodal fusion perception model with a two-stage progressive knowledge distillation framework. On NuScenes, the method achieves an ADE of 0.88 m, an FDE of 1.32 m (4.34% and 10.81% reductions), and a collision rate of 15.2%, with 42.6 M parameters and 46 ms latency. Ablation shows removing attention distillation increases FDE by 13.6%. For system validation, a multi-sensor UGV platform is built. Through NuScenes online testing and real-world closed-loop validation, the Euclidean deviation remains within 0.5 m. Compared with traditional distillation, speed prediction MSE is reduced by 51.5%, wheel angle RMSE by 58.4%, and route completion improves from 60.99% to 97.26%. The results provide practical support for autonomous driving in smart cities, disaster rescue, and infrastructure inspection.

30 August 2025 in Cluster Computing
Verified
Journal Article
Closed access
PDF file
HHHuiyan Han
Huiyan Han
WLWanning Li
Wanning Li
XHXie Han
Xie Han
LKLiqun Kuang
Liqun Kuang
XYXiaowen Yang
Xiaowen Yang