Haiwen Zheng

Haiwen Zheng


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
11 August 2026 in Drones
Verified
Journal Article
Open access
PDF file
WJWeijian Jia
Weijian Jia
FWFenghua Wang
Fenghua Wang
HZHaiwen Zheng
Haiwen Zheng
PHPenglei Hu
Penglei Hu
XWXiaobing Wang
Xiaobing Wang
YGYufei Gao
Yufei Gao
To address the susceptibility of single-modality approaches to illumination variations and imaging conditions in low-altitude unmanned aerial vehicle (UAV) detection, this study proposes a structure-aware heterogeneous dual-stream detection network based on infrared and visible-light fusion. First, a multimodal UAV detection dataset oriented toward complex low-altitude scenarios is constructed, providing a data foundation for cross-modal detection research. Then, a structure-aware heterogeneous dual-stream feature extraction framework is designed to enable collaborative modeling of visible-light and infrared features through modality-specific encoding. In the visible-light branch, a Structure-Aware Gated Enhancement Block (SAGE Block) is introduced to enhance the representation of fine-grained structural and edge information. In the cross-modal fusion stage, a Bidirectional Wavelet-Guided Fusion Module (BWFM) is proposed to decouple structural semantics and detailed information in the frequency domain. Adaptive fusion is further achieved through low-frequency cross-modal interaction and high-frequency detail-preservation strategies. Finally, the proposed method is experimentally validated on the proposed Multispectral UAV Detection Dataset (MUDD) and the Multi-scenario Multi-Modality Fusion Dataset (M3FD).. The experimental results show that the proposed method achieves an mAP@0.5 of 0.9680 and an mAP@0.5:0.95 of 0.6794 on the proposed MUDD, as well as an mAP@0.5:0.95 of 0.6072 on the M3FD dataset, demonstrating competitive detection accuracy and generalization capability. Ablation experiments further indicate that the SAGE Block, BWFM, and the low-frequency cross-modal fusion and high-frequency detail-preservation strategies within BWFM all contribute positively to performance improvement.

29 December 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
WJWeijian Jia
Weijian Jia
YZYao Zhao
Yao Zhao
HZHaiwen Zheng
Haiwen Zheng
PHPenglei Hu
Penglei Hu
YGYufei Gao
Yufei Gao

After the unmanned transformation of the transmission system of a heavy tracked vehicle, there are problems of low shift smoothness and long shift time during remote driving. Aiming to realize the smooth shift of tracked vehicles by remote driving, this study mines the manned driving data of the vehicle and develops an auxiliary decision-making model for the shift timing of remote driving. In addition, an integrated shift control strategy of tracked vehicle power transmission based on a hierarchical finite state machine is designed. The effectiveness of the proposed remote control shift strategy for tracked vehicles is verified by bench test and real vehicle test. During the entire shifting process, the average shift impact of the tracked vehicle is 9.02\(\:\text{m/}{\text{s}}^{3}\), the average shift time is 4.6\(\:s\), and the vehicle has good ride comfort。The research results can provide useful guidance and lay a foundation for the research of driving control and trajectory tracking control of this type of heavy tracked vehicle after unmanned transformation.