Hengyang Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hengyang Liu has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Guifang Shao
Xiamen University
2 shared publications - Bolin Cao
School of Computer Science and Engineering, Chongqing University of Technology, Chongqing, China
1 shared publication - Chao Liu
Ocean University of China, Qingdao, Shandong, China
1 shared publication - Cong Zhou
School of Computer Science and Engineering, Chongqing University of Technology, Chongqing, China
1 shared publication - Fen Luo
College of Artificial Intelligence, Chongqing Technology and Business University, Chongqing 400067, People’s Republic of China
1 shared publication - Hongjie Ma
School of Computer Science and Engineering, Chongqing University of Technology, Chongqing 400054, People’s Republic of China
1 shared publication
Latest Publications
- 20 April 2026
- Published by IOP Publishing in Engineering Research Express
- Vol. 8 (9)
Dcmt_Net: Crack Image Segmentation via Dual Frequency-Domain Branches
Cracks are a ubiquitous and critical form of surface damage in infrastructure; their precise detection and segmentation are paramount for structural safety assessment. To address critical challenges such as feature ambiguity in small-scale cracks, boundary discontinuity, and background interference, this paper proposes Dcmt_Net, a crack segmentation network based on a dual-branch encoder architecture. Specifically, the CNN branch incorporates Fourier frequency-domain enhancement and a Channel-Spatial Group Attention mechanism to bolster edge responses and multi-scale feature modeling. Simultaneously, the Transformer branch integrates Wavelet feature enhancement with a local self-attention structure to effectively capture long-range dependencies and the global continuity of crack images. Furthermore, to achieve efficient complementarity across branches, a Feature Difference Fusion Module is designed to optimize the fusion quality of local and global information. Experimental results on multiple public datasets demonstrate that Dcmt_Net outperforms state-ofthe-art methods. Notably, on the DeepCrack dataset, it achieved 91.46% and 89.13% in key metrics such as RE and F1-score, respectively, validating its robustness and generalization ability in complex crack scenarios.
- 20 April 2026
- Published by IOP Publishing in Engineering Research Express
- Vol. 8 (9)
Dcmt_Net: Crack Image Segmentation via Dual Frequency-Domain Branches
Cracks are a ubiquitous and critical form of surface damage in infrastructure; their precise detection and segmentation are paramount for structural safety assessment. To address critical challenges such as feature ambiguity in small-scale cracks, boundary discontinuity, and background interference, this paper proposes Dcmt_Net, a crack segmentation network based on a dual-branch encoder architecture. Specifically, the CNN branch incorporates Fourier frequency-domain enhancement and a Channel-Spatial Group Attention mechanism to bolster edge responses and multi-scale feature modeling. Simultaneously, the Transformer branch integrates Wavelet feature enhancement with a local self-attention structure to effectively capture long-range dependencies and the global continuity of crack images. Furthermore, to achieve efficient complementarity across branches, a Feature Difference Fusion Module is designed to optimize the fusion quality of local and global information. Experimental results on multiple public datasets demonstrate that Dcmt_Net outperforms state-ofthe-art methods. Notably, on the DeepCrack dataset, it achieved 91.46% and 89.13% in key metrics such as RE and F1-score, respectively, validating its robustness and generalization ability in complex crack scenarios.
- 16 September 2025
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 16 (12) , 10799-10818
Multi-scale feature dense connection fusion with hybrid attention mechanism in crack segmentation
- 16 September 2025
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 16 (12) , 10799-10818
Multi-scale feature dense connection fusion with hybrid attention mechanism in crack segmentation
- Open Access
- 22 August 2018
- Published by MDPI AG in Information
- Vol. 9 (9) , 210
Time-Varying Communication Channel High Altitude Platform Station Link Budget and Channel Modeling
Because of the high BER (Bit Error Rate), low time delay and low channel transmission efficiency of HAPS (High Altitude Platform Station) in the near space. The link budget of HAPS and channel model are proposed in this paper. According to the channel characteristic, the channel model is set up, combined with different CNR (Carrier Noise Ratio), elevation angle, coding situations of wireless communication link by using Hamming code, PSK (Pulse Shift Keying) and Golay code respectively, then the situations of link quality and BER are analyzed. The simulation results show that the established model of the link budget and channel are suitable for the theoretical analysis results. The elevation of the HAPS communication link is smaller while the BER is increasing. The case of channel in the coding is better than in the un-coded situation. When every bit power and thermal noise power spectral density is larger, the BER of the HAPS communication link is becoming smaller.
- 22 August 2018
- Published by MDPI AG in Information
- Vol. 9 (9) , 210
Open AccessTime-Varying Communication Channel High Altitude Platform Station Link Budget and Channel Modeling
Because of the high BER (Bit Error Rate), low time delay and low channel transmission efficiency of HAPS (High Altitude Platform Station) in the near space. The link budget of HAPS and channel model are proposed in this paper. According to the channel characteristic, the channel model is set up, combined with different CNR (Carrier Noise Ratio), elevation angle, coding situations of wireless communication link by using Hamming code, PSK (Pulse Shift Keying) and Golay code respectively, then the situations of link quality and BER are analyzed. The simulation results show that the established model of the link budget and channel are suitable for the theoretical analysis results. The elevation of the HAPS communication link is smaller while the BER is increasing. The case of channel in the coding is better than in the un-coded situation. When every bit power and thermal noise power spectral density is larger, the BER of the HAPS communication link is becoming smaller.
- 1 January 2012
- Published by Springer Nature
- p. 1595-1601
Deeply Research on Diversity Evaluation Mode of “Fundamentals of Programming”
- 1 January 2012
- Published by Springer Nature
- p. 1595-1601
Deeply Research on Diversity Evaluation Mode of “Fundamentals of Programming”