Huoping Yi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Huoping Yi has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Ping Tan
School of Automation and Electrical Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, China
4 shared publications - Yongbo Wu
School of Automation and Electrical Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, China
3 shared publications - Zhen Xu
School of Automation and Electrical Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, China
3 shared publications - Agustin Motuhu Oyegue Onguene1 shared publication
- Cedrick B. Atse
School of Automation and Electrical Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, China
1 shared publication Fuhao Chang
College of Automation and Electrical Engineering, Zhejiang University of Science and Technology, Hangzhou, China
1 shared publication
Latest Publications
- Open Access
- 3 November 2026
- Published by MDPI AG in Computation
- Vol. 14 (11) , 273
PDR-DETR: Prior-Driven and Detail-Refined Detection Transformer for Railway Signal Light Detection
Reliable railway signal light detection remains challenging because distant signals occupy only a small image area and are easily confused with complex background structures. To address unreliable ranking of weak foreground candidates and insufficient local-detail retrieval in Detection Transformer (DETR)-based detectors, we propose the Prior-Driven and Detail-Refined Detection Transformer (PDR-DETR), built on the Real-Time Detection Transformer (RT-DETR). PDR-DETR introduces two stage-specific modules. Query-guided frequency prior injection (QFPI) converts target-related spectral responses into priors for encoder-memory recalibration and multi-scale query ranking, improving the selection of weak foreground candidates. Reference-guided cross-scale local aggregation (RCLA) retrieves candidate-centered local evidence from high-resolution features to refine intermediate decoder queries. Experiments on a self-collected five-category railway signal light dataset containing 12,810 images show that PDR-DETR achieves 0.580 and 0.561 , improving the RT-DETR baseline by 0.041 and 0.037, respectively. These results demonstrate the effectiveness of the proposed prior-to-detail detection framework for small railway signal light detection in complex railway environments.- 3 November 2026
- Published by MDPI AG in Computation
- Vol. 14 (11) , 273
Open AccessPDR-DETR: Prior-Driven and Detail-Refined Detection Transformer for Railway Signal Light Detection
Reliable railway signal light detection remains challenging because distant signals occupy only a small image area and are easily confused with complex background structures. To address unreliable ranking of weak foreground candidates and insufficient local-detail retrieval in Detection Transformer (DETR)-based detectors, we propose the Prior-Driven and Detail-Refined Detection Transformer (PDR-DETR), built on the Real-Time Detection Transformer (RT-DETR). PDR-DETR introduces two stage-specific modules. Query-guided frequency prior injection (QFPI) converts target-related spectral responses into priors for encoder-memory recalibration and multi-scale query ranking, improving the selection of weak foreground candidates. Reference-guided cross-scale local aggregation (RCLA) retrieves candidate-centered local evidence from high-resolution features to refine intermediate decoder queries. Experiments on a self-collected five-category railway signal light dataset containing 12,810 images show that PDR-DETR achieves 0.580 and 0.561 , improving the RT-DETR baseline by 0.041 and 0.037, respectively. These results demonstrate the effectiveness of the proposed prior-to-detail detection framework for small railway signal light detection in complex railway environments. - Open Access
- 10 September 2026
- Published by Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne in Eksploatacja i Niezawodność – Maintenance and Reliability
Real-Time Human Pose Estimation Based on Selective Knowledge Distillation and Robot Occlusion Detection in Football Stadiums
In dynamic, occlusion-prone environments like football stadiums, reliable human pose estimation is essential for mobile robots, where conventional systems often fail due to partial visibility and rapid motion. This paper presents a lightweight pose estimation framework for real-time operation on resource-constrained edge platforms and the X5 robot. It employs selective knowledge distillation to transfer occlusion-robust and motion-aware features from a pre-trained teacher model to a compact student model, preserving efficiency while enhancing reliability. Three components are integrated by synthetic occlusion pattern embeddings for visibility, temporal motion cue extraction for movements and cross-modal attention alignment to focus on visible body regions. Validated on the D-Robotics mono2d_body_detection benchmark, the system achieves accuracy improvements under heavy occlusion while maintaining ≥30 FPS on the target platform. Experimental results confirm the framework balances high accuracy with low complexity, which makes it suitable for reliable deployment in football stadiums.
- 10 September 2026
- Published by Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne in Eksploatacja i Niezawodność – Maintenance and Reliability
Open AccessReal-Time Human Pose Estimation Based on Selective Knowledge Distillation and Robot Occlusion Detection in Football Stadiums
In dynamic, occlusion-prone environments like football stadiums, reliable human pose estimation is essential for mobile robots, where conventional systems often fail due to partial visibility and rapid motion. This paper presents a lightweight pose estimation framework for real-time operation on resource-constrained edge platforms and the X5 robot. It employs selective knowledge distillation to transfer occlusion-robust and motion-aware features from a pre-trained teacher model to a compact student model, preserving efficiency while enhancing reliability. Three components are integrated by synthetic occlusion pattern embeddings for visibility, temporal motion cue extraction for movements and cross-modal attention alignment to focus on visible body regions. Validated on the D-Robotics mono2d_body_detection benchmark, the system achieves accuracy improvements under heavy occlusion while maintaining ≥30 FPS on the target platform. Experimental results confirm the framework balances high accuracy with low complexity, which makes it suitable for reliable deployment in football stadiums.
- Open Access
Dynamic Scheduling and Adaptive Power Control for LoRaWAN-Based Waste Management: An Energy-Efficient IoT Framework
Efficient waste management is a critical challenge in urban areas. This paper explores the optimization of power consumption in a smart bin management system using LoRa (long-range) communication technology. LoRa’s low-power, wide-area capabilities make it an ideal choice for IoT-based waste management systems. However, energy efficiency remains a crucial factor for ensuring the long-term sustainability of such systems, to avoid frequent intervention and reduce operating costs. This study employs advanced optimization techniques to minimize the energy usage of LoRa nodes while maintaining a reliable data transmission and system performance. By integrating a dynamic scheduling algorithm based on the usage of bins, and a custom adaptive data rate and power algorithm, the proposed solution significantly reduces the system’s energy impact. The performance of the system is evaluated through simulations and real-world deployment, where the results demonstrate a significant reduction in energy usage, over 84%, a longer battery life, and fewer maintenance interventions. The findings provide a scalable and energy-efficient framework for deploying smart waste management systems in resource-constrained environments.
Open AccessDynamic Scheduling and Adaptive Power Control for LoRaWAN-Based Waste Management: An Energy-Efficient IoT Framework
Efficient waste management is a critical challenge in urban areas. This paper explores the optimization of power consumption in a smart bin management system using LoRa (long-range) communication technology. LoRa’s low-power, wide-area capabilities make it an ideal choice for IoT-based waste management systems. However, energy efficiency remains a crucial factor for ensuring the long-term sustainability of such systems, to avoid frequent intervention and reduce operating costs. This study employs advanced optimization techniques to minimize the energy usage of LoRa nodes while maintaining a reliable data transmission and system performance. By integrating a dynamic scheduling algorithm based on the usage of bins, and a custom adaptive data rate and power algorithm, the proposed solution significantly reduces the system’s energy impact. The performance of the system is evaluated through simulations and real-world deployment, where the results demonstrate a significant reduction in energy usage, over 84%, a longer battery life, and fewer maintenance interventions. The findings provide a scalable and energy-efficient framework for deploying smart waste management systems in resource-constrained environments.
- 10 November 2025
- Published by Zhejiang University Press in Journal of Zhejiang University-SCIENCE A
- Vol. 26 (11) , 1127-1140
A dual-focal-plane augmented reality head-up display optical system adapted for heavy-haul locomotives
Heavy-haul locomotives operate in complex and dynamic environments. Drivers are required to frequently monitor numerous displays within the cab and track c
- 10 November 2025
- Published by Zhejiang University Press in Journal of Zhejiang University-SCIENCE A
- Vol. 26 (11) , 1127-1140
A dual-focal-plane augmented reality head-up display optical system adapted for heavy-haul locomotives
Heavy-haul locomotives operate in complex and dynamic environments. Drivers are required to frequently monitor numerous displays within the cab and track c