Yuancheng Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yuancheng Yang has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Chao Tong
School of Computer Science and Engineering, Beihang University, Beijing, China
2 shared publications - Luyang Jin
Beihang University, Beijing, China
1 shared publication - Shuai Zhang
University of Science and Technology Beijing, Beijing, China
1 shared publication Tingting Yang
School of Computer Science and Engineering, Beihang University, Beijing, China
1 shared publication
Latest Publications
- 11 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (2) , 2240-2251
Lightweight Deep Learning Framework for Real-Time Traffic Sign Detection on In-Vehicle Embedded Computing Platforms
Traffic sign detection is crucial for both autonomous and manual driving, but high-resolution images from in-vehicle cameras pose challenges due to the small size of distant objects and the substantial computational cost. Due to the limited computational and parallel processing capabilities of in-vehicle computing platforms, achieving real-time, high-precision traffic sign detection in practical scenarios based on high-resolution images becomes impractical. Therefore, we propose a lightweight subgraph-based deep learning traffic sign detection framework tailored for in-vehicle embedded computing devices. The framework comprises two sub-models: 1) a Subgraph Filtering Model based on lightweight Convolutional Neural Networks, and 2) a Lightweight Deep Learning Traffic Sign Detection Model. The proposed framework enables to input high-resolution images while significantly reducing computational costs and produces high-precision traffic sign detection results. Experimental results on the TT100K dataset show an mAP@0.5 of 0.954 with only 0.93M parameters, demonstrating the framework’s ability to perform real-time, high-precision traffic sign detection on in-vehicle embedded devices.
- 11 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (2) , 2240-2251
Lightweight Deep Learning Framework for Real-Time Traffic Sign Detection on In-Vehicle Embedded Computing Platforms
Traffic sign detection is crucial for both autonomous and manual driving, but high-resolution images from in-vehicle cameras pose challenges due to the small size of distant objects and the substantial computational cost. Due to the limited computational and parallel processing capabilities of in-vehicle computing platforms, achieving real-time, high-precision traffic sign detection in practical scenarios based on high-resolution images becomes impractical. Therefore, we propose a lightweight subgraph-based deep learning traffic sign detection framework tailored for in-vehicle embedded computing devices. The framework comprises two sub-models: 1) a Subgraph Filtering Model based on lightweight Convolutional Neural Networks, and 2) a Lightweight Deep Learning Traffic Sign Detection Model. The proposed framework enables to input high-resolution images while significantly reducing computational costs and produces high-precision traffic sign detection results. Experimental results on the TT100K dataset show an mAP@0.5 of 0.954 with only 0.93M parameters, demonstrating the framework’s ability to perform real-time, high-precision traffic sign detection on in-vehicle embedded devices.
- Open Access
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1672-1681
Separable and Flexible Classification on Pseudo-Features for Few-Shot Class-Incremental Learning
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1672-1681
Open AccessSeparable and Flexible Classification on Pseudo-Features for Few-Shot Class-Incremental Learning