Feng Shi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Feng Shi has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Chaofan Wu
School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China
1 shared publication - Chengze Li
School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China
1 shared publication - Haibo Fan
Science and Technology on Low-Light-Level Night Vision Laboratory, Xi’an 710065, China
1 shared publication - Hezu Bai
School of Physics, Changchun University of Science and Technology, Changchun 130015, China
1 shared publication - Hongchang Cheng
Science and Technology on Low-Light-Level Night Vision Laboratory, Xi’an 710065, China
1 shared publication - Shilong Li
Science and Technology on Low-Light-Level Night Vision Laboratory, Xi’an 710065, China
1 shared publication
Latest Publications
- Open Access
Dark-Scene Neuromorphic Imaging for Human Pose Estimation
Neuromorphic imaging sensors (event cameras) offer a promising paradigm for computational imaging and human pose estimation (HPE) under extreme illumination conditions. Nevertheless, dark-scene background activity originating from photodiode dark current and circuit thermal noise, together with hot-pixel noise, severely corrupts event streams and impedes reliable HPE in low-light scenarios. To address this issue, we propose an adaptive event denoising framework built upon a spatiotemporal Gaussian-weighted neighborhood model with a dynamic thresholding mechanism. It can effectively suppress background activity and hot-pixel noise while preserving edge and motion details critical for pose estimation. Leveraging this denoising front-end, we construct a complete dark-scene neuromorphic HPE pipeline by transferring the pre-trained MediaPipe model onto event-based time-surfaces. Quantitative and qualitative evaluations on public and self-collected datasets demonstrate that our approach outperforms state-of-the-art denoising methods with an improvement of over 20% on public benchmarks and over 30% on self-collected dark-scene data. We expect our work to pave the way toward reliable dark-scene human–robot interaction through robust neuromorphic pose estimation.
Open AccessDark-Scene Neuromorphic Imaging for Human Pose Estimation
Neuromorphic imaging sensors (event cameras) offer a promising paradigm for computational imaging and human pose estimation (HPE) under extreme illumination conditions. Nevertheless, dark-scene background activity originating from photodiode dark current and circuit thermal noise, together with hot-pixel noise, severely corrupts event streams and impedes reliable HPE in low-light scenarios. To address this issue, we propose an adaptive event denoising framework built upon a spatiotemporal Gaussian-weighted neighborhood model with a dynamic thresholding mechanism. It can effectively suppress background activity and hot-pixel noise while preserving edge and motion details critical for pose estimation. Leveraging this denoising front-end, we construct a complete dark-scene neuromorphic HPE pipeline by transferring the pre-trained MediaPipe model onto event-based time-surfaces. Quantitative and qualitative evaluations on public and self-collected datasets demonstrate that our approach outperforms state-of-the-art denoising methods with an improvement of over 20% on public benchmarks and over 30% on self-collected dark-scene data. We expect our work to pave the way toward reliable dark-scene human–robot interaction through robust neuromorphic pose estimation.