Jiongnan Lou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jiongnan Lou has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Lianxin Hu
School of Information Engineering, Huzhou Normal University, Huzhou 313000, China
3 shared publications Haifei Shen
2 shared publicationsXun Zhang
LISIT-ECoS
2 shared publicationsYiqian Qian
2 shared publicationsZefeng Wang
Zhejiang-France Joint Laboratory for Digital Monitoring of Aquatic Resources and the Environment
2 shared publicationsZhan Wang
2 shared publications
Latest Publications
- 3 April 2026
- Published by Optica Publishing Group in Applied Optics
- Vol. 65 (11) , 3654-3663
Efficient and robust 3D indoor visible light positioning via uniform and power-of-two quantization on multi-head ResNet50
Existing indoor positioning methods in visible light communication systems typically rely on large databases, powerful signal processing units, and additional sensors such as gyroscopes, which limit their applicability in efficiency-sensitive scenarios. To address this issue and achieve an optimal balance between positioning accuracy, inference time, and model size, we propose uniform and power-of-two quantization on a multi-head ResNet50 (UPU-MH-ResNet50) algorithm in this paper. The proposed algorithm does not require additional sensors and can accurately estimate the three-dimensional coordinates of the receiver, including X and Y coordinates and rotation angle. It effectively mitigates the impact of random angle changes on positioning accuracy, significantly enhancing the system’s robustness. Additionally, the algorithm is further optimized through model quantization to reduce computational costs. We conducted validation on a self-built experimental testbed in a laboratory environment with dimensions of 2.6m×2.6m×2.2m and a receiver rotation angle range of ±30 ∘ . Within this tilt range, 90% of the 3D positioning errors are controlled within 2 cm. Moreover, the proposed 4-bit UPU-MH-ResNet50 achieves a 7.7× reduction in model size and a 2.7× speedup in inference, where the acceleration and efficiency results are measured from the GPU-based implementation using real captured data collected on the developed testbed, indicating high energy efficiency.
- 3 April 2026
- Published by Optica Publishing Group in Applied Optics
- Vol. 65 (11) , 3654-3663
Efficient and robust 3D indoor visible light positioning via uniform and power-of-two quantization on multi-head ResNet50
Existing indoor positioning methods in visible light communication systems typically rely on large databases, powerful signal processing units, and additional sensors such as gyroscopes, which limit their applicability in efficiency-sensitive scenarios. To address this issue and achieve an optimal balance between positioning accuracy, inference time, and model size, we propose uniform and power-of-two quantization on a multi-head ResNet50 (UPU-MH-ResNet50) algorithm in this paper. The proposed algorithm does not require additional sensors and can accurately estimate the three-dimensional coordinates of the receiver, including X and Y coordinates and rotation angle. It effectively mitigates the impact of random angle changes on positioning accuracy, significantly enhancing the system’s robustness. Additionally, the algorithm is further optimized through model quantization to reduce computational costs. We conducted validation on a self-built experimental testbed in a laboratory environment with dimensions of 2.6m×2.6m×2.2m and a receiver rotation angle range of ±30 ∘ . Within this tilt range, 90% of the 3D positioning errors are controlled within 2 cm. Moreover, the proposed 4-bit UPU-MH-ResNet50 achieves a 7.7× reduction in model size and a 2.7× speedup in inference, where the acceleration and efficiency results are measured from the GPU-based implementation using real captured data collected on the developed testbed, indicating high energy efficiency.
- 3 December 2025
- Published by Optica Publishing Group in Applied Optics
- Vol. 64 (35) , 10487-10496
Multimodal deep learning for intelligent camera parameter control in underwater optical camera communication imaging
Underwater optical camera communication (UOCC) relies on image-based signal reception, where the quality of recorded stripes directly determines the achievable optical signal-to-noise ratio (SNR). However, fixed camera parameters—such as exposure level and International Standards Organization (ISO) sensitivity—are often inadequate under dynamically varying aquatic conditions including turbidity, flow velocity, and ambient illumination. To overcome these limitations, we propose a multimodal deep model that fuses visual cues with environmental context to predict scene-optimal camera parameters at capture time. A ResNet50 backbone extracts semantic representations from raw stripe images, while environmental factors—including turbidity, flow speed, ambient illumination, and LED power—are jointly encoded through a parallel embedding architecture. These modalities are fused within a regression network to infer settings that maximize imaging clarity and stability. The experimental results demonstrate that the proposed model achieves robust accuracy. Crucially, the capture-time parameter selection improves stripe visibility and delivers an average ∼3dB gain in optical SNR across diverse conditions. This capture-time optimization sustains a higher and more stable SNR band than both the original fixed settings and a representative learning-based post-processing baseline (DnCNN with horizontal-banding suppression). Beyond accuracy, the approach is computationally light and portable: context-aware parameter prediction at capture time eliminates per-frame processing, providing a practical route to real-time, resource-constrained UOCC with enhanced image quality and robustness.
- 3 December 2025
- Published by Optica Publishing Group in Applied Optics
- Vol. 64 (35) , 10487-10496
Multimodal deep learning for intelligent camera parameter control in underwater optical camera communication imaging
Underwater optical camera communication (UOCC) relies on image-based signal reception, where the quality of recorded stripes directly determines the achievable optical signal-to-noise ratio (SNR). However, fixed camera parameters—such as exposure level and International Standards Organization (ISO) sensitivity—are often inadequate under dynamically varying aquatic conditions including turbidity, flow velocity, and ambient illumination. To overcome these limitations, we propose a multimodal deep model that fuses visual cues with environmental context to predict scene-optimal camera parameters at capture time. A ResNet50 backbone extracts semantic representations from raw stripe images, while environmental factors—including turbidity, flow speed, ambient illumination, and LED power—are jointly encoded through a parallel embedding architecture. These modalities are fused within a regression network to infer settings that maximize imaging clarity and stability. The experimental results demonstrate that the proposed model achieves robust accuracy. Crucially, the capture-time parameter selection improves stripe visibility and delivers an average ∼3dB gain in optical SNR across diverse conditions. This capture-time optimization sustains a higher and more stable SNR band than both the original fixed settings and a representative learning-based post-processing baseline (DnCNN with horizontal-banding suppression). Beyond accuracy, the approach is computationally light and portable: context-aware parameter prediction at capture time eliminates per-frame processing, providing a practical route to real-time, resource-constrained UOCC with enhanced image quality and robustness.
- Open Access
Adaptive Exposure Optimization for Underwater Optical Camera Communication via Multimodal Feature Learning and Real-to-Sim Channel Emulation
Underwater Optical Camera Communication (UOCC) has emerged as a promising paradigm for short-range, high-bandwidth, and secure data exchange in autonomous underwater vehicles (AUVs). UOCC performance strongly depends on exposure time and International Standards Organization (ISO) sensitivity—two parameters that govern photon capture, contrast, and bit detection fidelity. However, optical propagation in aquatic environments is highly susceptible to turbidity, scattering, and illumination variability, which severely degrade image clarity and signal-to-noise ratio (SNR). Conventional systems with fixed imaging settings cannot adapt to time-varying conditions, limiting communication reliability. While validating the feasibility of deep learning for exposure prediction, this baseline lacked environmental awareness and generalization to dynamic scenarios. To overcome these limitations, we introduce a Real-to-Sim-to-Deployment framework that couples a physically calibrated emulation platform with a Hybrid CNN-MLP Model (HCMM). By fusing optical images, environmental states, and camera configurations, the HCMM achieves substantially improved parameter prediction accuracy, reducing RMSE to 0.23–0.33. When deployed on embedded hardware, it enables real-time adaptive reconfiguration and delivers up to 8.5 dB SNR gain, surpassing both static-parameter systems and the prior CNN baseline. These results demonstrate that environment-aware multimodal learning, supported by reproducible optical channel emulation, provides a scalable and robust solution for practical UOCC deployment in positioning, inspection, and laser-based underwater communication.
Open AccessAdaptive Exposure Optimization for Underwater Optical Camera Communication via Multimodal Feature Learning and Real-to-Sim Channel Emulation
Underwater Optical Camera Communication (UOCC) has emerged as a promising paradigm for short-range, high-bandwidth, and secure data exchange in autonomous underwater vehicles (AUVs). UOCC performance strongly depends on exposure time and International Standards Organization (ISO) sensitivity—two parameters that govern photon capture, contrast, and bit detection fidelity. However, optical propagation in aquatic environments is highly susceptible to turbidity, scattering, and illumination variability, which severely degrade image clarity and signal-to-noise ratio (SNR). Conventional systems with fixed imaging settings cannot adapt to time-varying conditions, limiting communication reliability. While validating the feasibility of deep learning for exposure prediction, this baseline lacked environmental awareness and generalization to dynamic scenarios. To overcome these limitations, we introduce a Real-to-Sim-to-Deployment framework that couples a physically calibrated emulation platform with a Hybrid CNN-MLP Model (HCMM). By fusing optical images, environmental states, and camera configurations, the HCMM achieves substantially improved parameter prediction accuracy, reducing RMSE to 0.23–0.33. When deployed on embedded hardware, it enables real-time adaptive reconfiguration and delivers up to 8.5 dB SNR gain, surpassing both static-parameter systems and the prior CNN baseline. These results demonstrate that environment-aware multimodal learning, supported by reproducible optical channel emulation, provides a scalable and robust solution for practical UOCC deployment in positioning, inspection, and laser-based underwater communication.