প্রচ্ছদ

Hardware-Aware Neural Architecture Search for Real-Time Video Processing in FPGA-Accelerated Endoscopic Imaging

সংরক্ষণ করুন:
প্রকাশিত:Applied Sciences vol. 15, no. 20 (2025), p. 11200-11228
প্রধান লেখক: Zhang Cunguang
অন্যান্য লেখক: Cui Rui, Wang, Gang, Gao, Tong, Jielu, Yan, Weizhi, Xian, Xuekai, Wei, Qin, Yi
প্রকাশিত:
MDPI AG
বিষয়গুলি:
Xilinx Inc
United States > US
Accuracy
Deep learning
Optimization techniques
Temperature
Neural networks
Design
Medical equipment
Energy efficiency
Digital signal processors
Medical imaging
Field programmable gate arrays
Endoscopy
অনলাইন ব্যবহার করুন:Citation/Abstract
Full Text + Graphics
Full Text - PDF
ট্যাগগুলো: ট্যাগ যুক্ত করুন
কোনো ট্যাগ নেই, প্রথমজন হিসাবে ট্যাগ করুন!
সার সংক্ষেপ:Medical endoscopic video processing requires real-time execution of color component acquisition, color filter array (CFA) demosaicing, and high dynamic range (HDR) compression under low-light conditions, while adhering to strict thermal constraints within the surgical handpiece. Traditional hardware-aware neural architecture search (NAS) relies on fixed hardware design spaces, making it difficult to balance accuracy, power consumption, and real-time performance. A collaborative “power-accuracy” optimization method is proposed for hardware-aware NAS. Firstly, we proposed a novel hardware modeling framework by abstracting FPGA heterogeneous resources into unified cell units and establishing a power–temperature closed-loop model to ensure that the handpiece surface temperature does not exceed clinical thresholds. In this framework, we constrained the interstage latency balance in pipelines to avoid routing congestion and frequency degradation caused by deep pipelines. Then, we optimized the NAS strategy by using pipeline blocks and combined with a hardware efficiency reward function. Finally, color component acquisition, CFA demosaicing, dynamic range compression, dynamic precision quantization, and streaming architecture are integrated into our framework. Experiments demonstrate that the proposed method achieves 2.8 W power consumption at 47 °C on a Xilinx ZCU102 platform, with a 54% improvement in throughput (vs. hardware-aware NAS), providing an engineer-ready lightweight network for medical edge devices such as endoscopes.
আইএসএসএন:2076-3417
ডিওআই:10.3390/app152011200
সম্পদ:Publicly Available Content Database