|
|
|
| Edge Chip Deployment Methods for Lightweight Infrared Computational Imaging Reconstruction Algorithms |
| ZHAO Ziyu1，2， WANG Xuquan1，2， MA Jie3， XING Yujie1，2， DUN Xiong1，2， WANG Zhanshan1，2， CHENG Xinbin1，2 |
| 1. Institute of Precision Optical Engineering， School of Physics Science and Engineering， Tongji University， Shanghai 200092， China； 2. MOE Key Laboratory of Advanced Micro-Structured Materials， Tongji University， Shanghai 200092， China； 3. College of Electronics and Information Engineering， Tongji University， Shanghai 200092， China |
|
|
|
|
Abstract By integrating intelligent algorithm-driven image processing techniques, computational imaging has the potential to transcend the limits of conventional hardware-centric optical systems, enabling optical systems to achieve high performance and a compact design. Focusing on the image reconstruction requirements in lightweight infrared single-lens computational imaging, this study investigated lightweight model deployment methodologies tailored for edge AI chips. Through targeted operator optimisation, model pruning, and quantisation implemented on edge devices, the deployed U-Net reconstruction model achieved a 52.3% reduction in parameters and a 60.3% reduction in computational operations, resulting in a 56% acceleration in edge processing frame rate while sacrificing only 0.91 dB in PSNR and 0.021 in SSIM. Further architectural simplification allowed ultra-high-speed video-rate on-chip image reconstruction exceeding 95 FPS, at the cost of just 1.3 dB PSNR and 0.018 SSIM. The experiments examined edge hardware acceleration for computational single-chip infrared camera reconstruction algorithms. This study provides technical references for engineering applications of lightweight infrared computational imaging systems.
|
|
Received: 11 February 2025
Published: 09 September 2025
|
|
|
|
|
|
| [1] |
CUI Shan, PAN Junyang, WANG Wei, GUO Ye, XU Jiangtao. Air Defence and Anti-Missile Interception Decision-Making Study Based on Deep Learning[J]. Air & Space Defense, 2024, 7(5): 54-64. |
| [2] |
LIU Jing, GUO Xiaolei, ZHANG Xinhai, MAO Jingjun, LYU Ruiheng. A Lightweight Aerial Rotated Object Detection Algorithm of Air-to-Surface Missile[J]. Air & Space Defense, 2024, 7(4): 106-113. |
| [3] |
LIN Zhaochen, ZHANG Xinran, LIU Ziyang, HE Fenghua, OUYANG Lei. Deep Learning-Based Hypersonic Vehicle Motion Behavior Recognition[J]. Air & Space Defense, 2024, 7(1): 48-55. |
| [4] |
WANG Bing, PI Gang, CHEN Wencheng, XIE Haifeng, SHI Xiangling. Deep Learning Based Surface Defect Detection Method of Flexible Solar Array Hinge[J]. Air & Space Defense, 2023, 6(1): 96-101. |
| [5] |
JIN Lijie, WU Yatao. Radar Signal Modulation Type Recognition Based on Double CNN[J]. Air & Space Defense, 2022, 5(1): 66-70. |
| [6] |
TAO Haihong, YAN Yingfei. A Netted Radar Node Selection Algorithm Based on GA-CNN[J]. Air & Space Defense, 2022, 5(1): 1-5. |
| [7] |
CAI Yunze, ZHANG Yanjun. Infrared Dim and Small Target Detection Based on Dual-Channel Feature-Enhancement Integrated Attention Network[J]. Air & Space Defense, 2021, 4(4): 14-22. |
| [8] |
CAO Jinghao, ZHANG Junju, HUANG Wei, YAO Ruotong, ZHANG Ping. UAV Recognition and Detection Based on Multi-scale Feature Fusion[J]. Air & Space Defense, 2021, 4(1): 60-64. |
| [9] |
CHEN Jichi, WEI Guohua, GUO Conglong, ZHANG Lihe. Preliminary Study on a Deep Learning 3D Reconstruction Simulation Method Based on Infrared Image Sequence[J]. Air & Space Defense, 2020, 3(4): 21-29. |
| [10] |
FAN Jinxiang, HOU Wentao. Development and Thinking of Precision Homing Terminal Guidance Technology for Air and Missile Defense[J]. Air & Space Defense, 2020, 3(3): 31-37. |
| [11] |
Zhou Lai, Jin Xiaowei, Zheng Yikai. Researchon Operational Decision Support Based on Deep Reinforcement Learning[J]. Air & Space Defense, 2018, 1(1): 31-35. |
|
|
|
|
2025, Vol. 8 
