An Efficient FPGA-Based Implementation for Quantized Remote Sensing Image Scene Classification Network

被引:13
|
作者
Zhang, Xiaoli [1 ]
Wei, Xin [1 ]
Sang, Qianbo [1 ]
Chen, He [1 ]
Xie, Yizhuang [1 ]
机构
[1] Beijing Inst Technol, Beijing Key Lab Embedded Real Time Informat Proc, Beijing 100081, Peoples R China
关键词
remote sensing image; scene classification; accelerator; DCNN; FPGA; quantization;
D O I
10.3390/electronics9091344
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Deep Convolutional Neural Network (DCNN)-based image scene classification models play an important role in a wide variety of remote sensing applications and achieve great success. However, the large-scale remote sensing images and the intensive computations make the deployment of these DCNN-based models on low-power processing systems (e.g., spaceborne or airborne) a challenging problem. To solve this problem, this paper proposes a high-performance Field-Programmable Gate Array (FPGA)-based DCNN accelerator by combining an efficient network compression scheme and reasonable hardware architecture. Firstly, this paper applies the network quantization to a high-accuracy remote sensing scene classification network, an improved oriented response network (IORN). The volume of the parameters and feature maps in the network is greatly reduced. Secondly, an efficient hardware architecture for network implementation is proposed. The architecture employs dual-channel Double Data Rate Synchronous Dynamic Random-Access Memory (DDR) access mode, rational on-chip data processing scheme and efficient processing engine design. Finally, we implement the quantized IORN (Q-IORN) with the proposed architecture on a Xilinx VC709 development board. The experimental results show that the proposed accelerator has 88.31% top-1 classification accuracy and achieves a throughput of 209.60 Giga-Operations Per Second (GOP/s) with a 6.32 W on-chip power consumption at 200 MHz. The comparison results with off-the-shelf devices and recent state-of-the-art implementations illustrate that the proposed accelerator has obvious advantages in terms of energy efficiency.
引用
收藏
页码:1 / 20
页数:20
相关论文
共 50 条
  • [1] FPGA-Based Hybrid-Type Implementation of Quantized Neural Networks for Remote Sensing Applications
    Wei, Xin
    Liu, Wenchao
    Chen, Lei
    Ma, Long
    Chen, He
    Zhuang, Yin
    [J]. SENSORS, 2019, 19 (04)
  • [2] An Efficient and Lightweight Convolutional Neural Network for Remote Sensing Image Scene Classification
    Yu, Donghang
    Xu, Qing
    Guo, Haitao
    Zhao, Chuan
    Lin, Yuzhun
    Li, Daoji
    [J]. SENSORS, 2020, 20 (07)
  • [3] EMSCNet: Efficient Multisample Contrastive Network for Remote Sensing Image Scene Classification
    Zhao, Yibo
    Liu, Jianjun
    Yang, Jinlong
    Wu, Zebin
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
  • [4] Scene Classification of Remote Sensing Image Based on Deep Convolutional Neural Network
    Yang, Zhou
    Mu, Xiao-dong
    Zhao, Feng-an
    [J]. TENTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2018), 2018, 10806
  • [5] Scene classification of remote sensing image based on deep network grading transferring
    Yang, Zhou
    Mu, Xiao-dong
    Zhao, Feng-an
    [J]. OPTIK, 2018, 168 : 127 - 133
  • [6] A Lightweight and Multiscale Network for Remote Sensing Image Scene Classification
    Bai, Lin
    Liu, Qingxin
    Li, Cuiling
    Zhu, Chunlin
    Ye, Zhen
    Xi, Meng
    [J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [7] Efficient recurrent attention network for remote sensing scene classification
    Liang, Le
    Wang, Guoli
    [J]. IET IMAGE PROCESSING, 2021, 15 (08) : 1712 - 1721
  • [8] ATTENTION BASED NETWORK FOR REMOTE SENSING SCENE CLASSIFICATION
    Liu, Shaoteng
    Wang, Qi
    Li, Xuelong
    [J]. IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2018, : 4740 - 4743
  • [9] Remote sensing image scene classification based on multilayer feature context encoding network
    Li Ruo-Yao
    Zhang Bo
    Wang Bin
    [J]. JOURNAL OF INFRARED AND MILLIMETER WAVES, 2021, 40 (04) : 530 - 538
  • [10] Channel-Attention-Based DenseNet Network for Remote Sensing Image Scene Classification
    Tong, Wei
    Chen, Weitao
    Han, Wei
    Li, Xianju
    Wang, Lizhe
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2020, 13 : 4121 - 4132