Hardware Implementation of Convolutional Neural Network-Based Remote Sensing Image Classification Method

被引:1
作者
Chen, Lei [1 ,2 ]
Wei, Xin [1 ,2 ]
Liu, Wenchao [1 ,2 ]
Chen, He [1 ,2 ]
Chen, Liang [1 ,2 ]
机构
[1] Beijing Inst Technol, Sch Informat & Elect, Radar Res Lab, Beijing 100081, Peoples R China
[2] Beijing Inst Technol, Beijing Key Lab Embedded Real Time Informat Proc, Beijing 100081, Peoples R China
来源
COMMUNICATIONS, SIGNAL PROCESSING, AND SYSTEMS, CSPS 2018, VOL II: SIGNAL PROCESSING | 2020年 / 516卷
关键词
CNN; Remote sensing image; FPGA; Classification;
D O I
10.1007/978-981-13-6504-1_19
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
The convolutional neural networks have achieved very good results in the field of remote sensing image classification and recognition. However, the cost of huge computational complexity with the significant accuracy improvement of CNNs makes a huge challenge to hardware implementation. A promising solution is FPGA due to it supports parallel computing with low power consumption. In this paper, LeNet-5-based remote sensing image classification method is implemented on FPGA. The test images with a size of 126 x 126 are transformed to the system from PC by serial port. The classification accuracy is 98.18% tested on the designed system, which is the same as that on PC. In the term of efficiency, the designed system runs 2.29 ms per image, which satisfies the real-time requirements.
引用
收藏
页码:140 / 148
页数:9
相关论文
共 10 条
[1]  
[Anonymous], 2015, 2015 ACMSIGDA INT S, DOI DOI 10.1145/2684746.2689060
[2]   Caffe CNN-based classification of hyperspectral images on GPU [J].
Garea, Alberto S. ;
Heras, Dora B. ;
Arguello, Francisco .
JOURNAL OF SUPERCOMPUTING, 2019, 75 (03) :1065-1077
[3]   Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery [J].
Hu, Fan ;
Xia, Gui-Song ;
Hu, Jingwen ;
Zhang, Liangpei .
REMOTE SENSING, 2015, 7 (11) :14680-14707
[4]   Gradient-based learning applied to document recognition [J].
Lecun, Y ;
Bottou, L ;
Bengio, Y ;
Haffner, P .
PROCEEDINGS OF THE IEEE, 1998, 86 (11) :2278-2324
[5]   p-Laplacian Regularization for Scene Recognition [J].
Liu, Weifeng ;
Ma, Xuegi ;
Zhou, Yicong ;
Tao, Dapeng ;
Cheng, Jun .
IEEE TRANSACTIONS ON CYBERNETICS, 2019, 49 (08) :2927-2940
[6]   Going Deeper with Embedded FPGA Platform for Convolutional Neural Network [J].
Qiu, Jiantao ;
Wang, Jie ;
Yao, Song ;
Guo, Kaiyuan ;
Li, Boxun ;
Zhou, Erjin ;
Yu, Jincheng ;
Tang, Tianqi ;
Xu, Ningyi ;
Song, Sen ;
Wang, Yu ;
Yang, Huazhong .
PROCEEDINGS OF THE 2016 ACM/SIGDA INTERNATIONAL SYMPOSIUM ON FIELD-PROGRAMMABLE GATE ARRAYS (FPGA'16), 2016, :26-35
[7]   Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks [J].
Ren, Shaoqing ;
He, Kaiming ;
Girshick, Ross ;
Sun, Jian .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (06) :1137-1149
[8]   MatConvNet Convolutional Neural Networks for MATLAB [J].
Vedaldi, Andrea ;
Lenc, Karel .
MM'15: PROCEEDINGS OF THE 2015 ACM MULTIMEDIA CONFERENCE, 2015, :689-692
[9]   M-FCN: Effective Fully Convolutional Network-Based Airplane Detection Framework [J].
Yang, Yiding ;
Zhuang, Yin ;
Bi, Fukun ;
Shi, Hao ;
Xie, Yizhuang .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2017, 14 (08) :1293-1297
[10]   Energy-Efficient CNN Implementation on a Deeply Pipelined FPGA Cluster [J].
Zhang, Chen ;
Wu, Di ;
Sun, Jiayu ;
Sun, Guangyu ;
Luo, Guojie ;
Cong, Jason .
ISLPED '16: PROCEEDINGS OF THE 2016 INTERNATIONAL SYMPOSIUM ON LOW POWER ELECTRONICS AND DESIGN, 2016, :326-331