HOG-VGG: VGG Network with HOG Feature Fusion for High-Precision PolSAR Terrain Classification

作     者：Jiewen Li Zhicheng Zhao Yanlan Wu Jiaqiu Ai Jun Shi 

作者机构：School of Software， Hefei University of Technology School of Computer Science and Information Engineering， Hefei University of Technology School of Artificial Intelligence， Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province， Anhui University Intelligent Interconnected Systems Laboratory of Anhui Province (Hefei University of Technology) 

出 版 物：《Journal of Harbin Institute of Technology(New series)》 (哈尔滨工业大学学报(英文版))

年 卷 期：2024年

学科分类：080904[工学-电磁场与微波技术] 0810[工学-信息与通信工程] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 081105[工学-导航、制导与控制] 081001[工学-通信与信息系统] 081002[工学-信号与信息处理] 0825[工学-航空宇航科学与技术] 0811[工学-控制科学与工程] 

基　　金：Sponsored by the Fundamental Research Funds for the Central Universities of China(Grant No.PA2023IISL0098) the Hefei Municipal Natural Science Foundation(Grant No.202201) the National Natural Science Foundation of China(Grant No.62071164) the Open Fund of Information Materials and Intelligent Sensing Laboratory of Anhui Province (Anhui University)(Grant No.IMIS202214 and IMIS202102) 

摘      要：This article proposes a VGG network with histogram of oriented gradient (HOG) feature fusion (HOG-VGG) for polarization synthetic aperture radar (PolSAR) image terrain classification. VGG-Net has a strong ability of deep feature extraction， which can fully extract the global deep features of different terrains in PolSAR images， so it is widely used in PolSAR terrain classification. However， VGG-Net ignores the local edge & shape features， resulting in incomplete feature representation of the PolSAR terrains， as a consequence， the terrain classification accuracy is not promising. In fact， edge and shape features play an important role in PolSAR terrain classification. To solve this problem， a new VGG network with HOG feature fusion was specifically proposed for high-precision PolSAR terrain classification. HOG-VGG extracts both the global deep semantic features and the local edge & shape features of the PolSAR terrains， so the terrain feature representation completeness is greatly elevated. Moreover， HOG-VGG optimally fuses the global deep features and the local edge & shape features to achieve the best classification results. The superiority of HOG-VGG is verified on the Flevoland， San Francisco and Oberpfaffenhofen datasets. Experiments show that the proposed HOG-VGG achieves much better PolSAR terrain classification performance， with overall accuracies of 97.54%， 94.63%， and 96.07%， respectively.