A CNN-TRANSFORMER HYBRID FEATURE DESCRIPTOR FOR OPTICAL-SAR IMAGE REGISTRATION

被引：0

作者：

Lin, Mingxin ^{[1
]}

Liu, Binyuan ^{[1
]}

Liu, Yijun ^{[1
]}

Wang, Qingsong ^{[1
]}

机构：

[1] Sun Yat Sen Univ, Sch Elect & Commun Engn, Guangzhou, Peoples R China

来源：

IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM | 2023年

基金：

美国国家科学基金会;

关键词：

optical-SAR image registration; feature descriptor; CNN; Transformer;

D O I：

10.1109/IGARSS52108.2023.10281985

中图分类号：

P [天文学、地球科学];

学科分类号：

07 ;

摘要：

This paper presents a CNN-Transformer hybrid feature descriptor for the registration of optical and SAR images. The proposed feature descriptor is composed of a shallow feature extraction module based on CNN and a deep feature extraction module based on Transformer, which are tailored to extract features from different levels. Its effectiveness is demonstrated in experiments with comparison to state-of-the-art methods. Experimental results demonstrated its superior performance compare to the state-of-the-art methods, thus showcasing its efficacy and potential for practical applications. Index

引用

页码：6069 / 6072

页数：4

共 50 条

[31] Hybrid CNN-Transformer Features for Visual Place Recognition
Wang, Yuwei
Qiu, Yuanying
Cheng, Peitao
Zhang, Junyu
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 33 (03) : 1109 - 1122
[32] Semhybridnet: a semantically enhanced hybrid CNN-transformer network for radar pulse image segmentation
Hongjia Liu
Yubin Xiao
Xuan Wu
Yuanshu Li
Peng Zhao
Yanchun Liang
Liupu Wang
You Zhou
Complex & Intelligent Systems, 2024, 10 : 2851 - 2868
[33] FBDPN: CNN-Transformer hybrid feature boosting and differential pyramid network for underwater object detection
Ji, Xun
Chen, Shijie
Hao, Li-Ying
Zhou, Jingchun
Chen, Long
EXPERT SYSTEMS WITH APPLICATIONS, 2024, 256
[34] Semantic segmentation of terrace image regions based on lightweight CNN-Transformer hybrid networks
Liu X.
Yi S.
Li L.
Cheng X.
Wang C.
Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering, 2023, 39 (13): : 171 - 181
[35] 基于CNN-Transformer的SAR图像语义描述方法
于兴超
岳耀
陈庆
资源导刊, 2024, (16) : 37 - 40+44
[36] Cross Attention Multi Scale CNN-Transformer Hybrid Encoder Is General Medical Image Learner
Zhou, Rongzhou
Yao, Junfeng
Hong, Qingqi
Li, Xingxin
Cao, Xianpeng
PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2023, PT XIII, 2024, 14437 : 85 - 97
[37] Optical and SAR Image Registration Based on Feature Decoupling Network
Xiang, Deliang
Xie, Yuzhen
Cheng, Jianda
Xu, Yihao
Zhang, Han
Zheng, Yanpeng
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
[38] TransHSI: A Hybrid CNN-Transformer Method for Disjoint Sample-Based Hyperspectral Image Classification
Zhang, Ping
Yu, Haiyang
Li, Pengao
Wang, Ruili
REMOTE SENSING, 2023, 15 (22)
[39] Hybrid CNN-transformer based meta-learning approach for personalized image aesthetics assessment
Yan, Xingao
Shao, Feng
Chen, Hangwei
Jiang, Qiuping
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2024, 98
[40] A CNN-transformer hybrid network with selective fusion and dual attention for image super-resolution
Chun Zhang
Jin Wang
Yunhui Shi
Baocai Yin
Nam Ling
Multimedia Systems, 2025, 31 (2)

← 1 2 3 4 5 →