S-CycleGAN: A Novel Target Signature Segmentation Method for GPR Image Interpretation

图像分割 人工智能 计算机科学 分割 探地雷达 口译(哲学) 模式识别(心理学) 签名(拓扑) 计算机视觉 图像(数学) 数学 雷达 电信 几何学 程序设计语言
作者
Feifei Hou,Boxuan Qiao,Jian Dong,Z.Y. Ma
出处
期刊:IEEE Geoscience and Remote Sensing Letters [Institute of Electrical and Electronics Engineers]
卷期号:: 1-1
标识
DOI:10.1109/lgrs.2024.3365470
摘要

Subsurface object detection and segmentation, which has been widely conducted in the ground-penetrating radar (GPR) image field, is of real significance but technically challenging. Although deep learning-based methods have been implemented to segment GPR target signatures, they still rely on complex network architectures such as region proposal networks, which are tedious and time-consuming and not suitable for on-site engineering. To address this challenge, we propose a novel supervised learning-driven model for GPR targe signature segmentation based on cycle-consistence generative adversarial networks (CycleGAN), called S-CycleGAN. Significantly distinguished from the original unsupervised CycleGAN, S-CycleGAN can achieve supervised learning while preserving the attributes and loss function of the previous model. Furthermore, the proposed model can learn a function that maps the GPR B-scan data to the segmented hyperbolic targets. Moreover, a new loss combination strategy including the perceptual loss is developed to improve the segmentation performance. This strategy can highlight and segment GPR target by comparing the perceptual features of a segmented output against those of the labelled images in same established feature space. Therefore, the proposed method transfers our visual perception knowledge to the target instance segmentation task and is able to preserve key information. Experiment results indicate a 97.88% F1-score and a 97.15% MIoU, and the modified loss function accelerates convergence speed and reduces computational costs.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
SciGPT应助sda采纳,获得30
1秒前
略略发布了新的文献求助10
1秒前
2秒前
3秒前
4秒前
曹欣雨完成签到,获得积分10
5秒前
JAY23发布了新的文献求助20
6秒前
华仔应助GCMTG采纳,获得10
7秒前
MrCat完成签到,获得积分10
7秒前
陈里里发布了新的文献求助10
8秒前
CXY完成签到,获得积分10
8秒前
9秒前
做优质男人完成签到,获得积分20
9秒前
汉堡包应助七七采纳,获得10
9秒前
诚c发布了新的文献求助10
10秒前
失眠的汽车关注了科研通微信公众号
11秒前
11秒前
mfy完成签到,获得积分10
11秒前
12秒前
852应助haihe采纳,获得10
12秒前
13秒前
思源应助蒲公英采纳,获得10
13秒前
崛起之邦完成签到,获得积分10
14秒前
富人雄完成签到,获得积分10
14秒前
乔佳佳发布了新的文献求助10
15秒前
文静丹秋发布了新的文献求助10
16秒前
超帅蛋挞完成签到,获得积分10
16秒前
16秒前
希望天下0贩的0应助laola采纳,获得10
18秒前
18秒前
BinL完成签到,获得积分10
18秒前
ShenQ发布了新的文献求助10
18秒前
Wone3发布了新的文献求助10
18秒前
19秒前
所所应助只是朋友还是采纳,获得10
20秒前
21秒前
21秒前
naomic发布了新的文献求助10
22秒前
qqqqq发布了新的文献求助20
23秒前
高分求助中
The three stars each : the Astrolabes and related texts 1070
Manual of Clinical Microbiology, 4 Volume Set (ASM Books) 13th Edition 1000
Sport in der Antike 800
Aspect and Predication: The Semantics of Argument Structure 666
De arte gymnastica. The art of gymnastics 600
少脉山油柑叶的化学成分研究 530
Berns Ziesemer - Maos deutscher Topagent: Wie China die Bundesrepublik eroberte 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 有机化学 工程类 生物化学 纳米技术 物理 内科学 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 电极 光电子学 量子力学
热门帖子
关注 科研通微信公众号,转发送积分 2410385
求助须知:如何正确求助?哪些是违规求助? 2105858
关于积分的说明 5320189
捐赠科研通 1833350
什么是DOI,文献DOI怎么找? 913570
版权声明 560825
科研通“疑难数据库(出版商)”最低求助积分说明 488512