RaNeRF: Neural 3-D Reconstruction of Space Targets From ISAR Image Sequences

逆合成孔径雷达 人工智能 计算机科学 计算机视觉 合成孔径雷达 雷达成像 迭代重建 模式识别(心理学) 雷达 电信
作者
Afei Liu,Shuanghui Zhang,Chi Zhang,Shuaifeng Zhi,Xiang Li
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:61: 1-15 被引量:2
标识
DOI:10.1109/tgrs.2023.3298067
摘要

Compared to 2D inverse synthetic aperture radar (ISAR) images of a space target, its 3D model can provide adequate details and accurate measurement parameters. However, it is challenging to tackle the problem of feature extraction and correlation during 3D reconstruction of space targets purely based on radar image sequences, due to their lack of clear evidence in imaging similarity compared to optical images. To address this problem, this paper proposes radar neural radiance fields (i.e. RaNeRF), which is a novel 3D reconstruction method using only observed ISAR image sequences. Firstly, the 3D structure of a target is represented as a continuous 6D function of space positions and viewing directions using a fully-connected deep network. Secondly, the relationship between the 3D structure and 2D ISAR images of the target is constructed to enable differential rendering of ISAR images. Our overall pipeline can thus be trained using the discrepancy between the modulus of rendered and observed ISAR images in a purely self-supervised manner without 3D supervision. Finally, the 3D mesh model of the target can be retrieved from the learned density field via marching cube. As a result, the proposed RaNeRF can directly reconstruct the 3D structure of targets without explicit feature extraction and correlation of ISAR image sequences. Both quantitative and qualitative results verify the effectiveness of the proposed method. Compared to conventional baseline methods using point clouds, our reconstructed structure is more complete and accurate. In addition, the optimized model can synthesize ISAR images at novel observation direction, which can be used for downstream tasks including data augmentation and target recognition.
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
PDF的下载单位、IP信息已删除 (2025-6-4)

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
jeremiah发布了新的文献求助10
1秒前
AnYijing完成签到,获得积分10
1秒前
1秒前
1秒前
喵喵发布了新的文献求助10
1秒前
Cici发布了新的文献求助10
1秒前
kuaikuai完成签到,获得积分20
2秒前
哈哈哈哈哈哈完成签到,获得积分10
2秒前
柠檬完成签到 ,获得积分10
2秒前
3秒前
wang完成签到,获得积分10
3秒前
Sun完成签到,获得积分10
3秒前
科研通AI2S应助苗条的摇伽采纳,获得10
3秒前
zhangzhen完成签到,获得积分10
3秒前
花花完成签到 ,获得积分10
3秒前
lily发布了新的文献求助10
4秒前
QIN完成签到,获得积分10
4秒前
张志远发布了新的文献求助10
5秒前
明亮的绫完成签到 ,获得积分10
5秒前
plasmid发布了新的文献求助10
6秒前
1351567822应助何hao采纳,获得80
6秒前
7秒前
7秒前
kuaikuai发布了新的文献求助10
7秒前
Orange应助Jean0603采纳,获得10
7秒前
7秒前
三岁居居发布了新的文献求助10
8秒前
白日梦发布了新的文献求助10
8秒前
aaaaa完成签到,获得积分10
8秒前
霸气的寒蕾给霸气的寒蕾的求助进行了留言
9秒前
隐形曼青应助西早12采纳,获得10
10秒前
香蕉冬云完成签到 ,获得积分10
10秒前
自然的青筠完成签到,获得积分10
10秒前
赘婿应助平淡小土豆采纳,获得10
10秒前
10秒前
hackfeng完成签到,获得积分10
10秒前
Ao发布了新的文献求助10
11秒前
11秒前
见祥雨完成签到,获得积分10
12秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 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 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3970632
求助须知:如何正确求助?哪些是违规求助? 3515261
关于积分的说明 11177794
捐赠科研通 3250448
什么是DOI,文献DOI怎么找? 1795314
邀请新用户注册赠送积分活动 875781
科研通“疑难数据库(出版商)”最低求助积分说明 805073