Space Target Attitude Estimation From ISAR Image Sequences With Key Point Extraction Network

Xie, Pengfei; Zhang, Lei; Du, Chuan; Wang, Xiaoqing; Zhong, Wei

doi:10.1109/lsp.2021.3075606

Cited by 20 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given that the region containing strong scattering points in a radar image plays a pivotal role in automatic target recognition, we incorporate the distribution characteristics of these strong scattering points as prior information into the C2FIPNet loss function. This approach involves defining an extraction function for the scattering point distribution feature map [36], which comprises four steps: firstly, the strongest scattering point of an ISAR image can be obtained after traversing the entire image; afterward, based on the 3dB bandwidth criterion, the crossregion within the 3dB bandwidth range of the scattering point is set as zero; then, repeat the steps above several times to obtain images that remove several strong scattering points and their 3dB bandwidth; finally, the difference between the images without strong scattering points and the input ISAR images can be calculated. The strong scattering points distribution feature map of the input ISAR images are now extracted, which can be applied to define the local L1 loss function:…”

Section: Loss Functionmentioning

confidence: 99%

From Coarse to Fine: ISAR Object View Interpolation via Flow Estimation and GAN

Zhang,

Liu,

Jiang

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Section: Loss Functionmentioning

confidence: 99%

From Coarse to Fine: ISAR Object View Interpolation via Flow Estimation and GAN

Zhang,

Liu,

Jiang

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Apart from SC-U-net, the KPEN model developed in [12] is also selected for comparison. According to the projection relationship in Section 2.1, the ground truths of long edge and short edge directions can be obtained as a prior.…”

Section: Comparison Studymentioning

confidence: 99%

“…Recently, key point extraction network (KPEN) is developed and a novel method for attitude determination via extracted key points is proposed thereafter [12] . Focused on the size and attitude information of satellite key component, pix2pix generative adversarial network is developed in [13] for ISAR image segmentation.…”

Section: Introductionmentioning

confidence: 99%

Joint estimation of space target attitude and size based on polarimetric ISAR images and modified U-net model

Cui,

Fu,

Chen

2023

Eighth Asia Pacific Conference on Optics Manufacture and Third International Forum of Young Scientists on Advanced Optical Manu

View full text Add to dashboard Cite

“…Space targets fly in outer space and are only affected by gravity and drag force [1]. With the development of space technology, it is thus very important to carry out the measuring, tracking, and recognition of space targets [2][3][4].…”

Section: Introduction 1background and Motivationmentioning

confidence: 99%

Space Targets with Micro-Motion Classification Using Complex-Valued GAN and Kinematically Sifted Methods

Han,

Feng,

2023

Remote Sensing

View full text Add to dashboard Cite

Space target classification based on micro-motion characteristics has become a subject of great interest in the field of radar, particularly when using deep learning techniques. However, in practical applications, the ability of deep learning is hampered by the available radar datasets. As a result, obtaining a sufficient amount of the training dataset is a daunting challenge. To address this issue, this paper presents a novel framework for space target classification, consisting of three distinct modules: dataset generation, the kinematically sifted module, and classification. Initially, the micro-motion model of cone-shaped space targets is constructed to analyze target characteristics. Subsequently, the dataset generation module employs a complex-valued generative adversarial network (CV-GAN) to generate a large number of time-range maps. These maps serve as the foundation for training the subsequent modules. Next, the kinematically sifted module is introduced to eliminate images that do not align with the micro-motion characteristics of space targets. By filtering out incompatible images, the module ensures that only relevant and accurate dataset is utilized for further analysis. Finally, the classification model is constructed using complex-valued parallel blocks (CV-PB) to extract valuable information from the target. Experimental results validate the effectiveness of the proposed framework in space micro-motion target classification. The main contribution of the framework is to generate a sufficient amount of high-quality training data that conforms to motion characteristics, and to achieve accurate classification of space targets based on their micro-motion signatures. This breakthrough has significant implications for various applications in space target classification.

show abstract

Space Target Attitude Estimation From ISAR Image Sequences With Key Point Extraction Network

Cited by 20 publications

References 21 publications

From Coarse to Fine: ISAR Object View Interpolation via Flow Estimation and GAN

From Coarse to Fine: ISAR Object View Interpolation via Flow Estimation and GAN

Joint estimation of space target attitude and size based on polarimetric ISAR images and modified U-net model

Space Targets with Micro-Motion Classification Using Complex-Valued GAN and Kinematically Sifted Methods

Contact Info

Product

Resources

About