Prof. Xin Chen Profile

Prof. Xin Chen

SPIE Involvement:

Author

Publications (4)

Proceedings Article | 4 December 2024 Paper

Efficient multispectral infrared dim target detection framework based on slice registration

Fenghong Li, Peng Rao, Xin Chen, Wen Sun

Proceedings Volume 13283, 1328328 (2024) https://doi.org/10.1117/12.3036696

KEYWORDS: Target detection, Infrared radiation, Infrared detectors, Detection and tracking algorithms, Infrared imaging, Feature extraction, Image fusion, Image enhancement, Feature fusion, Small targets

Read Abstract +

In recent years, infrared dim-target detection has emerged as a pivotal area of research. However, most existing detection methodologies focus on single-spectral imagery. Owing to the optical diffraction limit, the image resolution obtained from different detection bands under the same conditions varies significantly. Single-spectral infrared imagery offers limited target and background features, failing to capture a comprehensive representation of the environment and thus struggling with target detection in complex backgrounds. Although multispectral image fusion can enhance the detection capability for dim infrared targets, processing across all spectral regions leads to increased computational complexity, resulting in time-consuming and redundant detection algorithms. In response to this challenge, we propose an efficient multispectral infrared dim target detection framework based on slice registration. The framework consists of a reference spectral rapid localization module (RSLM) and a multispectral feature enhancement detection network (MFE-Net). The latter includes a feature extraction module, a multispectral information-weighted fusion module (MIWF), and a detection module. Initially, potential target locations in the image are rapidly identified through the reference spectral rapid localization module, and corresponding image slices are extracted from other spectral bands based on spectral coordinate transformation. Subsequently, the multispectral feature enhancement network's feature extraction module processes these multispectral target slices to extract features from each band. Finally, the MIWF module integrates information from different spectral bands to enhance the network's sensitivity to infrared dim targets, allowing the multispectral feature enhancement detection network to conduct precise detection, reduce false alarms, and improve detection rates. The proposed method utilizes the reference spectral rapid localization module to reduce the complexity of multispectral data fusion, while the multispectral feature enhancement detection network leverages information from different bands to enrich target features, thereby enhancing the accuracy of weak infrared target detection. Experiments conducted on a comprehensive dataset demonstrate that this method outperforms other state-of-the-art methods in terms of detection probability (Pd) and false alarm rate (Fa).

SPIE Journal Paper | 19 March 2023

Blind turbulent image deblurring through dual patch-wise pixels prior

Shuyuan Zhang, Peng Rao, Xin Chen

OE, Vol. 62, Issue 03, 033104, (March 2023) https://doi.org/10.1117/12.10.1117/1.OE.62.3.033104

KEYWORDS: Deblurring, Image processing, Image restoration, Optical engineering, Image quality, Turbulence, Image sharpness, Visualization, Tunable filters, Atmospheric turbulence

Read Abstract +

Proceedings Article | 31 January 2023 Paper

Visualization of radiation intensity sequences for space infrared target recognition

Shenghao Zhang, Xin Chen, Peng Rao, Hao Zhang

Proceedings Volume 12505, 125051W (2023) https://doi.org/10.1117/12.2665173

KEYWORDS: Visualization, Infrared radiation, Target recognition, Signal to noise ratio, Signal processing, Target detection, Data modeling, Interference (communication)

Read Abstract +

Proceedings Article | 15 November 2022 Paper

Study on periodic law of micromotion feature for space infrared moving target recognition

Hao Zhang, Rao Peng, Xin Chen, Hui Xia, ShengHao Zhang

Proceedings Volume 12448, 124480C (2022) https://doi.org/10.1117/12.2630897

KEYWORDS: Infrared radiation, Target detection, Target recognition, Infrared imaging

Read Abstract +

Using the observation data of various detectors to identify reentry vehicles, heavy and light decoys, and separate debris is a key task in space situational awareness. During the flight, the space targets are always in a rotating or rolling state (called micromotion). micromotion can reflect the physical attribute information such as mass distribution and shape of different targets, which provides important essential characteristics for identifying space targets. Infrared sensor has the advantages of working all day, long detection distance, and small load. The image data obtained by it can be used to estimate the temperature, radiation, and other information, but the research on estimating the target micromotion characteristics from the multi-infrared images is rarely mentioned. Therefore, aiming to solve the problem of micromotion period estimation of space infrared moving targets under long-distance observation, firstly, considering the factors such as flight scene, target shape and micromotion, the infrared radiation and imaging models of space moving targets under micromotion state are established according to the micromotion dynamics, temperature and imaging relationship; Secondly, the period of infrared radiation extracted from multi-frame images is estimated. Through theoretical analysis, it is pointed that the assumption that there must be a similarity between the sample sets sampled by period length is the main reason for the doubling misjudgment of the average amplitude difference (AMDF) function, and there is also a false valley misjudgment problem in AMDF. The cyclic average amplitude difference function (CAMDF) is used to estimate the micromotion period of multi-shape objects, which can not only effectively decrease the double misjudgment of the period but also solve the misjudgment of false valley estimation points. Finally, a semi-physical simulation platform for space infrared dim moving target detection and recognition is designed and built, and the experimental data is used to verify the effectiveness of CAMDF in estimating the micromotion period. The results show that when the signal-to-noise ratio(SNR) of the simulated infrared radiation is greater than 15, the average accuracy of CAMDF is greater than 90%; Experimental data of five shape objects is used to verify the algorithm, and the average relative error is about 6%. It shows that the algorithm can better estimate the micromotion period of space targets.

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years