SSShuo Shi

Shuo Shi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Shuo Shi has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A Novel Large-Swath Fast Ship Detection Framework With Adaptive Anchor Boxes

    by Shuo Shi, Chaoyue Liu, Heng Zhang, Yunkai Deng

    Synthetic aperture radar (SAR), capable of ultra-wide swath imaging, serves as a vital tool for ocean surveillance. Ship detection in SAR imagery holds significant importance for maritime security and traffic management. Current ship detection algorithms exhibit excessive computational complexity, and both conventional and deep learning-based approaches struggle to achieve rapid detection in ultra-wide swath SAR imagery acquired by next-generation SAR systems. This paper proposes a rapid adaptive anchor framework for ship detection. First, the detection criterion statistics are decomposed into multiple prefix sum matrices, ensuring minimal computational complexity for anchor boxes of arbitrary sizes. Second, the image is quadrant-divided, with detection criterion statistics computed separately to determine ship presence in each quadrant. Third, quadrants containing ships undergo iterative quadrant division, while ship-free quadrants are annotated using differential matrices. Finally, the initial anchor boxes are systematically shifted to repeat the second and third steps across the entire image, ultimately generating a sea clutter mask. The computational complexity of the proposed ship detection framework remains equivalent to that of loading the full SAR image, introducing negligible additional overhead to existing systems. The framework is validated using empirical SAR datasets, demonstrating enhanced computational efficiency without compromising detection accuracy.


  • Iteration Phase Gradient Resample Autofocus: A Real-Time and Robust Algorithm for Focusing Maneuvering Ships in SAR Images

    by Shuo Shi, Heng Zhang, Chenrui Zuo, Zhanyang Ai, Jiang Du, Yunkai Deng

    Synthetic aperture radar (SAR) is a crucial tool for maritime monitoring. Maneuvering ships often appear defocused in SAR images. Ship refocusing typically employs inverse synthetic aperture radar (ISAR) methods, which are divided into translational compensation and rotational compensation. Currently, rotational compensation lacks robust, efficient, and non-parametric methods akin to phase gradient autofocus (PGA) for translational compensation. This paper proposes an iterative phase gradient resampling autofocus (IPGRA) method, extending the widely used PGA algorithm to compensate for space-variant phase errors caused by non-uniform rotation. The proposed algorithm consists of the following steps: First, extract the defocused ship and perform azimuth decompression and translational motion compensation. Second, divide the echo signal into two parts according to the range cell, use range envelope alignment and PGA to extract the phase error for each part. Third, resample the echo signal based on the phase error. Fourth, introduce a coefficient to describe the degree of rotational defocusing, and repeat the second and third steps until this coefficient converges. Fifth, the Keystone transform is applied to correct the migration through range cells. The proposed algorithm requires only range compression parameters, can achieve undistorted non-sparse imaging, and can quantify imaging quality through the defocusing coefficient. The algorithm inherits the noise resistance and robustness of PGA. Simulation and measured data verify the effectiveness of the proposed algorithm. Finally, this paper introduces an onboard real-time precise focusing processing system incorporating the proposed algorithm.


  • Azimuth Envelope Alignment for Focusing Maneuvering Ships in SAR Images

    by Shuo Shi, Heng Zhang, Yunkai Deng, Sisi Dong

    Synthetic aperture radar (SAR) is a crucial technology in marine surveillance. Moving ships are always defocused in SAR images, which affects the following identification process. Inverse synthetic aperture radar (ISAR) technology has been employed to focus moving targets in SAR images, typically involving two steps: translation motion compensation and rotation motion compensation. Range envelope alignment is generally considered a well-established method for translation motion compensation. However, in rotation motion compensation, current approaches rely on signal parameter estimation and optimization algorithms, which lack robust methods. This paper presents a rotational motion compensation framework, named "azimuth envelope alignment", which extends the range envelope alignment to the azimuth direction. First, a novel concept of "azimuth envelope" is introduced, and the process of azimuth envelope alignment is discussed. Then, a specific method is presented: the use of the iterative adaptive approach (IAA) and resampling for implementation "azimuth envelope alignment". This method first estimates the alignment parameter using IAA, followed by achieving alignment through resampling. This method exploits the high-precision estimation capability of the IAA while avoiding its sparse estimation results, enabling the robust, nonsparse refocusing of moving targets. Finally, simulations and experimental data validate the effectiveness of the proposed algorithm. The azimuth envelope alignment framework introduced in this paper can serve as a general approach for moving target imaging, similar to range envelope alignment.


  • Expanding Defocused Ship Data Using Existing SAR Ship Datasets by Inverse Refocusing Algorithm

    by Shuo Shi, Chaoyue Liu, Heng Zhang, Yunkai Deng

    Synthetic aperture radar (SAR) is a crucial tool for maritime observation, with ships being the main targets at sea. Detecting these ships is foundational for other downstream tasks, making the study of ship detection algorithms highly significant. Currently, ship detection primarily relies on deep learning algorithms, and training neural networks requires a large amount of data. In various maritime observation tasks, identifying defocused ships is particularly important. However, current databases lack defocused ship data, and SAR ship image generation algorithms are not yet mature. Therefore, this letter proposes generating defocused ship data using existing ship data. First, we introduce the signal model of defocused ships and the causes of defocusing. Next, we describe the generation of defocused ships with non-uniform rotation by introducing motion errors through resampling. We also explain the generation of defocused ships with translational motion using initial phase compensation and envelope shift. Finally, expansion experiments using spaceborne SAR data demonstrate the effectiveness of our method.

  • Increase the Coherent Processing Interval for SAR Focusing of Maneuvering Ships by Data Resampling

    by Shuo Shi, Heng Zhang, Yunkai Deng, Mingshan Ren

    Synthetic aperture radar (SAR) is important for marine surveillance. The image resolution of SAR is obtained via coherent integration. However, with increasing coherent processing intervals (CPIs), the focusing quality of maneuvering ships in images will worsen, impacting target recognition. Defocusing is caused mainly by the change in the image projection plane (IPP) of the maneuvering ship and the change in the effective rotation vector (ERV). In this article, an improved inverse SAR (ISAR) method is used to focus the ships in SAR images. First, the factors influencing the instantaneous imaging position are analyzed. Then, a new method based on data resampling for maneuvering ship imaging with a long CPI is proposed. This method consists of two main steps: ERV estimation and data resampling. The change in the ERV is estimated by using the instantaneous imaging position of all the scatterers, and the ship echo is resampled according to the estimation of the time-varying ERV. After resampling, we can obtain the echo from a constant rotating ship and can ensure a well-focused ship by using the traditional range-Doppler algorithm. This new method overcomes the restriction of ERV variation. Thus, a longer CPI can be used for imaging, while the IPP remains stable. Finally, simulation and measured data are used to verify the effectiveness of the proposed algorithm.


  • Open Access

    Application of 5G Communication Technology in Power Communication and Research on Key Technologies

    by Guohui Chen, Hongliang Wei, Yizhu Zhang, Chao Guo, Shuo Shi, Zhipeng Wang, Tianji Yan, Siqian Ma

    With the rapid development of power system and the deepening construction of smart grid, 5G communication technology is favored by all walks of life because of its ultra-low delay, ultra-high reliability, deep coverage, extreme capacity and ultra-low power consumption. It has become the key technology to lead scientific and technological innovation and promote the sustainable development of power system, providing a solid guarantee for the realization of human-computer interaction and Internet of Everything. This paper first introduces the network structure, basic principle and core features of 5G communication, and expounds the core slice of 5G communication and its three application scenarios; secondly, the potential demand scenarios of 5G communication in power system are analyzed in depth, that is, high capacity, high bandwidth and low delay business scenarios; finally, the key technologies of 5G communication, such as large-scale MIMO communication technology, ultra-dense heterogeneous network technology, green communication technology and millimeter wave communication technology, are discussed, and the linkage between current communication requirements and communication technologies is studied, which provides theoretical support for the application of 5G communication in power system.