Gaofan Ji

Mr. Gaofan Ji

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 December 2024 in Electronics
Verified
Journal Article
Open access
PDF file
Gaofan JiGaofan Ji
Gaofan Ji
LFLi Fan
Li Fan
LCLi Chuanxiang
Li Chuanxiang
Detecting maritime ship targets in complex aerial images is significantly challenging due to the relatively small size of the ship compared to the image’s predominant background. Current methodologies used to identify maritime targets in aerial imagery are susceptible to disruption from intricate backgrounds, leading to misidentification, overlooked detection, and inaccurate target localization. To address these challenges, we proposed the maritime background suppression network (MBSDet), which facilitates the reliable detection of multi-scale targets in intricate backgrounds. Firstly, we developed a background suppression (BS) module that integrates the Transformer’s context-aware capabilities with local attention features to enhance the model’s ability to identify multi-scale objects. Secondly, we present the multidimensional feature enrichment (MFE) module, which employs feature pyramid-based rearrangement modules and dynamic upsampling operators instead of conventional upsampling methods to enhance feature richness while attenuating background features. The mean average precision (mAP) values can reach 90.54% and 88.89% on HRSC2016 and DOTA v1.0 datasets, respectively. The experimental results indicate that MBSDet exhibits outstanding detection and localization accuracy for objects in difficult background situations.

4 May 2024 in Electronics
Verified
Journal Article
Open access
PDF file
Gaofan JiGaofan Ji
Gaofan Ji
YHYunhan He
Yunhan He
LCLi Chuanxiang
Li Chuanxiang
LFLi Fan
Li Fan
HWHaibo Wang
Haibo Wang
YZYantong Zhu
Yantong Zhu
In coal-fired power plants, coal piles serve as the fundamental management units. Acquiring point clouds of coal piles facilitates the convenient measurement of daily coal consumption and combustion efficiency. When using servo motors to drive Light Detection and Ranging (LiDAR) scanning of large-scale coal piles, the motors are subject to rotational errors due to gravitational effects. As a result, the acquired point clouds often contain significant noise. To address this issue, we proposes a Rapid Point Cloud Stitching–Constrained Particle Filter (RPCS-CPF) method. By introducing random noise to simulate servo motor rotational errors, both local and global point clouds are sequentially subjected to RPCS-CPF operations, resulting in smooth and continuous coal pile point clouds. Moreover, this paper presents a coal pile boundary detection method based on gradient region growing clustering. Experimental results demonstrate that our proposed RPCS-CPF method can generate smooth and continuous coal pile point clouds, even in the presence of servo motor rotational errors.

1 January 2026 in Electronics Letters
Verified
Journal Article
Open access
Gaofan JiGaofan Ji
Gaofan Ji
JYJian Yang
Jian Yang
XDXueyan Dong
Xueyan Dong
LYLing Yan
Ling Yan
CLChuanxiang Li
Chuanxiang Li
Deep learning‐based synthetic aperture radar (SAR) ship image processing is valuable for civilian and military applications, yet training deep models requires abundant high‐resolution SAR ship images. Due to the high cost of SAR sensors and limited data availability, constructing large‐scale, high‐quality datasets remains challenging. SAR image generation offers a promising solution. However, most existing generation methods focus on natural images, with few targeting SAR ship targets. This paper proposes a high‐resolution SAR ship image generation method using an improved denoising diffusion generative adversarial network. To enhance detail generation, a context‐aware upsampling filter is designed to incorporate SAR‐specific information, enabling the backbone network to capture more effective features during upsampling. Experiments show that our method achieves a Fréchet inception distance of 55.21 and a structural similarity index of 0.7245, producing high‐quality SAR‐consistent images with rich details.

9 February 2026
Verified
Preprint
Open access
Gaofan JiGaofan Ji
Gaofan Ji
JYJian Yang
Jian Yang
XDXueyan Dong
Xueyan Dong
LYLing Yan
Ling Yan
CLChuanxiang Li
Chuanxiang Li
Deep learning-based synthetic aperture radar (SAR) ship image processing is valuable for civilian and military applications, yet training deep models requires abundant high-resolution SAR ship images. Due to the high cost of SAR sensors and limited data availability, constructing large-scale, high-quality datasets remains challenging. SAR image generation offers a promising solution. However, most existing generation methods focus on natural images, with few targeting SAR ship targets. This paper proposes a high-resolution SAR ship image generation method using an improved Denoising Diffusion Generative Adversarial Network (DDGAN). To enhance detail generation, a Context-Aware Upsampling Filter (CAUF) is designed to incorporate SAR-specific information, enabling the backbone network to capture more effective features during upsampling. Experiments show that our method achieves a Fréchet Inception Distance (FID) of 55.21 and a Structural Similarity Index (SSIM) of 0.7245, producing high-quality SAR-consistent images with rich details.