Xiaoxuan Zhou

Dr. Xiaoxuan Zhou

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
31 January 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
楠方楠 方
楠 方
LLLiyuan Li
Liyuan Li
XZXiaoxuan Zhou
Xiaoxuan Zhou
WZWencong Zhang
Wencong Zhang
Fansheng ChenFansheng Chen
Fansheng Chen
Small-object detection in satellite remote sensing images plays a pivotal role in the field of remote sensing. Achieving high-performance real-time detection demands not only efficient algorithms but also low-power, high-performance hardware platforms. However, most mainstream target detection methods currently rely on graphics processing units (GPUs) for acceleration, and the high power consumption of GPUs limits their use in resource-constrained platforms such as small satellites. Moreover, small-object detection faces multiple challenges: the targets occupy only a small number of pixels in the image, the background is often complex with significant noise interference, and existing detection models typically exhibit low accuracy when dealing with small targets. In addition, the large number of parameters in these models makes direct deployment on embedded devices difficult. To address these issues, we propose a hybrid overlapping acceleration architecture based on FPGA, along with a lightweight model derived from YOLOv5s that is specifically designed to enhance the detection of small objects in remote sensing images. This model incorporates a lightweight GhostBottleneckV2 module, significantly reducing both model parameters and computational complexity. Experimental results on the TIFAD thermal infrared small-object dataset show that our approach achieves an average precision (mAP) of 67.8% while consuming an average power of only 2.8 W. The robustness of the proposed model is verified by the HRSID dataset. Combining real-time performance with high energy efficiency, this architecture is particularly well suited for on-board remote sensing image processing systems, where reliable and efficient small-object detection is paramount.

6 April 2022 in Optical and Quantum Electronics
Verified
Journal Article
Closed access
PDF file
XZXiaoxuan Zhou
Xiaoxuan Zhou
XNXinyue Ni
Xinyue Ni
JZJingwen Zhang
Jingwen Zhang
DWDongshan Weng
Dongshan Weng
ZHZhuoyue Hu
Zhuoyue Hu
Fansheng ChenFansheng Chen
Fansheng Chen

5 December 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
LQLintong Qi
Lintong Qi
XHxinZhuoyue Hu
xinZhuoyue Hu
XZXiaoxuan Zhou
Xiaoxuan Zhou
XNXinyue Ni
Xinyue Ni
Fansheng ChenFansheng Chen
Fansheng Chen
Thermal infrared imagery plays an important role in a variety of fields, such as surface temperature inversion and urban heat island effect analysis, but the spatial resolution has severely restricted the potential for further applications. Data fusion is defined as data combination using multiple sensors, and fused information often has better results than when the sensors are used alone. Since multi-resolution analysis is considered an effective method of image fusion, we propose an MTF-GLP-TAM model to combine thermal infrared (30 m) and multispectral (10 m) information of SDGSAT-1. Firstly, the most relevant multispectral bands to the thermal infrared bands are found. Secondly, to obtain better performance, the high-resolution multispectral bands are histogram-matched with each thermal infrared band. Finally, the spatial details of the multispectral bands are injected into the thermal infrared bands with an MTF Gaussian filter and an additive injection model. Despite the lack of spectral overlap between thermal infrared and multispectral bands, the fused image improves the spatial resolution while maintaining the thermal infrared spectral properties as shown by subjective and objective experimental analyses.

5 November 2026 in EGUsphere
Verified
Preprint
Open access
PDF file
JYJianing Yu
Jianing Yu
LZLixing Zhao
Lixing Zhao
XZXiaoxuan Zhou
Xiaoxuan Zhou
LLLiyuan Li
Liyuan Li
XNXinyue Ni
Xinyue Ni
Fansheng ChenFansheng Chen
Fansheng Chen
Aircraft contrails are an important source of aviation's non-CO2 climate effects, and fine-scale satellite observations provide a means of characterizing their spatial structure. Distinguishing narrow, adjacent, and overlapping contrails from complex backgrounds requires reference data with explicit pixel-level annotations. We present ContrailStruct30, a three-band thermal-infrared contrail segmentation dataset derived from Sustainable Development Science Satellite 1 (SDGSAT-1) observations at 30 m nominal sampling. The dataset contains 19,455 patches of 256 × 256 pixels from 819 source-scene entries acquired on 305 dates between August 2022 and September 2024, including 9,023 positive patches and 10,432 deliberately selected difficult negatives. Each sample provides an enhanced RGB image, corresponding three-band source values stored as uint16, and a human-corrected binary mask. Construction began with 300 manually annotated patches identified through ADS-B-assisted searches and continued through four rounds of model-assisted annotation, manual correction, and expert review. Fixed training, validation, and test partitions separate both source scenes and acquisition dates. As an application baseline, we developed a MaxViT–U-Net segmentation model and compared it with three public models under a shared training protocol to evaluate foreground recovery, centerline agreement, and difficult-background discrimination. Across three training seeds, the baseline achieved a mean positive-patch test Dice of 0.8230 ± 0.0056 (mean ± standard deviation), with strong foreground overlap and centerline agreement in the common evaluation. By combining fine-scale thermal-infrared observations, diverse contrail morphologies, expert-reviewed labels, and corresponding image representations, ContrailStruct30 provides a reusable resource for extracting fine contrail structures and developing and evaluating high-resolution segmentation methods. The dataset presented in this study corresponds to Version 3, which is publicly available via Figshare at https://doi.org/10.6084/m9.figshare.33435496.v3 (Yu et al., 2026).

12 January 2026 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
LLLiyuan Li
Liyuan Li
XZXiaoxuan Zhou
Xiaoxuan Zhou
WZWencong Zhang
Wencong Zhang
YZYifan Zhong
Yifan Zhong
MLMengqi Lv
Mengqi Lv
Fansheng ChenFansheng Chen
Fansheng Chen
The detection and tracking of fast-moving and maneuverable airborne targets, over a wide area from space has long been a technical challenge in the field of aerospace remote sensing. Existing solutions often struggle to balance wide coverage with high frame rate detection. To tackle this problem, our team has developed an innovative bidirectional whisk-broom thermal infrared sensor (TIS). SDGSAT-1 TIS operates in a 505 km sun-synchronous orbit, with an imaging coverage area of 300 km × 300 km. The sensor integrates four 512-pixel LWIR focal plane modules covering three spectral bands: 8-10.5 μm, 10.3-11.3 μm, and 11.5-12.5 μm. Unlike other payloads that overlook the importance of reverse scanning, the SDGSAT-1 TIS employs a unique bidirectional whisk-broom technique to generate two images within a short time interval. And a multi-model joint detection method based on physics, geometry informed and state-of-the-art deep detection models has been proposed, which enhances the detection of flying aircraft and substantially reduces false alarms for wide-area. The results demonstrate that the thermal infrared band provides stable radiometric sensitivity for airborne targets both day and night, and the proposed two-frame detection strategy enables reliable moving-target identification across the full 300 km field of view with greatly reduced data volume. This system achieves real-time, all-day wide-area airborne target monitoring and represents a significant advancement in satellite-based surveillance technology.

1 January 2026 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
JYJianing Yu
Jianing Yu
KWKefang Wang
Kefang Wang
XZXiaoxuan Zhou
Xiaoxuan Zhou
XHxinZhuoyue Hu
xinZhuoyue Hu
LZLixing Zhao
Lixing Zhao
Fansheng ChenFansheng Chen
Fansheng Chen