Xiaowen Zhang

Mr. Xiaowen Zhang

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
13 September 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
XZXiaowen Zhang
Xiaowen Zhang
QLQiaoyuan Liu
Qiaoyuan Liu
HCHongliang Chang
Hongliang Chang
HSHaijiang Sun
Haijiang Sun
Small object detection in remote sensing enables the identification and analysis of unapparent but important information, playing a crucial role in various ground monitoring tasks. Due to the small size, the available feature information contained in small objects is very limited, making them more easily buried by the complex background. As one of the research hotspots in remote sensing, although many breakthroughs have been made, there still exist two significant shortcomings for the existing approaches: first, the down-sampling operation commonly used for feature extraction can barely preserve weak features of objects in a tiny size; second, the convolutional neural network methods have limitations in modeling global context to address cluttered backgrounds. To tackle these issues, a high-resolution network with transformer embedding parallel detection (HRTP-Net) is proposed in this paper. A high-resolution feature fusion network (HR-FFN) is designed to solve the first problem by maintaining high spatial resolution features with enhanced semantic information. Furthermore, a Swin-transformer-based mixed attention module (STMA) is proposed to augment the object information in the transformer block by establishing a pixel-level correlation, thereby enabling global background–object modeling, which can address the second shortcoming. Finally, a parallel detection structure for remote sensing is constructed by integrating the attentional outputs of STMA with standard convolutional features. The proposed method effectively mitigates the impact of the intricate background on small objects. The comprehensive experiment results on three representative remote sensing datasets with small objects (MASATI, VEDAI and DOTA datasets) demonstrate that the proposed HRTP-Net achieves a promising and competitive performance.

27 October 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
YLYide Liu
Yide Liu
HSHaijiang Sun
Haijiang Sun
XZXiaowen Zhang
Xiaowen Zhang
QLQiaoyuan Liu
Qiaoyuan Liu
ZCZhouchang Chen
Zhouchang Chen
CXChongzhuo Xiao
Chongzhuo Xiao
Remote Sensing Image Super-Resolution (RSISR) aims to reconstruct high-resolution (HR) remote sensing (RS) images from low-resolution (LR) RS images inputs by overcoming the physical limitations of imaging systems. As a specialized task in the RS domain, RSISR provides critical support for downstream fine-grained ground object interpretation. Traditional RSISR methods face three major technical shortcomings: First, since wide-area RS images exhibit highly complex ground object characteristics, it is challenging to extract effective multi-scale features for SR reconstruction from their blurred representations. Second, the inherent imaging constraints of RS images lead to insufficient prior information, resulting in poor semantic consistency between SR reconstructions and real scenes. Third, existing SR methods struggle to balance the inherent trade-off between geometric accuracy and visual quality. To address these challenges, this paper proposes Texture Transfer Residual Denoising Dual Diffusion Model (TTRD3), a diffusion model (DM)-based reference-based super-resolution (RefSR) framework. Specifically, the Multi-scale Feature Aggregation Block (MFAB) is designed to extract spatially heterogeneous features with scale variations through parallel heterogeneous convolutional kernels. The Sparse Texture Transfer Guidance (STTG) is developed to mine multi-scale sparse texture features from high-resolution reference (Ref) images of similar scenes. The Residual Denoising Dual Diffusion Model (RDDM) framework is constructed to synergistically optimize geometric accuracy and visual quality by integrating the deterministic modeling of residual diffusion with the diverse generation of noise diffusion. Experiments on multi-source RS datasets demonstrate that TTRD3 significantly outperforms existing state-of-the-art (SOTA) methods in both geometric accuracy and visual quality. Our code and model are available at https://github.com/LED-666/TTRD3.

1 January 2017 in Magnetohydrodynamics
Verified
Journal Article
Closed access
XZXiaowen Zhang
Xiaowen Zhang
OZO. Zikanov
O. Zikanov

19 August 2025 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
HCHongliang Chang
Hongliang Chang
HSHaijiang Sun
Haijiang Sun
Jinchang RenJinchang Ren
Jinchang Ren
QLQiaoyuan Liu
Qiaoyuan Liu
XZXiaowen Zhang
Xiaowen Zhang
Super-Resolution (SR) of satellite video has long been a critical research direction in the field of remote sensing video processing and analysis, and blind SR has attracted increasing attention in the face of satellite video with unknown degradation. However, existing blind SR methods mainly focus on accurate blur kernel estimation, while ignoring the importance of inter-frame information compensation in the time domain. Therefore, this paper focuses on precise temporal information compensation and proposes a blind SR Network based on Inter-Frame Information Compensation (IFIC-SRNet). First, we propose a Multi-Scale Parallel Convolution block (MSPC) to alleviate the difficulty of alignment between satellite video frames due to the presence of moving objects of different scales. Second, we propose a Hybrid Attention-based Feature Extraction Module (HAFEM) that effectively extracts both local and global information between video frames. While activating more pixels, more attention is allocated to informative pixels to obtain the clean features. Finally, a Pyramid Space Activation Module (PSAM) is proposed to gradually adjust the clean features through a multi-layer iterative pyramid structure, enabling the clean features to better perceive blur and achieve pixel-level fine compensation for unknown degraded frames. Extensive experiments on real satellite video datasets demonstrate that our method is superior to state-of-the-art non-blind and blind SR methods, both qualitatively and quantitatively.

9 February 2026 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
XZXiaowen Zhang
Xiaowen Zhang
HSHaijiang Sun
Haijiang Sun
Hanqing SunHanqing Sun
Hanqing Sun
QLQiaoyuan Liu
Qiaoyuan Liu
XSXinglong Sun
Xinglong Sun
XYXinyi Yao
Xinyi Yao
The adjacency effect introduces a coupled challenge of blurry targets and similar-object interference in satellite videos, leading to severe ambiguity in template matching and error accumulation in existing satellite video single object tracking (SOT) methods. Current approaches rely mainly on spatial or temporal modeling, or employ frequency-spatial fusion in either serial or coupled forms, but fail to prevent cross-domain error propagation. To meet the coupled adjacency effect challenge, we present a synergistic perception tracker (SPTrack) that integrates frequency, spatial, and temporal reasoning. The core of SPTrack is the frequency-spatial separate-interact (FSSI) block, which optimizes frequency restoration via adaptive frequency recalibration (AFR) and spatial localization via multiscale context extraction (MCE), and then establishes a bidirectional interaction through a frequency-spatial interaction (FSI) module. This design preserves domain-specific strengths while enabling frequency contours to guide spatial representation learning for robust localization under blur. To further resolve spatial ambiguity caused by similar objects, we introduce an interframe temporal correlation (IFTC) module that exploits historical trajectories and score-map memory to perform drift-aware centroid correction and temporally consistent box refinement. The composition of the above frequency-spatial-temporal synergistic perception methods can track more robustly in scenes affected by the adjacency effect. We conduct comprehensive experiments on the public SatSOT, SV248 s, and OOTB datasets, where SPTrack achieves competitive performance with a success rate of 55.4% and 45.6% on challenging low quality and similar object attributes, a success rate of 49.9% and precision of 65.6% overall performance, while operating at 164.4 FPS. Moreover, our proposed modules can also be integrated into other one-stream trackers as a general solution for the adjacency effect in satellite video SOT.

1 January 2026 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
HCHongliang Chang
Hongliang Chang
HSHaijiang Sun
Haijiang Sun
QLQiaoyuan Liu
Qiaoyuan Liu
XZXiaowen Zhang
Xiaowen Zhang