TZTianxue Zhang

Tianxue Zhang

*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


Tianxue Zhang has a total of 59 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Top Cited Papers
    Open Access

    Interaction-aware dexterous robot for minimally invasive transcanal inner ear interventions

    by Haiming Li, Peiyuan Gao, Haoyue Tan, Haotian Li, Haifeng Zhu, Mengyuan Jiang, Yuting Ni, Yandi He, Junhong Huang, Yue Zhu, et al.

    Intracochlear theranostics, particularly targeted drug delivery and microsampling, offers a promising solution to inner ear diseases. However, specialized medical devices remain limited by a fundamental design challenge imposed by anatomical constraints: balancing miniaturization, dexterity, and perceptive functionality. Here, we present a low–aspect-ratio, dual-segment continuum robot that integrates catheter, endoscopic and instrumental functions. Driven by antagonistic cables, the robot uses a transition-free backbone composed of saddle-shaped joints to achieve a minimum bending radius of 1.9 mm. Dual-segment motion decoupling yields programmable C-/S-shaped configurations, facilitating anatomical navigation. The microneedle, embedded in the central channel, serves as an end-effector with positioning accuracy of 17.9 ± 4.1 μm. Fiber Bragg grating sensors, mounted on the needle, measure axial force to estimate tool-tissue interaction. Validation is performed on cadavers and in vivo animals, demonstrating the feasibility of a transcanal, atraumatic robotic paradigm. Thus, this system provides a practical and accessible approach for early diagnosis and treatment, helping extend precision medicine to underserved areas.


  • Top Cited Papers
    Open Access

    YOLO-MSRF: A Multimodal Segmentation and Refinement Framework for Tomato Fruit Detection and Segmentation with Count and Size Estimation Under Complex Illumination

    by Ao Li, Chunrui Wang, Aichen Wang, Jianpeng Sun, Fengwei Gu, Tianxue Zhang

    Segmentation of tomato fruits under complex lighting conditions remains technically challenging, especially in low illumination or overexposure, where RGB-only methods often suffer from blurred boundaries and missed small or occluded instances, and simple multimodal fusion cannot fully exploit complementary cues. To address these gaps, we propose YOLO-MSRF, a lightweight RGB–NIR multimodal segmentation and refinement framework for robust tomato perception in facility agriculture. Firstly, we propose a dual-branch multimodal backbone, introduce Cross-Modality Difference Complement Fusion (C-MDCF) for difference-based complementary RGB–NIR fusion, and design C2f-DCB to reduce computation while strengthening feature extraction. Furthermore, we develop a cross-scale attention fusion network and introduce the proposed MS-CPAM to jointly model multi-scale channel and position cues, strengthening fine-grained detail representation and spatial context aggregation for small and occluded tomatoes. Finally, we design the Multi-Scale Fusion and Semantic Refinement Network, MSF-SRNet, which combines the Scale-Concatenate Fusion Module (Scale-Concat) fusion with SDI-based cross-layer detail injection to progressively align and refine multi-scale features, improving representation quality and segmentation accuracy. Extensive experiments show that YOLO-MSRF achieves substantial gains under weak and low-light conditions, where RGB-only models are most prone to boundary degradation and missed instances, and it still delivers consistent improvements on the mixed four-light validation set, increasing mAP0.5 by 2.3 points, mAP0.5–0.95 by 2.4 points, and mIoU by 3.60 points while maintaining real-time inference at 105.07 FPS. The proposed system further supports counting, size estimation, and maturity analysis of harvestable tomatoes, and can be integrated with depth sensing and yield estimation to enable real-time yield prediction in practical greenhouse operations.


  • Shape Sensing Method of Discrete-Jointed Continuum of Narrow Auditory Meatus Based on FBG Sensing

    by Yuting Ni, Yimin Luo, Lei Yang, Fuxin Du, He Zhang, Tianxue Zhang

    Injection and sampling of inner ear lymphatic fluid through auditory meatus is an innovative procedure in otology. The urgent need for precision surgery further motivates the application of continuum robots. The tradeoff between confined working space and high precision shape sensing that can intelligently avoid critical anatomy poses a major challenge. In this article, we study an error compensation method of continuum robot shape sensing based on fiber Bragg grating (FBG). The FBG sensing array is integrated with the extremely short continuum. Further, we present a dynamic shape sensing method for otology continuum robot based on FBG and conducted dynamic experiments on models to simulate the injection progress. The percentage error on the planar C-shaped model is 3.32%. On the planar S-shaped models, the percentage error reduces from 6.25% to 5.86% with the decrease in the channel diameter. An experimental shape sensing system of the otology continuum robot is built. The standard deviation of shape sensing is 0.6185–1.6638 mm. An innovative detection method is proposed for the shape sensing of continuum in narrow spaces. The experimental results with an average error of 1.2163 mm effectively verify the feasibility of continuum shape sensing in narrow channels based on FBG.


  • Design and evaluation of FBG-based vascular shape reconstruction sensors through animal experiments

    by Yimin Luo, Shijia Chen, Cheng Wang, Yuting Ni, He Zhang, Shengnan Lyu, Tianxue Zhang


  • YOLOv8np-RCW: A multi-task deep learning model for comprehensive visual information in tomato harvesting robot

    by Ai Xinyi, Zhang Tianxue, Yuan Ting, Zheng Xiajun, Xiong Ziming, Yuan Jiace

    In greenhouse environments, using automated machines for tomato harvesting to reduce labor consumption is a future development trend. Accurate and effective visual recognition is essential to accomplish harvesting tasks. However, most current studies use various models to gain harvesting information in multiple steps, resulting in heavy calculation costs, poor real-time availability, and weak recognition precision. In this study, an improved YOLOv8np-RCW end-to-end model based on YOLOv8n pose is proposed to simultaneously detect tomato bunches, maturity, and keypoints using a decoupled-head structure. The model integrates a ResNet-enhanced RepVGG architecture for a balance of accuracy and speed, employs the CARAFE upsampling algorithm for a larger receptive field with lightweight design, and optimizes the loss function with WIoU loss to enhance bounding box prediction, maturity detection, and keypoint extraction. Experimental results indicate that mAP50 of YOLOv8np-RCW model for bounding box and keypoints is 87.3% and 86.8% respectively, which is 6.2% and 5.5% higher than YOLOv8n pose model. Completing the tasks of bunch detection, maturity assessment, and keypoint localization requires only 9.8 ms. Euclidean distance error is less than 20 pixels in detecting keypoints. Based on this model, a method is proposed to quickly determine the orientation of tomato bunches using geometric cross-product and cross-multiplication calculations from keypoint 2D information, providing guidance for the motion planning of the end-effector. In field experiments, the robot achieved a harvesting success rate of 68%, with an average time of 10.8366 seconds per tomato bunch.


  • Top Cited Papers
    Open Access

    D3-YOLOv10: Improved YOLOv10-Based Lightweight Tomato Detection Algorithm Under Facility Scenario

    by Ao Li, Chunrui Wang, Tongtong Ji, Qiyang Wang, Tianxue Zhang

    Accurate and efficient tomato detection is one of the key techniques for intelligent automatic picking in the area of precision agriculture. However, under the facility scenario, existing detection algorithms still have challenging problems such as weak feature extraction ability for occlusion conditions and different fruit sizes, low accuracy on edge location, and heavy model parameters. To address these problems, this paper proposed D3-YOLOv10, a lightweight YOLOv10-based detection framework. Initially, a compact dynamic faster network (DyFasterNet) was developed, where multiple adaptive convolution kernels are aggregated to extract local effective features for fruit size adaption. Additionally, the deformable large kernel attention mechanism (D-LKA) was designed for the terminal phase of the neck network by adaptively adjusting the receptive field to focus on irregular tomato deformations and occlusions. Then, to further improve detection boundary accuracy and convergence, a dynamic FM-WIoU regression loss with a scaling factor was proposed. Finally, a knowledge distillation scheme using semantic frequency prompts was developed to optimize the model for lightweight deployment in practical applications. We evaluated the proposed framework using a self-made tomato dataset and designed a two-stage category balancing method based on diffusion models to address the sample class-imbalanced issue. The experimental results demonstrated that the D3-YOLOv10 model achieved an mAP0.5 of 91.8%, with a substantial reduction of 54.0% in parameters and 64.9% in FLOPs, compared to the benchmark model. Meanwhile, the detection speed of 80.1 FPS more effectively meets the demand for real-time tomato detection. This study can effectively contribute to the advancement of smart agriculture research on the detection of fruit targets.


  • Research on Vascular Thrombosis Detection Methods Based on Fiber Bragg Grating Sensing

    by Tianxue Zhang, Yimin Luo, Yuting Ni, Shijia Chen, Shuo Wu, Anzhu Gao, Shengnan Lyu

    Thrombosis is a major cause of stroke. Current medical diagnosis and treatment of vascular thrombosis is mainly based on angiographic techniques using iodinated contrast agents, which expose both the physician and the patient to high doses of radiation, leading to risks and injuries. In this article, we propose a thrombus detection method based on fiber Bragg grating (FBG) sensors. Firstly, a mathematical model related to thrombus-FBG strain for uniform and variable diameter blood vessels is constructed. Then, we reveal the correlation between blood flow, thrombus hardness, scale, and FBG strain through mathematical and thrombus biomechanical methods. On this basis, we develop an analytical model to detect the extent of vascular thrombus occlusion using FBG and confirm its efficacy in identifying thrombotic occlusions. Further experiments validate the correlation between FBG measurements and thrombus hardness. The experiments demonstrate that the maximum strain difference between high-hardness and low-hardness thrombi is 9.89με. Finally, experiments validate the relationship between FBG strains and blood flow. Under varying blood flow conditions, the average strain difference generated by thrombus in regions adjacent to the FBG gratings is 4.48με. These findings demonstrate the potential of FBG sensors to detect thrombus locations across different blood flow rates.


  • A Vascular Shape Reconstruction Method Based on Multicore FBG Sensing

    by Tianxue Zhang, Anzhu Gao, Jianjun Zhu, Bohan Zhang, Jiachun Lin, Yuting Ni

    Fiber Bragg grating (FBG) optical fiber shape sensing has the potential to minimize harmful radiation exposure for both medical professionals and patients. It provides real-time, three-dimensional visualization of vascular structures during interventional procedures. The field has witnessed advancements through the development of a multi-core 5-FBG sensor array engineered to capture critical attributes inherent to vascular morphology, such as curvature and torsion. An optimized helical extension method (HEM) has been introduced to accurately measure vessel curvature degrees and facilitate precise three-dimensional reconstruction of vascular shapes. This refined HEM algorithm has significantly reduced the reconstruction error rate to 15.611%. An experimental system for interventional vascular optical fiber sensing was established to validate the effectiveness of the proposed method. The obtained vascular shape measurements were compared with those derived from computed tomography (CT) imaging. The maximum error between the two measurements was found to be less than 1.4156 mm, affirming the accuracy of the enhanced HEM algorithm in perceiving vascular shape. This research demonstrates the feasibility of utilizing the constructed multi-core 5-FBGs optical fiber for shape perception in a wide range of vascular structures. This study serves as a foundation for the integration of FBG sensors into clinical vascular shape perception approaches, presenting the potential benefits of reduced radiation exposure and improved accuracy in interventional procedures.


  • An MR Compatible Vascular Stenosis Method Based on Fiber Bragg Grating

    by Tianxue Zhang, Anzhu Gao, Guang-Zhong Yang

    Progressive stenosis of blood vessels is an important cause of cardiovascular diseases. Traditional intervention methods rely on fluoroscopy, which exposes both patients and operators to ionizing radiation. In this paper, we propose a real-time detection method for vascular stenosis intervention based on Fiber Bragg Grating (FBG) sensors that can be used under magnetic resonance imaging (MRI) guidance. An FBG sensor array with 5 sensors is developed and validated using a vascular flow phantom that simulates the morphological features of stenoses. We first verify the sensor for measuring vascular stenosis through flow rate and profile using the FBG sensor array, followed by a detailed assessment of the MRI compatibility of the sensor in terms of imaging artefact and changes in SNR, The error of FBG array is within the range of ±10με, the SNR variation is 3.608%, indicating that the FBG sensor array has excellent MR image compatibility. Experiment results show a good correlation between the degrees of stenoses with strain measurements, thus offering real-time information to aid MR guided vascular intervention.