A5032543777- Target Tracking and Data Fusion in Sensor Networks
- Advanced Image Fusion Techniques
- Infrared Target Detection Methodologies
- Remote-Sensing Image Classification
- Advanced Measurement and Detection Methods
- Image and Signal Denoising Methods
- Distributed Sensor Networks and Detection Algorithms
- Fault Detection and Control Systems
- Video Surveillance and Tracking Methods
- Inertial Sensor and Navigation
- Distributed Control Multi-Agent Systems
- Robotics and Sensor-Based Localization
- Advanced Vision and Imaging
- Advanced Image and Video Retrieval Techniques
- Remote Sensing and Land Use
- Adaptive Control of Nonlinear Systems
- Face and Expression Recognition
- Neural Networks and Applications
- Space Satellite Systems and Control
- Sparse and Compressive Sensing Techniques
- Image Retrieval and Classification Techniques
- Image Processing Techniques and Applications
- Photoacoustic and Ultrasonic Imaging
- Guidance and Control Systems
- Advanced Algorithms and Applications
Shanghai Jiao Tong University
2016-2025
Nanjing University of Aeronautics and Astronautics
2014-2025
Shanghai Children's Medical Center
2025
Jiangsu Vocational College of Medicine
2024
Laoshan Laboratory
2024
China University of Petroleum, East China
2024
State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation
2024
Northwestern Polytechnical University
1990-2002
This paper presents a noise adaptive variational Bayesian cubature information filter based on Wishart distribution. In the frame of recursive estimation, propagating matrix and state is derived. And integration estimation approximated by rule. Then, inverse measurement modeled as distribution, so joint distribution posterior can be product independent Gaussian Wishart. Furthermore, corresponding square root version also derived to improve numerical characteristics. Simulation results with...
The traditional consensus-based filters are widely used in distributed sensor networks. However, they suffer from divergence when outliers occur. This paper proposes a robust consensus nonlinear information filter for state estimation with measurement outliers. Unlike the Gaussian assumption filers, of each node is modeled here as multivariate Student- t process unknown parameters sufficient statistic. variational Bayesian method employed to jointly estimate and parameters. As coupled,...
This letter addresses the consensus-based nonlinear state estimation in distributed sensor networks with unknown measurement noise statistics. The existence of naive nodes and communication constraint requires a hybrid consensus filtering method. In frame filtering, novel approach named variational Bayesian cubature Kalman filter (VB-CCKF) is proposed, which CKF employed to handle VB approximation adopted iteratively estimate sufficient statistics covariance on each step. Simulations are...
This article introduces a novel consensus-based labeled multi-Bernoulli (LMB) filter to tackle multitarget tracking (MTT) in distributed sensor network (DSN), whose nodes have limited and different fields of view (FoVs). Although algorithms are effective for fusion MTT, it may be problematic when FoVs. To deal with this issue, the proposed method constructs an extended label space mapping overcome "label mismatching" phenomenon; after that, model undetected multitargets is established so...
Unmanned Aerial Manipulators (UAMs) have much potential for automating the cleaning of high-rise windows. In this letter, a switchable UAM system is designed to carry out task by installing robot onto window. The divided into four phases: free-flight, attaching, delivery and detaching. Control methods are developed all phases, switch strategies between different phases proposed. results outdoor window-cleaning installation experiments using proposed demonstrate effectiveness our control strategies.
In this paper, we consider the position control problem of nonholonomic mobile robots, i.e., regulation robots to a desired specified by image feature point onboard robot, using visual feedback information from an overhead fixed camera. Many vision-based approaches have been proposed for motion however, they usually assume that exact or approximate knowledge full/partial intrinsic and/or extrinsic parameters camera can be available, and large even very small errors in these deteriorate...
In this letter, a robust minimum error entropy based cubature information filter is proposed for state estimation in non-Gaussian measurement noise. A new combined optimization cost defined on the entropy. Through transform, statistical linearization regression model constructed, and then developed by minimizing cost. The fixed-point iteration approach used to compute estimate. Further, convergence of analyzed, conditions are derived. Simulations performed demonstrate effectiveness...
This paper introduces a novel consensus-based labeled multi-Bernoulli (LMB) filter to tackle multi-target tracking (MTT) in communication resource-sensitive distributed sensor network (DSN). Although approaches provide effective tools for fusion and MTT, the requirement of iterative makes it impractical resource limited situations. To deal with this issue, two event-triggered strategies are proposed incorporated into LMB. Focusing on information discrepancy between local probability density...
Considerable progress has recently been made in leveraging CLIP (Contrastive Language-Image Pre-Training) models for text-guided image manipulation. However, all existing works rely on additional generative to ensure the quality of results, because alone cannot provide enough guidance information fine-scale pixel-level changes. In this paper, we introduce CLIPVG, a manipulation framework using differentiable vector graphics, which is also first CLIP-based general that does not require any...
Abstract Background Congenital and acquired heart disease affects ∼1% of children globally, with right ventricular (RV) dysfunction being a common complex issue due to conditions like congenital (CHD), pulmonary hypertension (PH), prematurity. Accurate RV assessment is challenging its unique geometry, interventricular interactions, morphological variability in pediatric patients. Fractional area change (FAC), key echocardiographic measure, correlates strongly severity, aiding timely...
Aiming at achieving the object grasping task, an inchworm-snake inspired flexible robotic manipulator (FRM) is presented in this article. By using both and rigid materials robot structure, FRM has stability control accuracy of a as well compliant behavior soft robot. The piecewise-linear driving characteristic shape memory alloy (SMA) actuator enables accurate establishment FRM's kinematic model model-based method. Deep learning-based eye-in-hand binocular visual perception designed to...