Tianhong Yan
YOU?
Author Swipe
View article: Astra: Toward General-Purpose Mobile Robots via Hierarchical Multimodal Learning
Astra: Toward General-Purpose Mobile Robots via Hierarchical Multimodal Learning Open
Modern robot navigation systems encounter difficulties in diverse and complex indoor environments. Traditional approaches rely on multiple modules with small models or rule-based systems and thus lack adaptability to new environments. To a…
View article: ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models
ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models Open
Large Multimodal Models (LMMs) exhibit major shortfalls when interpreting images and, by some measures, have poorer spatial cognition than small children or animals. Despite this, they attain high scores on many popular visual benchmarks, …
View article: Intelligent evaluation method for identifying favorable shale oil areas based on improved stacked sparse autoencoder
Intelligent evaluation method for identifying favorable shale oil areas based on improved stacked sparse autoencoder Open
Identifying and evaluating favorable areas is crucial for shale oil exploration and development, well-location deployment, and fracturing design. Traditional machine learning methods struggle to accurately extract the characteristics of fa…
View article: A Robust and Adaptive AUV Integrated Navigation Algorithm Based on a Maximum Correntropy Criterion
A Robust and Adaptive AUV Integrated Navigation Algorithm Based on a Maximum Correntropy Criterion Open
In the underwater domain where Autonomous Underwater Vehicles (AUVs) operate, measurements may suffer from the impact of outliers and non-Gaussian noise. These factors can potentially undermine the efficacy of integrated navigation algorit…
View article: EA-YOLO: Efficient Extraction and Aggregation Mechanismof YOLO for Fire Detection
EA-YOLO: Efficient Extraction and Aggregation Mechanismof YOLO for Fire Detection Open
For fire detection, there are characteristics such as variable sample feature morphology, complex background and dense target, small sample size of dataset and imbalance ofcategories, which lead to the problems of low accuracy and poor rea…
View article: Toward the development of smart capabilities for understanding seafloor stretching morphology and biogeographic patterns via DenseNet from high-resolution multibeam bathymetric surveys for underwater vehicles
Toward the development of smart capabilities for understanding seafloor stretching morphology and biogeographic patterns via DenseNet from high-resolution multibeam bathymetric surveys for underwater vehicles Open
The increasing use of underwater vehicles facilitates deep-sea exploration at a wide range of depths and spatial scales. In this paper, we make an initial attempt to develop online computing strategies to identify seafloor categories and p…
View article: Endoscopic image classification algorithm based on Poolformer
Endoscopic image classification algorithm based on Poolformer Open
Image desmoking is a significant aspect of endoscopic image processing, effectively mitigating visual field obstructions without the need for additional surgical interventions. However, current smoke removal techniques tend to apply compre…
View article: MS23D: A 3D Object Detection Method Using Multi-Scale Semantic Feature Points to Construct 3D Feature Layer
MS23D: A 3D Object Detection Method Using Multi-Scale Semantic Feature Points to Construct 3D Feature Layer Open
LiDAR point clouds can effectively depict the motion and posture of objects in three-dimensional space. Many studies accomplish the 3D object detection by voxelizing point clouds. However, in autonomous driving scenarios, the sparsity and …
View article: PV-SSD: A Multi-Modal Point Cloud Feature Fusion Method for Projection Features and Variable Receptive Field Voxel Features
PV-SSD: A Multi-Modal Point Cloud Feature Fusion Method for Projection Features and Variable Receptive Field Voxel Features Open
LiDAR-based 3D object detection and classification is crucial for autonomous driving. However, real-time inference from extremely sparse 3D data is a formidable challenge. To address this problem, a typical class of approaches transforms t…
View article: DPNet: Dual-Pyramid Semantic Segmentation Network Based on Improved Deeplabv3 Plus
DPNet: Dual-Pyramid Semantic Segmentation Network Based on Improved Deeplabv3 Plus Open
Semantic segmentation finds wide-ranging applications and stands as a crucial task in the realm of computer vision. It holds significant implications for scene comprehension and decision-making in unmanned systems, including domains such a…
View article: Data-Driven Fault Detection of AUV Rudder System: A Mixture Model Approach
Data-Driven Fault Detection of AUV Rudder System: A Mixture Model Approach Open
Based on data-driven and mixed models, this study proposes a fault detection method for autonomous underwater vehicle (AUV) rudder systems. The proposed method can effectively detect faults in the absence of angle feedback from the rudder.…
View article: Efficient three-dimensional point cloud object detection based on improved Complex-YOLO
Efficient three-dimensional point cloud object detection based on improved Complex-YOLO Open
Lidar-based 3D object detection and classification is a critical task for autonomous driving. However, inferencing from exceedingly sparse 3D data in real-time is a formidable challenge. Complex-YOLO solves the problem of point cloud disor…
View article: Performance-guaranteed distributed control for multiple plant protection UAVs with collision avoidance and a directed topology
Performance-guaranteed distributed control for multiple plant protection UAVs with collision avoidance and a directed topology Open
The urgent requirement for improving the efficiency of agricultural plant protection operations has spurred considerable interest in multiple plant protection UAV systems. In this study, a performance-guaranteed distributed control scheme …
View article: Hydrodynamic numerical simulation and prediction of bionic fish based on computational fluid dynamics and multilayer perceptron
Hydrodynamic numerical simulation and prediction of bionic fish based on computational fluid dynamics and multilayer perceptron Open
This paper proposes a prediction strategy for the hydrodynamic performance of bionic fish. The major challenges are meshing and building prediction model. The NACA0012 airfoil is used to replace the fish driven by the body and/or caudal fi…
View article: Non-condensable helium effect on heat and mass transfer characteristics inside a liquid hydrogen tank.
Non-condensable helium effect on heat and mass transfer characteristics inside a liquid hydrogen tank. Open
Existence of non-condensable helium in cryogenic tank ullage may affect the interfacial heat and mass transfer characteristics and also the pressurization performance. In the present paper, helium effect on heat and mass transfer inside a …
View article: [Atrial fibrillation diagnosis algorithm based on improved convolutional neural network].
[Atrial fibrillation diagnosis algorithm based on improved convolutional neural network]. Open
Atrial fibrillation (AF) is a common arrhythmia, which can lead to thrombosis and increase the risk of a stroke or even death. In order to meet the need for a low false-negative rate (FNR) of the screening test in clinical application, a c…
View article: A FEATURE SELECTION-BASED ALGORITHM FOR DETECTION OF ATRIAL FIBRILLATION USING SHORT-TERM ECG
A FEATURE SELECTION-BASED ALGORITHM FOR DETECTION OF ATRIAL FIBRILLATION USING SHORT-TERM ECG Open
In the presence of premature atrial contraction (PAC), premature ventricular contraction (PVC) or other ectopic beats, RR intervals (RRIs) may be disturbed, which results in other types of heart disease being misdiagnosed as atrial fibrill…
View article: Multiple Receptive Field Network (MRF-Net) for Autonomous Underwater Vehicle Fishing Net Detection Using Forward-Looking Sonar Images
Multiple Receptive Field Network (MRF-Net) for Autonomous Underwater Vehicle Fishing Net Detection Using Forward-Looking Sonar Images Open
Underwater fishing nets represent a danger faced by autonomous underwater vehicles (AUVs). To avoid irreparable damage to the AUV caused by fishing nets, the AUV needs to be able to identify and locate them autonomously and avoid them in a…
View article: Soft Sensing Applications for Non-Stable Processes Based on a Weighted High-Order Dynamic Information Structure
Soft Sensing Applications for Non-Stable Processes Based on a Weighted High-Order Dynamic Information Structure Open
Nowadays, industrial processes are fully equipped by redundant hardware sensors which can be interfered by random noises. Hence, it is of high importance to develop soft sensing solutions for key variables prediction and process monitoring…
View article: Visual Navigation Features Selection Algorithm Based on Instance Segmentation in Dynamic Environment
Visual Navigation Features Selection Algorithm Based on Instance Segmentation in Dynamic Environment Open
Ego-motion estimation, as one of the core technologies of unmanned systems, is widely used in autonomous robot navigation, unmanned driving, augmented reality and other fields. With the development of computer vision, there has been consid…
View article: ECNet: Efficient Convolutional Networks for Side Scan Sonar Image Segmentation
ECNet: Efficient Convolutional Networks for Side Scan Sonar Image Segmentation Open
This paper presents a novel and practical convolutional neural network architecture to implement semantic segmentation for side scan sonar (SSS) image. As a widely used sensor for marine survey, SSS provides higher-resolution images of the…
View article: A new modified wavelet-based ECG denoising
A new modified wavelet-based ECG denoising Open
Purpose: Wavelet denoising is one of the denoising methods commonly used for ECG signals. However, due to the frequency overlap between the EMG and ECG, the feeble characteristics of ECG signals exists the risk of being weakened in the pro…
View article: Fractional-Order PID Motion Control for AUV Using Cloud-Model-Based Quantum Genetic Algorithm
Fractional-Order PID Motion Control for AUV Using Cloud-Model-Based Quantum Genetic Algorithm Open
Aiming to improve the performance of motion for autonomous underwater vehicle (AUV), a fractional-order PID strategy is proposed. It is a more generalized form for the conventional integer-order PID controller, keeping its simplicity and u…
View article: CFD investigation on thermodynamic characteristics of on-orbit cryogenic tank during reorientation process.
CFD investigation on thermodynamic characteristics of on-orbit cryogenic tank during reorientation process. Open
For a typical aerospace exploration mission, engine restart operation is usually encountered in which propellant slosh and reorientation are necessary. In this process, a series of thermodynamic characteristics including slosh, gas-liquid …
View article: A Novel Reaching Law for Sliding Mode Control of Uncertain Discrete-Time Systems
A Novel Reaching Law for Sliding Mode Control of Uncertain Discrete-Time Systems Open
This paper proposed a new sliding mode control algorithm for discrete-time systems with matched uncertainty. The new control algorithm is characterized by a new discrete switching surface. Although the exponential reaching law can reduce o…
View article: An inverted micro-mixer based on a magnetically-actuated cilium made of Fe doped PDMS
An inverted micro-mixer based on a magnetically-actuated cilium made of Fe doped PDMS Open
In this paper, we report a new micromixer based on a flexible artificial cilium activated by an external magnetic field. The cilium is fabricated from Polydimethylsiloxane doped with Fe microparticles. The fabrication method is based on th…