A5100333956- Robotics and Sensor-Based Localization
- Robotic Path Planning Algorithms
- Image Processing Techniques and Applications
- Autonomous Vehicle Technology and Safety
- Indoor and Outdoor Localization Technologies
- Advanced Image Fusion Techniques
- Enhanced Oil Recovery Techniques
- Advanced Vision and Imaging
- Advanced Neural Network Applications
- Human Pose and Action Recognition
- Reservoir Engineering and Simulation Methods
- Video Surveillance and Tracking Methods
- Text and Document Classification Technologies
- CO2 Sequestration and Geologic Interactions
- Machine Learning and Data Classification
- Retinopathy of Prematurity Studies
- Technology's Impact on Media
- Connexins and lens biology
- Personal Information Management and User Behavior
- Globalization, Economics, and Policies
- Gait Recognition and Analysis
- Cognitive Computing and Networks
- Water Quality Monitoring Technologies
- Digital Platforms and Economics
- Nuclear Engineering Thermal-Hydraulics
State Key Laboratory of Vehicle NVH and Safety Technology
2022-2024
Peng Cheng Laboratory
2024
Research Institute of Petroleum Exploration and Development
2022-2023
Chinese Academy of Medical Sciences & Peking Union Medical College
2023
Beijing Academy of Artificial Intelligence
2023
Harbin Normal University
2023
Peking Union Medical College Hospital
2023
Qingdao University
2022
Wuhan University of Technology
2017
Jinan University
2013
Disease diagnosis occupies an important position in the medical field. The of disease is basis for choosing right treatment plan. Doctors must first diagnose what patient has based on clinical characteristics various diseases, and then they can administer medicine. When building models diagnosis, are required to be able handle uncertainty information. belief rule base (BRB) effectively information under by introducing distributions. However, current research, BRB-based still have problems...
Simultaneous localization and mapping (SLAM) is one of the fundamental capabilities for autonomous vehicles to achieve accurate in dynamic urban environments. However, real-world scenarios, presence moving objects such as pedestrians, bicycles, or affects accuracy SLAM leaves behind ghost trails created map. Hence, it essential remove real-time improve its accuracy. In this article, we present removal LiDAR-inertial (DOR-LINS), a framework light detection ranging (LiDAR)-Inertial SLAM. Built...
Background: NOD-, LRR-, and pyrin domain-containing protein 3 (NLRP3) is a common inflammatory factor that induces inflammation by increasing the expression of related cytokines. Although NLRP3 inflammasome has been implicated in many ophthalmic diseases, its role myopia largely unknown. The aim this study was to explore relationship between progression pathway. Methods: A form-deprivation (FDM) mouse model used. Different degrees myopic shift were achieved via monocular form deprivation...
OPINION article Front. Energy Res., 19 January 2023Sec. Carbon Capture, Utilization and Storage Volume 10 - 2022 | https://doi.org/10.3389/fenrg.2022.1102774
Many visual SLAM systems are generally solved using natural landmarks or optical flow. However, due to textureless areas, illumination change motion blur, they often acquire poor camera poses even fail track. Additionally, cannot obtain with a metric scale in the monocular case. In some cases (such as when calibrating extrinsic parameters of camera-IMU), we prefer sacrifice flexibility such methods improve accuracy and robustness by artificial landmarks. This paper proposes enhancements...
This article investigates the multi-vehicle task assignment and motion planning (MVTAMP) problem. In a dense environment, fleet of non-holonomic vehicles is appointed to visit series target positions then move specific ending area for real-world applications such as clearing threat targets, aid rescue, package delivery. We presented novel hierarchical method simultaneously address multiple vehicles’ Unlike most related work, our considers MVTAMP problem applied in large-scale scenarios. At...
In view of the traditional Canny edge detection algorithm in smoothing filter will make image become blurred and threshold selection is not adaptive, its defects gradient calculation, this paper proposes an improved algorithm.The uses adaptive median filtering instead Gaussian filtering.The method adopted to enhance influence middle pixel improve precision.The Otsu introduced calculate value according information, which avoids difficulty artificially setting high low thresholds.The...
LiDAR–binocular camera systems have attracted increasing research attention with their advantages of two sensors. The two-sensor data fusion premise accurately calibrates the external parameters both However, existing LiDAR and binocular calibration uses geometric methods to calibrate left right cameras or register point cloud depth map obtain extrinsic parameters. Existing difficulty obtaining low baseline length reprojection errors simultaneously. This article proposes a parameter method...
In recent years, LiDAR has emerged as one of the primary sensors for mobile robots, enabling accurate detection 3D objects. On other hand, 4D millimeter-wave Radar presents several advantages which can be a complementary LiDAR, including an extended range, enhanced sensitivity to moving objects, and ability operate seamlessly in various weather conditions, making it highly promising technology. To leverage strengths both sensors, this paper proposes novel fusion method that combines object...
Full-reference image quality assessment (FR-IQA) models generally operate by measuring the visual differences between a degraded and its reference. However, existing FR-IQA including both classical ones (eg, PSNR SSIM) deep-learning based measures LPIPS DISTS) still exhibit limitations in capturing full perception characteristics of human system (HVS). In this paper, instead designing new measure, we aim to explore generalized attention estimation strategy mimic process rating enhance IQA...
3D human tracking plays a crucial role in the automation intelligence system. Current approaches focus on achieving higher performance traditional driving datasets like KITTI, which overlook jitteriness of platform and complexity environments. Once scenarios are migrated to jolting robot platforms, they all degenerate severely with only 20-60% success rate, greatly restricts high-level application autonomous systems. In this work, beyond flat scenes, we introduce Multi-modal Human Tracking...
In this paper we present GPE4CGSP, which targets the interoperability between GPE (Grid Programming Environment) and CGSP (ChinaGrid Support Platform). The web services technique gridftp data transfer protocol are used to implement interoperation CGSP. Grid application can be deployed through GPE. Without modification, client freely visit use resources in Typically, end users submit jobs client. GPE4CGSP provides one feasible way for of heterogeneous grid infrastructures. evaluation proves...
The ability of environmental awareness is the premise for unmanned ground vehicles to navigate autonomously and avoid obstacles. Obstacle detection an important part technology. Compared with positive obstacles above ground, negative located below are more difficult detect cause damage vehicle. Consequently, research on various types obstacle technology has great significance value. Aiming at problem that texture features not obvious, easily blocked by shadows, relatively small in camera's...
New era's change and development make more higher requirements for small courtyard.Everyone's aesthetic view is different.Small courtyard style can reflect the subjectivity temperament interest of owner, design tool premier to put idea into reality.Small in horizontal direction define two-dimensional space.Different levels landscape, such as lawn, plants, water, roads, road teeth, create a different landscape effect accordingly.And vertical shapes three-dimensional space, easy give person...
Over the past two decades, popularity of ICT has brought humans into an unprecedented era information.A academia go in-depth study related fields, and made great progress in fields information economy, knowledge-based network virtual economy.However, none can provide a unified comprehensive explanation about new economic phenomena such as wide range free internet applications our daily life.The bit economy research emerged to heap up with times.This article, based on firstly discusses its...
In recent years, quantum computers have been attracting attention. Quantum become a hot topic of research in today's scientific research. This paper first introduces the basic principles computers, including storage principle and logic gates, then algorithm, organization finally is discussion that will evaluate strengths weaknesses discusses physical implementation outlook on computing.