A5062501106- Computer Graphics and Visualization Techniques
- Remote Sensing and LiDAR Applications
- Advanced Vision and Imaging
- 3D Surveying and Cultural Heritage
- 3D Shape Modeling and Analysis
- Robotics and Sensor-Based Localization
- Autonomous Vehicle Technology and Safety
- Advanced Image and Video Retrieval Techniques
- Military Defense Systems Analysis
- Magnetic Bearings and Levitation Dynamics
- Advanced Neural Network Applications
- Greenhouse Technology and Climate Control
- Advanced Clustering Algorithms Research
- Solar Radiation and Photovoltaics
- Industrial Technology and Control Systems
- Advanced Decision-Making Techniques
- Magnetic Properties and Applications
- Astronomical Observations and Instrumentation
- Remote Sensing in Agriculture
- Image Processing and 3D Reconstruction
- Infrared Target Detection Methodologies
- Electric Motor Design and Analysis
Jiangsu University
2022
Baidu (China)
2019-2020
National Engineering Laboratory of Deep Learning Technology and Application
2019
King Abdullah University of Science and Technology
2016
Shenzhen Institute of Information Technology
2015
Pre School Learning Alliance
2013
Shenzhen Institutes of Advanced Technology
2010
Jiaying University
2005
Simulation systems have become an essential component in the development and validation of autonomous driving technologies. The prevailing state-of-the-art approach for simulation is to use game engines or high-fidelity computer graphics (CG) models create scenarios. However, creating CG vehicle movements (e.g., assets simulation) remains a manual task that can be costly time-consuming. In addition, fidelity images still lacks richness authenticity real-world using these training leads...
Trees, bushes, and other plants are ubiquitous in urban environments, realistic models of trees can add a great deal realism to digital scene. There has been much research on modeling tree structures, but limited work reconstructing the geometry real-world -- even then, most works have focused reconstruction from photographs aided by significant user interaction. In this paper, we perform active laser scanning vegetation present an automatic approach that robustly reconstructs skeletal...
Trees, bushes, and other plants are ubiquitous in urban environments, realistic models of trees can add a great deal realism to digital scene. There has been much research on modeling tree structures, but limited work reconstructing the geometry real-world -- even then, most works have focused reconstruction from photographs aided by significant user interaction. In this paper, we perform active laser scanning vegetation present an automatic approach that robustly reconstructs skeletal...
We present a lobe-based tree representation for modeling trees. The new is based on the observation that tree's foliage details can be abstracted into canonical geometry structures, termed lobe-textures. introduce techniques to (i) approximate of given data and encode it representation, (ii) decode synthesize fully detailed model visually resembles input. encoded serves as light intermediate which facilitates efficient storage transmission massive amounts trees, e.g., from server clients...
We present a lobe-based tree representation for modeling trees. The new is based on the observation that tree's foliage details can be abstracted into canonical geometry structures, termed lobe-textures. introduce techniques to (i) approximate of given data and encode it representation, (ii) decode synthesize fully detailed model visually resembles input. encoded serves as light intermediate which facilitates efficient storage transmission massive amounts trees, e.g., from server clients...
In Autonomous Driving (AD), detection and tracking of obstacles on the roads is a critical task. Deep-learning based methods using annotated LiDAR data have been most widely adopted approach for this. Unfortunately, annotating 3D point cloud very challenging, time- money-consuming this letter, we propose novel simulator that augments real with synthetic (e.g., vehicles, pedestrians, other movable objects). Unlike previous simulators entirely rely CG (Computer Graphics) models game engines,...
3D instance segmentation plays a predominant role in environment perception of robotics and augmented reality. Many deep learning based methods have been presented recently for this task. These rely on either detection branch to propose objects or grouping step assemble same-instance points. However, do not ensure consistent label each point, while the requires parameter-tuning is computationally expensive. In paper, we introduce novel framework enable end-to-end without separate grouping....
Trees, bushes, and other plants are ubiquitous in urban environments, realistic models of trees can add a great deal realism to digital scene. There has been much research on modeling tree structures, but limited work reconstructing the geometry real-world -- even then, most works have focused reconstruction from photographs aided by significant user interaction. In this paper, we perform active laser scanning vegetation present an automatic approach that robustly reconstructs skeletal...
We propose a framework for global registration of building scans. The first contribution our work is to detect and use portals (e.g., doors windows) improve the local between two Our second an optimization based on linear integer programming formulation. abstract each scan as block model blocks problem that aims at maximizing overall matching score entire scene. efficient solution this by iteratively detecting adding constraints. demonstrate effectiveness proposed method buildings various...
We introduce a 3D tree modeling technique that utilizes examples of real trees to enhance creation with realistic structures and fine-level details. In contrast previous works use smooth generalized cylinders represent branches, our method generates looking models complex branching geometry by employing an exemplar database consisting real-life reconstructed from scanned data. These are sliced into representative parts (denoted as tree-cuts), representing trunk logs structures. the process,...
The evolution of 3D scanning technologies have revolutionized the way real-world object are digitally acquired. Nowadays, high-definition and high-speed scanners can capture even large scale scenes with very high accuracy. Nevertheless, acquisition complete objects remains a bottleneck, requiring to carefully sample whole object's surface, similar coverage process. Holes undersampled regions common in scans complex-shaped self occlusions hidden interiors. In this paper we introduce novel...
In this study, a novel dual permanent magnet excited vernier machine (DPMEVM) with magnets shifting in stator is proposed. Compared the conventional synchronous (PMSM), DPMEVM based on bidirectional field modulation effect can operate wider torque range. However, ripple of high because superposition generated by stator-side and rotor-side PMs. Consequently, proposed to further reduce ripple. First, topologies working principles baseline machines are introduced. Second, torque-contribution...
Abstract We present a semi‐automatic method for reconstructing flower models from single photograph. Such reconstruction is challenging since the 3D structure of can appear ambiguous in projection. However, head typically consists petals embedded space that share similar shapes and form certain level regular structure. Our technique employs these assumptions by first fitting cone subsequently surface revolution to then computing individual petal their projection photo. Flowers with multiple...
Point cloud segmentation is fundamental in under- standing 3D environments. However, most existing methods usually perform poorly on identifying boundaries of touching objects and large surfaces objects. Planes a scene act as supporting to separate provide geometry priors group points surface shown Fig. 1. Besides, planes can roughly represent the structure scene, are more efficient encode holistic contexts than scale point clouds. In light above advantages, we advise plane-assisted module,...