Open Access. Powered by Scholars. Published by Universities.®

Discipline
Institution
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 8191 - 8220 of 11334

Full-Text Articles in Artificial Intelligence and Robotics

Scalable Multi-Agent Reinforcement Learning For Aggregation Systems, Tanvi Verma Jun 2020

Scalable Multi-Agent Reinforcement Learning For Aggregation Systems, Tanvi Verma

Dissertations and Theses Collection (Open Access)

Efficient sequential matching of supply and demand is a problem of interest in many online to offline services. For instance, Uber, Lyft, Grab for matching taxis to customers; Ubereats, Deliveroo, FoodPanda etc. for matching restaurants to customers. In these systems, a centralized entity (e.g., Uber) aggregates supply and assigns them to demand so as to optimize a central metric such as profit, number of requests, delay etc. However, individuals (e.g., drivers, delivery boys) in the system are self interested and they try to maximize their own long term profit. The central entity has the full view of the system and …


Online Spatio - Temporal Demand Supply Matching, Meghna Lowalekar Jun 2020

Online Spatio - Temporal Demand Supply Matching, Meghna Lowalekar

Dissertations and Theses Collection (Open Access)

The rapid growth of cities in developing world coupled with the increase in rural to urban migration have led to cities being identified as the key actor for any nation's economy. Shared mobility has become an integral part of life of people in cities as it improves efficiency and enhances transportation accessibility. As a result, the mismatch between the demand and supply of shared mobility resources has a direct impact on people's life. Thus, the goal of my dissertation is to develop solution strategies for these real-time (online) spatio-temporal demand supply matching problems for shared mobility resources which can enhance …


Visual Commonsense R-Cnn, Tan Wang, Jianqiang Huang, Hanwang Zhang, Qianru Sun Jun 2020

Visual Commonsense R-Cnn, Tan Wang, Jianqiang Huang, Hanwang Zhang, Qianru Sun

Research Collection School Of Computing and Information Systems

We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual region encoder for high-level tasks such as captioning and VQA. Given a set of detected object regions in an image (e.g., using Faster R-CNN), like any other unsupervised feature learning methods (e.g., word2vec), the proxy training objective of VC R-CNN is to predict the contextual objects of a region. However, they are fundamentally different: the prediction of VC R-CNN is by using causal intervention: P(Y|do(X)), while others are by using the conventional likelihood: P(Y|X). This is also …


What Do Undergraduate Engineering Students And Preservice Teachers Learn By Collaborating And Teaching Engineering And Coding Through Robotics?, Jennifer Jill Kidd, Krishnanand Kaipa, Samuel J. Jacks, Stacie I. Ringleb, Pilar Pazos, Kristie Gutierrez, Orlando M. Ayala, Lillian Maria De Souza Almeida Jun 2020

What Do Undergraduate Engineering Students And Preservice Teachers Learn By Collaborating And Teaching Engineering And Coding Through Robotics?, Jennifer Jill Kidd, Krishnanand Kaipa, Samuel J. Jacks, Stacie I. Ringleb, Pilar Pazos, Kristie Gutierrez, Orlando M. Ayala, Lillian Maria De Souza Almeida

Teaching & Learning Faculty Publications

This research paper presents preliminary results of an NSF-supported interdisciplinary collaboration between undergraduate engineering students and preservice teachers. The fields of engineering and elementary education share similar challenges when it comes to preparing undergraduate students for the new demands they will encounter in their profession. Engineering students need interprofessional skills that will help them value and negotiate the contributions of various disciplines while working on problems that require a multidisciplinary approach. Increasingly, the solutions to today's complex problems must integrate knowledge and practices from multiple disciplines and engineers must be able to recognize when expertise from outside their field can …


Monte Carlo Tree Search Applied To A Modified Pursuit/Evasion Scotland Yard Game With Rendezvous Spaceflight Operation Applications, Joshua A. Daughtery Jun 2020

Monte Carlo Tree Search Applied To A Modified Pursuit/Evasion Scotland Yard Game With Rendezvous Spaceflight Operation Applications, Joshua A. Daughtery

Theses and Dissertations

This thesis takes the Scotland Yard board game and modifies its rules to mimic important aspects of space in order to facilitate the creation of artificial intelligence for space asset pursuit/evasion scenarios. Space has become a physical warfighting domain. To combat threats, an understanding of the tactics, techniques, and procedures must be captured and studied. Games and simulations are effective tools to capture data lacking historical context. Artificial intelligence and machine learning models can use simulations to develop proper defensive and offensive tactics, techniques, and procedures capable of protecting systems against potential threats. Monte Carlo Tree Search is a bandit-based …


Vision And Sensor-Based Signer-Independent Framework For Arabic Sign Language Recognition, Al-Shamayleh Ahmad Sami Abd Alkareem Jun 2020

Vision And Sensor-Based Signer-Independent Framework For Arabic Sign Language Recognition, Al-Shamayleh Ahmad Sami Abd Alkareem

Student Works (2020-2029)

Hearing and speech-impairment disability is widespread throughout the world. At present, 15 million people have this disability in the Arab world, and about 86% of them come from low- and middle-income countries. Meanwhile, sign language (SL) can be classified into standard Arabic sign language (ArSL) and local Arabic sign language (LArSL). ArSL is the formal standard and is the more acceptable SL in the Arab world; it is also considered as the medium of instructions for schools and universities as well as television news, shows and programmes. With the absence of usable ArSL recognition (ArSLR) platforms, hearing- and speech-impaired people …


Using Generative Adversarial Networks To Classify Structural Damage Caused By Earthquakes, Gian P. Delacruz Jun 2020

Using Generative Adversarial Networks To Classify Structural Damage Caused By Earthquakes, Gian P. Delacruz

Master's Theses

The amount of structural damage image data produced in the aftermath of an earthquake can be staggering. It is challenging for a few human volunteers to efficiently filter and tag these images with meaningful damage information. There are several solution to automate post-earthquake reconnaissance image tagging using Machine Learning (ML) solutions to classify each occurrence of damage per building material and structural member type. ML algorithms are data driven; improving with increased training data. Thanks to the vast amount of data available and advances in computer architectures, ML and in particular Deep Learning (DL) has become one of the most …


Simulation Modeling Method Of Distributed Supply Chain Based On Has, Wang Jian, Huang Yang Jun 2020

Simulation Modeling Method Of Distributed Supply Chain Based On Has, Wang Jian, Huang Yang

Journal of System Simulation

Abstract: There are some shortcomings in simulation modeling method of distributed supply chain based on High Level Architecture (HLA) and Supply Chain Operation Reference (SCOR), which result in low development efficiency of system simulation modeling and low reusability of simulation objects inside the federates. To solve the problems, a simulation modeling method of distributed supply chain based on HAS(HLA-Agent-SCOR) was put forward. The supply chain structure modeling based on HLA for building structure model of supply chain was discussed. Modeling of Agent blocks integrating processes from SCOR and modeling of federates based on Agent were illustrated to create model of …


Multi-Robots Global Path Planning Based On Pso Algorithm And Cubic Spline, Qiang Ning, Gao Jie, Fengju Kang Jun 2020

Multi-Robots Global Path Planning Based On Pso Algorithm And Cubic Spline, Qiang Ning, Gao Jie, Fengju Kang

Journal of System Simulation

Abstract: There are shortcomings such as premature convergence, high encoding dimension and unsmooth path for particle swarm optimization (PSO) algorithm to solve the robot path planning problem under free space. The particle coding is coordinates of several path nodes in the environment. The number of spline curves and the maximum turnings of path were determined by the number of path nodes. The cubic spline function was used to interpolate on the path of the starting point, path nodes and target point, thus a full path which was formed by connecting all interpolation points was obtained. Simulation results show that …


Improved Marching Cubes Algorithmand Its Three-Dimensional Meteorological Simulation, Shuoben Bi, Lu Yuan, Xiaowen Zeng, Mingyue Lu, Yonghua Zhang Jun 2020

Improved Marching Cubes Algorithmand Its Three-Dimensional Meteorological Simulation, Shuoben Bi, Lu Yuan, Xiaowen Zeng, Mingyue Lu, Yonghua Zhang

Journal of System Simulation

Abstract: Methodof obtaining intersection points of isosurface and vowex by linear interpolation in original Marching Cubes algorithm has been replaced by the method of trisecting element boundaries. The problem of linear interpolation not suitable for meteorological data simulation is therefore solved and the number of triangular facets in isosurfacemapping is effectively reduced. While reducing redundancy and improving mapping speed, the quality of isosurface mapping is further improved. The improved Marching Cubes algorithm is applied to the simulation of meteorological model data, i.e., the isosurface of WRF data, and good results are obtained in both the speed of image rendering and …


Trajectory Capture And Sway Frequency Analysis Of Trees Based On Kinect, He Peng, Shaojun Hu, Dongjian He Jun 2020

Trajectory Capture And Sway Frequency Analysis Of Trees Based On Kinect, He Peng, Shaojun Hu, Dongjian He

Journal of System Simulation

Abstract: The morphology and structure of plants were complex. It is of great significance to investigate the inherent motion law of plants under the action of external force, such as realistic animation formation, plant pruning, vibration picking and forest protection. A low cost outdoor tree complex motion capture method was explored, and the relationship between the stem motion and the external force was analyzed. The Kinect was used to capture the branches motion; MeanShift algorithm was used for tracking branches markers and the three-dimensional trajectory of the trunk was extracted according to the principle of Kinect coordinate transformation. A method …


Realistic Real-Time Road Rendering Technology Based On Road Boundaryalpha-Map, Jinlian Du, Shang Xin, Fengchao Zhao Jun 2020

Realistic Real-Time Road Rendering Technology Based On Road Boundaryalpha-Map, Jinlian Du, Shang Xin, Fengchao Zhao

Journal of System Simulation

Abstract: A method of realistic real-time rendering based on road boundary alpha-map was proposed to eliminate the blur and aliasing issues produced by traditional rendering method based on buffer mechanism. In the method, the road was generated by buffer mechanism based on grid model of terrain, and the road's borders were constructed by analyzing the characteristics of road boundary grids. Based on these, three types of road boundary alpha-maps were designed for producing the road borders with realistic visual effects. Experiment shows that the method can improve the rendering realism of the road borders than traditional method. Another advantage of …


Simulation On Psychosocial Adaption Of Urban New Migrants Based On Catastrophe Theory, Zhao Xu, Chuanchao Huang, Bin Hu Jun 2020

Simulation On Psychosocial Adaption Of Urban New Migrants Based On Catastrophe Theory, Zhao Xu, Chuanchao Huang, Bin Hu

Journal of System Simulation

Abstract: Based on the mental recovery and adaptive behavior translation of the new urban migrants, a two system decision-making model for psychological adaption was built. The simulation research of psychosocial adaption process was studied through the stochastic catastrophe theory and the specific artificial social environment. Simulation experiments indicate that the sustained pressure-bearing suffers from outside situation and the policy system result in the fluctuation of migrants' psychosocial adaption with the former more significant. In the translation of adaptive psychology to adaptive behavior, the attitude orientation and psychological cognition of migrants are critical. The duration or degree of the adaptive process …


Multiple Faults Identification Of Three-Level Inverter, Yanxia Shen, Wu Juan, Zhipu Zhao, Zhicheng Ji Jun 2020

Multiple Faults Identification Of Three-Level Inverter, Yanxia Shen, Wu Juan, Zhipu Zhao, Zhicheng Ji

Journal of System Simulation

Abstract: A three-level neutral point clamped (NPC) inverter was taken as an example, phase current and bridge voltage in the fault states of single switch open and several switches open at the same time were analyzed, and a method based on reconstructive phase space (RPS) and wavelet packet analysis was proposed to identify three-level inverter faults. Based on RPS method, totally different reconstructed current trajectories were obtained, which showed the features of the inverter under different fault conditions. With the help of image processing technology, all kinds of faults with different phase currents were identified. The wavelet packet analysis was …


Simulation Of Joint Power Control Routing Algorithm For Interference And Energy Consumption In Crahns, Zhufang Kuang, Zhigang Chen Jun 2020

Simulation Of Joint Power Control Routing Algorithm For Interference And Energy Consumption In Crahns, Zhufang Kuang, Zhigang Chen

Journal of System Simulation

Abstract: Problems of interference power to primary user by secondary userand the secondary user's running out of energy under underlay spectrum access model in cognitive radio ad hoc networks (CRAHNs) were investigated. Joint power control, routing and spectrum (channel) allocation algorithm (PRSA) based on particle swarm optimization were proposed. The goal of PRSA was to minimize interference power to primary user and prolong lifetime of CRAHNs. Particle encoding, particle initialization, fitness function, particle flight were included in PRSA. An Adjacency matrix with two-tuples containing allocated channel and power level was designed, and three operation rules for particle were redefined. …


Improved Design Scheme And Simulation Analysis Of Non-Valve Controlled Hydraulic Impact System, Liu Zhong, Zou Yu, Zhang Kai, Zhao Fei, Junjun Liu Jun 2020

Improved Design Scheme And Simulation Analysis Of Non-Valve Controlled Hydraulic Impact System, Liu Zhong, Zou Yu, Zhang Kai, Zhao Fei, Junjun Liu

Journal of System Simulation

Abstract: Due to valve port commutation of traditional hydraulic impact system caused valve leakage. For the above shortcomings, an improved structure principle of the new type of non-valve controlled hydraulic impact system was proposed establishing dynamic equations of impact system andconducting simulation analysis based on AMESim. Due to the simulation results which was inconsistent with design goal, two improvement schemes were proposed adding throttle device and controlling inlet and outlet circuit. The simulation results suggest that the working performance of impact system has been improved by adding throttle device, and its efficiency has been increased from 11.8% to 18.3% …


Study Of Model Predictive Control Of Pwm Voltage Source Converterwithout Ac Electromotive Force Sensor, Li Hui, Li Zhi, Zhang Jin, Hanmei Peng Jun 2020

Study Of Model Predictive Control Of Pwm Voltage Source Converterwithout Ac Electromotive Force Sensor, Li Hui, Li Zhi, Zhang Jin, Hanmei Peng

Journal of System Simulation

Abstract: The traditional model-predictive-control (MPC), applied to three-phase converter, requires to use AC electromotive force sensor, and then it reduces the system reliability. A three-phase converter model predictive control without AC electromotive force sensor was proposed, and the virtual flux observer was constructed by DC bus voltage, switching signal and AC current. On this basis, a mathematical model of three-phase converter model predictive control quadratic programming (QP-MPC) based on virtual flux oriented was established. Using quadratic programming algorithm, the system can quickly calculate the optimal change, minimize the objective function, and obtain the optimal switch control signal, so as to …


Under-Determined Blind Source Separation Anti-Collision Algorithm For Rfid Based On Hamming Weight Grouping, Yungang Jin, Xiaohong Zhang, Qiuli Wang Jun 2020

Under-Determined Blind Source Separation Anti-Collision Algorithm For Rfid Based On Hamming Weight Grouping, Yungang Jin, Xiaohong Zhang, Qiuli Wang

Journal of System Simulation

Abstract: The results of the algorithm ofunder-determined blind source separation RFID (Radio Frequency IDentification) system become worse or even lead to the degradation of overall system performancewith the large increase in the number of tags. Anovel parallelizable identification anti-collision algorithm based on constrained non negative matrix factorization (NMF) and Hamming weight grouping technology was proposed. The tag groupings were made by calculating the Hamming weight of the tag's front M bits, which were within the reader identification range. Each group was identified by the RFID reader according to the grouping sequence. Simulation results show that when the antenna number is …


Inertia Effect In Dynamic Tensile Tests Of Concrete-Like Materials, Zhang Shu, Yubin Lu, Dongmei Zhao, Chen Xing Jun 2020

Inertia Effect In Dynamic Tensile Tests Of Concrete-Like Materials, Zhang Shu, Yubin Lu, Dongmei Zhao, Chen Xing

Journal of System Simulation

Abstract: The different understanding on the influential degree of the inertial effect does exist among researchers, and it has not been uniformly defined in dynamic tensile tests. The finite element numerical simulation method was employed to analyze the three typical dynamic tensile tests, without considering the real strain-rate effect in these models, where a constitutive model only considered the influence of hydrostatic pressure was used for modeling the specimen in these models. It is found that the dynamic tensile strength of concrete specimens in the three models mentioned is strengthened with the increase of loading strain-rate, owing to the …


Fluid Flow, Heat And Mass Transfer In Hot Dip Galvanizing Bath, Shouqun Sun, Zhongshuang Wei, Huayang Lu Jun 2020

Fluid Flow, Heat And Mass Transfer In Hot Dip Galvanizing Bath, Shouqun Sun, Zhongshuang Wei, Huayang Lu

Journal of System Simulation

Abstract: Zinc dross is produced inevitably as a metallurgical phenomenon of continuous hot galvanizing process, and the quality of galvanizing is affected. The phenomenon is closely related to the physical field of molten zinc and more surface defects are easily produced if the zinc dross removal process is improperly handled. By constructing a three-dimensional viscous standard k-ε two equation turbulence model, the fluid flow, heat and mass transfer law and the distribution regularities of flow vortex were obtained under the specific initial conditions and boundary conditions. The simulation results of the observation points are basically in agreement with the experimental …


Rtds Simulation Of Quasi-Proportional Resonant Control Of Statcom Under High Voltage, Zhang Yang, Xiaopin Yang Jun 2020

Rtds Simulation Of Quasi-Proportional Resonant Control Of Statcom Under High Voltage, Zhang Yang, Xiaopin Yang

Journal of System Simulation

Abstract: ±100 MVar high voltage static synchronous compensator (STATCOM) device is used for high voltage DC transmission which needs higher reliability. Faster response for its control system to deal with metal ground fault and other situations is required. Direct Current Control (DCC) can be used for these situations. Quasi- Proportional Resonant (quasi-PR) controller under DCC was studied and its parameters settings were discussed. The calculation methods of key parameters such as Kp and Kr were explained by mathematical deduction process. The STATCOM under higher voltage in Yunnan-Guangxi Funing transaction station was taken as an example for the calculation …


Simulation Of Adaptive Dangerous Weather Warning Method Based On Airborne Weather Radar, Wang Lei, Xingang Liu, Wei Ming Jun 2020

Simulation Of Adaptive Dangerous Weather Warning Method Based On Airborne Weather Radar, Wang Lei, Xingang Liu, Wei Ming

Journal of System Simulation

Abstract: A kind of suitable airborne weather radar algorithm for different seasons, latitude and longitude and underlying surface in China was proposed. A simulation model of airborne weather radar for detecting strong storm weather based on the ground-based weather radar data was established. The improved algorithm of region segmentation and TITAN were used to identify strong storms and their characteristic parameters. China was divided into 16 climate characteristic regions (including East China Sea and South China Sea) per the latitude and longitude. The threshold of strong hail storm radar echo characteristic parameters in these areas was obtained, and the dangerous …


Meteorological Service Federate Design And Realization Based On Hla, Yintian Liu, Xiaodong Wang, Zaikui Wang Jun 2020

Meteorological Service Federate Design And Realization Based On Hla, Yintian Liu, Xiaodong Wang, Zaikui Wang

Journal of System Simulation

Abstract: To increase flight safety and flight experience under special weather phenomena, the diversity and typical cases of special weather conditions should be considered in flight simulation training, the dynamic and successive meteorological data should be studied, and the insufficient of meteorological services should be overcome by comparing with the traditional flight simulator. The meteorological service with the generation model of multiple size of template library for typical special weather, the dynamical deduction model of meteorological data, and the interpolation calculation model of meteorological grid-point data were proposed. The meteorological service federate based on High Level Architecture (HLA) was established. …


Weld Trajectory Measurement Based On Stripe Type Laser Sensor, Li Lin, Weijie Chen, Yanbiao Zou Jun 2020

Weld Trajectory Measurement Based On Stripe Type Laser Sensor, Li Lin, Weijie Chen, Yanbiao Zou

Journal of System Simulation

Abstract: Teaching and playback are usually used on welding robot to weld a part. To make sure the implementation of this mode, it is needed to locate the part using artificial sport welding in the front process, which could cause location error and make the actual track deviate from the teaching track. A welding track offline detection device using stripe type laser sensor was proposed for solving the problem. The laser sensor was mounted at the end of the robot. The robot moved along the weld trajectory before welding. The information of the weld track section was gotten and the …


Simulation On Global Demand Information Sharing Value In B2b Supply Chain, Dongbo Hu, Shen Yue, Rudan Heng, Binbin Zhang Jun 2020

Simulation On Global Demand Information Sharing Value In B2b Supply Chain, Dongbo Hu, Shen Yue, Rudan Heng, Binbin Zhang

Journal of System Simulation

Abstract: In B2B e-commerce environment, a multi-agent simulation model based on the supply chain with multi suppliers was established to study the incentive effects of the global demand information sharing on suppliers and the effects of different parameters on these incentive effects. The research results are as follows: Compared with the local demand information sharing, the global demand information sharing can bring significant incentive effect to the supplier. The global demand information sharing is more valuable with the number of selected suppliers getting closer to the number of alternative suppliers, and an optimal number of alternative suppliers do exist. Based …


Novel Power Control Algorithm For Cognitive Radio Network, Long Min, Juanjuan Lei Jun 2020

Novel Power Control Algorithm For Cognitive Radio Network, Long Min, Juanjuan Lei

Journal of System Simulation

Abstract: For the problems of near-far effect, large path loss, and stability of algorithm, etc., in the cognitive radio, a new power control algorithm was proposed. Utility function was improved effectively, where punishment factors, such as, link quality and the interference capacity limit of the primary users (PUs) were considered. Signal-to-interference radio (SINR) of cognitive users (CUs) was controlled above the minimum threshold, and the interference value of the CUs was controlled below the capacity tolerance of PUs. The existence of Nash equilibrium was given. Simulation results show that the new algorithm has better stability; the loss of path …


Research On Feedback Compensation Control For Aircraft Electric Antiskid Brake System Based On Il, Gao Jie, Gao Bing, Jianying Liu Jun 2020

Research On Feedback Compensation Control For Aircraft Electric Antiskid Brake System Based On Il, Gao Jie, Gao Bing, Jianying Liu

Journal of System Simulation

Abstract: Safety, efficiency and comfort of aircraft are all determined by antiskid braking system. Because of the problem of inadequate control in the anti-skid braking system, the nonlinear model of the aircraft electric braking system was built by the analysis of aircraft landing process, and the iterative learning algorithm was introduced for reciprocating characteristics of anti-skid control. The groups in different speeds and road conditions were trained using the PD type learning rate. The knowledge base on the relationship among the optimal slip ratio and velocity and road conditions was built. The feed-forward control knowledge system for identifying the different …


Survey Of Studies On Numerical Simulations Of Optical-Wave Propagation In Atmospheric Turbulence, Bin Ren, Chunyi Chen, Huamin Yang Jun 2020

Survey Of Studies On Numerical Simulations Of Optical-Wave Propagation In Atmospheric Turbulence, Bin Ren, Chunyi Chen, Huamin Yang

Journal of System Simulation

Abstract: The complicated random behavior of atmospheric turbulence makes it difficult to verify the theories of optical-wave propagation in atmospheric turbulence by conducting experimental measurements. The parameters used in numerical simulations can be easily controlled; therefore numerical simulations have been used as another important tool to investigate the optical-wave propagation in atmospheric turbulence. Based on the existing literature, both the theoretical models and numerical generating methods for random phase screens of atmospheric turbulence are surveyed, and the spatial sampling constraints for numerical simulations of optical propagation in atmospheric turbulence were summarized. By comprehending the existing results, it has been pointed …


Genetic Algorithm For Solving Multi-Objective Dynamic Flexible Job Shop Scheduling, Wang Chun, Zhang Ming, Zhicheng Ji, Wang Yan Jun 2020

Genetic Algorithm For Solving Multi-Objective Dynamic Flexible Job Shop Scheduling, Wang Chun, Zhang Ming, Zhicheng Ji, Wang Yan

Journal of System Simulation

Abstract: To solve the scheduling problem of mold workshop in a toy factory with dynamic and flexible features, a mathematical model was established by introducing virtual operation and virtual working hours. Based on the strategies of periodic scheduling combined with dynamic event scheduling as well as the rolling window scheduling operation technology, dynamic scheduling was transformed into several continuous static scheduling windows, under which multi-objective genetic algorithm was used to solve the model. The priority of operation scheduling was given in different dynamic events. In addition, the encoding and anti-encoding of chromosome's operation sequence were made based on the proposed …


Fast Tree Modeling Method Based On Simple Freehand Sketch, Ma Ling, Xiaoping Liu, Xiaoping Liu Jun 2020

Fast Tree Modeling Method Based On Simple Freehand Sketch, Ma Ling, Xiaoping Liu, Xiaoping Liu

Journal of System Simulation

Abstract: Aiming at problems such as complicated process and professional knowledge requirements in tree modeling, a quick tree modeling method for non-experts was proposed, combining branch library with simple sketch to make non-experts create tree model quickly. The method preprocessed the sketch to eliminate noise and error points and identify the strokes, the trunk and branch were reconstructed, child three-dimensional profile was built through the two-dimensional canopy profile, under the constraint of the child profile, suitable branches from library and insert were extracted into the branches, consequently the whole tree model was completed. Experimental results show that this method …