• Title/Summary/Keyword: Convergence Approach

Search Result 2,187, Processing Time 0.031 seconds

Development of 3D Crop Segmentation Model in Open-field Based on Supervised Machine Learning Algorithm (지도학습 알고리즘 기반 3D 노지 작물 구분 모델 개발)

  • Jeong, Young-Joon;Lee, Jong-Hyuk;Lee, Sang-Ik;Oh, Bu-Yeong;Ahmed, Fawzy;Seo, Byung-Hun;Kim, Dong-Su;Seo, Ye-Jin;Choi, Won
    • Journal of The Korean Society of Agricultural Engineers
    • /
    • v.64 no.1
    • /
    • pp.15-26
    • /
    • 2022
  • 3D open-field farm model developed from UAV (Unmanned Aerial Vehicle) data could make crop monitoring easier, also could be an important dataset for various fields like remote sensing or precision agriculture. It is essential to separate crops from the non-crop area because labeling in a manual way is extremely laborious and not appropriate for continuous monitoring. We, therefore, made a 3D open-field farm model based on UAV images and developed a crop segmentation model using a supervised machine learning algorithm. We compared performances from various models using different data features like color or geographic coordinates, and two supervised learning algorithms which are SVM (Support Vector Machine) and KNN (K-Nearest Neighbors). The best approach was trained with 2-dimensional data, ExGR (Excess of Green minus Excess of Red) and z coordinate value, using KNN algorithm, whose accuracy, precision, recall, F1 score was 97.85, 96.51, 88.54, 92.35% respectively. Also, we compared our model performance with similar previous work. Our approach showed slightly better accuracy, and it detected the actual crop better than the previous approach, while it also classified actual non-crop points (e.g. weeds) as crops.

Improved Dynamic Window Approach With Path-Following for Unmanned Surface Vehicle (무인수상정을 위한 경로선 추종이 가능한 개선된 Dynamic Window Approach)

  • Kim, Hyogon;Yun, Sung-Jo;Choi, Young-Ho;Lee, Jung-Woo;Ryu, Jae-KWan;Won, Byong-Jae;Suh, Jin-Ho
    • IEMEK Journal of Embedded Systems and Applications
    • /
    • v.12 no.5
    • /
    • pp.295-301
    • /
    • 2017
  • Recently, autonomous navigation technology, obstacle recognition, and obstacle collision avoidance technology are actively being developed for an unmanned surface vehicle (USV). The path to move from the current location to the destination should be planned, in order for an USV to autonomously operate safely to its destination. The dynamic window approach (DWA) is a well-known navigation scheme as a local path planning. The DWA algorithm derives the linear velocity and angular velocity by evaluating the destination direction, velocity, and distance from the obstacle. However, because DWA algorithm does not consider tracking the path, when using only the DWA algorithm, the ship may navigate away from the path line after avoiding obstacles. In this paper, we propose an improved DWA algorithm that can follow path line. And we implemented the simulation and compared the existing DWA algorithm with the improved DWA algorithm proposed in this paper. As a result, it is confirmed that the proposed DWA algorithm follows the path line better.

Perception and action: Approach to convergence on embodied cognition (지각과 행위: 체화된 인지와의 융복합적 접근)

  • Lee, Young-Lim
    • Journal of Digital Convergence
    • /
    • v.14 no.8
    • /
    • pp.555-564
    • /
    • 2016
  • Space perception is generally treated as a problem relevant to the ability to recognize objects. Alternatively, the data from shape perception studies contributes to discussions about the geometry of visual space. This geometry is generally acknowledged not to be Euclidian, but instead, elliptical, hyperbolic or affine, which is to say, something that admits the distortions found in so many shape perception studies. The purpose of this review article is to understand perceived shape and the geometry of visual space in the context of visually guided action. Thus, two prominent approaches that explain the relation between perception and action were compared. It is important to understand the fundamental information of how human perceive visual space and perform visually guided action for the convergence on embodied cognition, and further on artificial intelligence researches.

Nonlinear Identification of Electronic Brake Pedal Behavior Using Hybrid GMDH and Genetic Algorithm in Brake-By-Wire System

  • Bae, Junhyung;Lee, Seonghun;Shin, Dong-Hwan;Hong, Jaeseung;Lee, Jaeseong;Kim, Jong-Hae
    • Journal of Electrical Engineering and Technology
    • /
    • v.12 no.3
    • /
    • pp.1292-1298
    • /
    • 2017
  • In this paper, we represent a nonlinear identification of electronic brake pedal behavior in the brake-by-wire (BBW) system based on hybrid group method of data handling (GMDH) and genetic algorithm (GA). A GMDH is a kind of multi-layer network with a structure that is determined through training and which can express nonlinear dynamics as a mathematical model. The GA is used in the GMDH, enabling each neuron to search for its optimal set of connections with the preceding layer. The results obtained with this hybrid approach were compared with different nonlinear system identification methods. The experimental results showed that the hybrid approach performs better than the other methods in terms of root mean square error (RMSE) and correlation coefficients. The hybrid GMDH/GA approach was effective for modeling and predicting the brake pedal system under random braking conditions.

Development of Localization using Artificial and Natural Landmark for Indoor Mobile Robots (실내 이동 로봇을 위한 자연 표식과 인공 표식을 혼합한 위치 추정 기법 개발)

  • Ahn, Joonwoo;Shin, Seho;Park, Jaeheung
    • The Journal of Korea Robotics Society
    • /
    • v.11 no.4
    • /
    • pp.205-216
    • /
    • 2016
  • The localization of the robot is one of the most important factors of navigating mobile robots. The use of featured information of landmarks is one approach to estimate the location of the robot. This approach can be classified into two categories: the natural-landmark-based and artificial-landmark-based approach. Natural landmarks are suitable for any environment, but they may not be sufficient for localization in the less featured or dynamic environment. On the other hand, artificial landmarks may generate shaded areas due to space constraints. In order to improve these disadvantages, this paper presents a novel development of the localization system by using artificial and natural-landmarks-based approach on a topological map. The proposed localization system can recognize far or near landmarks without any distortion by using landmark tracking system based on top-view image transform. The camera is rotated by distance of landmark. The experiment shows a result of performing position recognition without shading section by applying the proposed system with a small number of artificial landmarks in the mobile robot.

Real-Time License Plate Detection in High-Resolution Videos Using Fastest Available Cascade Classifier and Core Patterns

  • Han, Byung-Gil;Lee, Jong Taek;Lim, Kil-Taek;Chung, Yunsu
    • ETRI Journal
    • /
    • v.37 no.2
    • /
    • pp.251-261
    • /
    • 2015
  • We present a novel method for real-time automatic license plate detection in high-resolution videos. Although there have been extensive studies of license plate detection since the 1970s, the suggested approaches resulting from such studies have difficulties in processing high-resolution imagery in real-time. Herein, we propose a novel cascade structure, the fastest classifier available, by rejecting false positives most efficiently. Furthermore, we train the classifier using the core patterns of various types of license plates, improving both the computation load and the accuracy of license plate detection. To show its superiority, our approach is compared with other state-of-the-art approaches. In addition, we collected 20,000 images including license plates from real traffic scenes for comprehensive experiments. The results show that our proposed approach significantly reduces the computational load in comparison to the other state-of-the-art approaches, with comparable performance accuracy.

Design of Spiral Spring in Sliding Mechanism for Mobile Phones Using Axiomatic Design (공리적설계를 이용한 휴대폰 슬라이드 기구의 스파이럴 스프링 설계)

  • Hwang, Eun-Ha;Han, Deok-Hee
    • Journal of the Korean Society of Industry Convergence
    • /
    • v.10 no.3
    • /
    • pp.171-177
    • /
    • 2007
  • It is well known that mobile phones have been a indispensable communication tool for human life. The spiral springs are used as the main component of the semi-auto sliding mechanism of mobile phones. The characteristic of axiomatic approach is scientific and analytical method, and axiomatic approach is different from other design methods in offering the systematic method at an early stage of design. The axiomatic approach could determine design parameter and arrange the order of design and estimate the optimum design in good order. In axiomatic approach, the composition is divided by customer requirement, functional requirement, design parameter, and design matrix in large portion. This paper presents design in sliding mechanism for mobile phones by finite element method and axiomatic design.

  • PDF

Emotion Recognition based on Multiple Modalities

  • Kim, Dong-Ju;Lee, Hyeon-Gu;Hong, Kwang-Seok
    • Journal of the Institute of Convergence Signal Processing
    • /
    • v.12 no.4
    • /
    • pp.228-236
    • /
    • 2011
  • Emotion recognition plays an important role in the research area of human-computer interaction, and it allows a more natural and more human-like communication between humans and computer. Most of previous work on emotion recognition focused on extracting emotions from face, speech or EEG information separately. Therefore, a novel approach is presented in this paper, including face, speech and EEG, to recognize the human emotion. The individual matching scores obtained from face, speech, and EEG are combined using a weighted-summation operation, and the fused-score is utilized to classify the human emotion. In the experiment results, the proposed approach gives an improvement of more than 18.64% when compared to the most successful unimodal approach, and also provides better performance compared to approaches integrating two modalities each other. From these results, we confirmed that the proposed approach achieved a significant performance improvement and the proposed method was very effective.

Simulation for Flexibility of Flexible Job Shop Scheduling (유연 Job Shop 일정계획의 유연성에 대한 시뮬레이션)

  • Kim, Sang-Cheon;Kim, Jung-Ja;Lee, Sang-Wan;Lee, Sung-Woo
    • Journal of the Korean Society of Industry Convergence
    • /
    • v.4 no.3
    • /
    • pp.281-287
    • /
    • 2001
  • Traditional job shop scheduling is supposed that machine has a fixed processing job type. But actually the machine has a highly utilization or long processing time is occurred delay. Therefore product system is difficult to respond quickly to the change of products or loads or machine failure etc. Here we use flexible job shop which is supposed that a machine has several jobs by tool change. The heuristic for the flexible job shop scheduling has to solve two problems. One is a routing problem which is determine a machine to process job. The other is sequencing problem which is determine processing sequence. The approach to solve two problems arc a hierarchical approach which is determined routing and then schedule, and a concurrence approach which is solved concurrently two problems by considering routing when it is scheduled. In this study, we simulate for flexibility efficiency fo flexible job shop scheduling with machine failure using hierarchical approach.

  • PDF

A Study on Modeling Tool for Convergence of Smart Appliances (스마트 기기의 컨버전스를 위한 모델링 도구에 관한 연구)

  • Son, Hyun Seung;Kim, Woo Yeol;Kim, R. Young Chul
    • The Journal of the Institute of Internet, Broadcasting and Communication
    • /
    • v.8 no.4
    • /
    • pp.119-125
    • /
    • 2008
  • The traditional way for convergence of smart appliances was software integrations on middleware. It is possible advantage to integrate easily and quickly with this way. But basically the middleware approach is slowly executed as it is huge the size of software. To solve this problem, we suggest a modeling tool for convergence. As we can execute and generate the automatic source code at the design phase with our modeling tool, it is possible to do software integration without the middleware. We use one example of U-Home environment to show the convergence for TV and the door lock system. With our approach, we will be able quickly to develop the convergent products what the customers desire with inexpensiveness, that is, the convergence of smart appliances without the middleware.

  • PDF