• Title/Summary/Keyword: top-down

Search Result 1,116, Processing Time 0.023 seconds

Comparison of Deep Learning Based Pose Detection Models to Detect Fall of Workers in Underground Utility Tunnels (딥러닝 자세 추정 모델을 이용한 지하공동구 다중 작업자 낙상 검출 모델 비교)

  • Jeongsoo Kim
    • Journal of the Society of Disaster Information
    • /
    • v.20 no.2
    • /
    • pp.302-314
    • /
    • 2024

  • Purpose: This study proposes a fall detection model based on a top-down deep learning pose estimation model to automatically determine falls of multiple workers in an underground utility tunnel, and evaluates the performance of the proposed model. Method: A model is presented that combines fall discrimination rules with the results inferred from YOLOv8-pose, one of the top-down pose estimation models, and metrics of the model are evaluated for images of standing and falling two or fewer workers in the tunnel. The same process is also conducted for a bottom-up type of pose estimation model (OpenPose). In addition, due to dependency of the falling interference of the models on worker detection by YOLOv8-pose and OpenPose, metrics of the models for fall was not only investigated, but also for person. Result: For worker detection, both YOLOv8-pose and OpenPose models have F1-score of 0.88 and 0.71, respectively. However, for fall detection, the metrics were deteriorated to 0.71 and 0.23. The results of the OpenPose based model were due to partially detected worker body, and detected workers but fail to part them correctly. Conclusion: Use of top-down type of pose estimation models would be more effective way to detect fall of workers in the underground utility tunnel, with respect to joint recognition and partition between workers.

  • https://doi.org/10.15683/kosdi.2024.6.30.302 인용 PDF HTML

A Study on the Development of Computer Aided Design System for Fixed Offshore Structures (고정식 해양구조물의 전산기 지원 설계시스템 개발에 관한 연구)

  • Sin, Hyeon-Gyeong;Park, Gyu-Won
    • Journal of Ocean Engineering and Technology
    • /
    • v.9 no.2
    • /
    • pp.83-88
    • /
    • 1995

  • In this paper, the solid modeller suitable for PC was developed for Top-down 3-D representation and analysis of fixed offshore structures. Also solid modelling and hidden line removal were conducted in order to visualize the offshore structures based on the scan line z-buffer algorithm.

  • PDF

A Study on Strenth of Top-Down concrete on placing ways of kind (타설법에 따른 역타콘크리트의 강도에 관한 연구)

  • 이영도;윤상혁;정근호;정상진
    • Proceedings of the Korean Institute of Building Construction Conference
    • /
    • 2002.05a
    • /
    • pp.37-40
    • /
    • 2002

  • The purpose of this study is promote perfect of construction and progress of packing ability through comparison and analysis with quality, as placing ways and placing direction are changed. Kinds of concrete are general, high fluidity, and high Performance concrete. Classified with concrete as placing ways - direct ways, sheath way - and placing directing - flange direction, web direction - is analyzed section and strength of hardened concrete. The results of this study is belows the more fluid of concrete, the more useful to top-down method.

  • PDF

Study on Strength Development of Concrete for Top-Down Method (역타공법에 적용을 위한 콘크리트 강도성상 연구)

  • 정근호;이종균;김영회;이영도;정상진
    • Proceedings of the Korea Concrete Institute Conference
    • /
    • 1998.10c
    • /
    • pp.48-53
    • /
    • 1998

  • The purpose of this study to fine the mixture of concrete for Top-Down method. As a result, In fresh concrete, slump value and slump-flow value were increased as fly ash concrete(10% ratio). When plasticizer was added 1.5% by weigh of binder in concrete, no fly ash concrete and fly ash concrete(10% ratio) all occurred segregation. And, no fly ash concrete and fly concrete(10% ratio) all showed compressive strength development close plain concrete as increasing plasticizer quantity. Especially, in case of 1.5% plasticizer of binder showed high compressive strength development.

  • PDF

A Decision Tree Algorithm using Genetic Programming

  • Park, Chongsun;Ko, Young Kyong
    • Communications for Statistical Applications and Methods
    • /
    • v.10 no.3
    • /
    • pp.845-857
    • /
    • 2003

  • We explore the use of genetic programming to evolve decision trees directly for classification problems with both discrete and continuous predictors. We demonstrate that the derived hypotheses of standard algorithms can substantially deviated from the optimum. This deviation is partly due to their top-down style procedures. The performance of the system is measured on a set of real and simulated data sets and compared with the performance of well-known algorithms like CHAID, CART, C5.0, and QUEST. Proposed algorithm seems to be effective in handling problems caused by top-down style procedures of existing algorithms.

  • https://doi.org/10.5351/CKSS.2003.10.3.845 인용 PDF KSCI

집속이온빔(Focused Ion Beam)을 이용한 3차원 나노가공

  • 박철우;이종항
    • Proceedings of the Korean Society of Precision Engineering Conference
    • /
    • 2004.05a
    • /
    • pp.11-11
    • /
    • 2004

  • 나노기술은 크게 2가지 접근방법을 가진다. 하나는 위에서 아래로(Top-Down)라는 관점으로 벌크물질로부터 이온빔 등을 이용해 이를 작게 잘라가는 방식이며, 다른 하나는 아래에서 위로(Bottom-Up) 방식으로 재질을 구성하는 분자를 재구성해 원하는 물성 및 특성을 가지도록 만드는 방법이다. 이 두 가지 접근 방법은 원하는 결과를 얻기 위해 상호 보완적으로 사용되기도 한다. Top-Down방식의 대표적인 기기로는 접속이온빔 장치(FIB, Focused Ion Beam)를 등 수 있으며, Bottom-Up방식의 대표적인 기기로는 SPM(Scanning Probe Microscope)을 들 수 있다.(중략)

  • PDF