Loading [MathJax]/jax/output/CommonHTML/jax.js
  • Title/Summary/Keyword: Obstacle model

Search Result 339, Processing Time 0.034 seconds

Development of the Algofithm for Gaussian Mixture Models based Traffic Accident Auto-Detection in Freeway (GMM(Gaussian Mixture Model)을 적용한 영상처리기법의 연속류도로 사고 자동검지 알고리즘 개발)

  • O, Ju-Taek;Im, Jae-Geuk;Yeo, Tae-Dong
    • Journal of Korean Society of Transportation
    • /
    • v.28 no.3
    • /
    • pp.169-183
    • /
    • 2010
  • Image-based traffic information collection systems have entered widespread adoption and use in many countries since these systems are not only capable of replacing existing loop-based detectors which have limitations in management and administration, but are also capable of providing and managing a wide variety of traffic related information. In addition, these systems are expanding rapidly in terms of purpose and scope of use. Currently, the utilization of image processing technology in the field of traffic accident management is limited to installing surveillance cameras on locations where traffic accidents are expected to occur and digitalizing of recorded data. Accurately recording the sequence of situations around a traffic accident in a freeway and then objectively and clearly analyzing how such accident occurred is more urgent and important than anything else in resolving a traffic accident. Therefore, in this research, existing technologies, this freeway attribute, velocity changes, volume changes, occupancy changes reflect judge the primary. Furthermore, We pointed out by many past researches while presenting and implementing an active and environmentally adaptive methodology capable of effectively reducing false detection situations which frequently occur even with the Gaussian Mixture model analytical method which has been considered the best among well-known environmental obstacle reduction methods. Therefore, in this way, the accident was the final decision. Also, environmental factors occur frequently, and with the index finger situations, effectively reducing that can actively and environmentally adaptive techniques through accident final judgment. This implementation of the evaluate performance of the experiment road of 12 incidents in simulated and the jang-hang IC's real-time accident experiment. As a result, the do well detection 93.33%, false alarm 6.7% as showed high reliability.

Implementation of AI-based Object Recognition Model for Improving Driving Safety of Electric Mobility Aids (전동 이동 보조기기 주행 안전성 향상을 위한 AI기반 객체 인식 모델의 구현)

  • Je-Seung Woo;Sun-Gi Hong;Jun-Mo Park
    • Journal of the Institute of Convergence Signal Processing
    • /
    • v.23 no.3
    • /
    • pp.166-172
    • /
    • 2022
  • In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

Implementation of AI-based Object Recognition Model for Improving Driving Safety of Electric Mobility Aids (객체 인식 모델과 지면 투영기법을 활용한 영상 내 다중 객체의 위치 보정 알고리즘 구현)

  • Dong-Seok Park;Sun-Gi Hong;Jun-Mo Park
    • Journal of the Institute of Convergence Signal Processing
    • /
    • v.24 no.2
    • /
    • pp.119-125
    • /
    • 2023
  • In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

The Model of Network Packet Analysis based on Big Data (빅 데이터 기반의 네트워크 패킷 분석 모델)

  • Choi, Bomin;Kong, Jong-Hwan;Han, Myung-Mook
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.23 no.5
    • /
    • pp.392-399
    • /
    • 2013
  • Due to the development of IT technology and the information age, a dependency of the network over the most of our lives have grown to a greater extent. Although it provides us to get various useful information and service, it also has negative effectiveness that can provide network intruder with vulnerable roots. In other words, we need to urgently cope with theses serious security problem causing service disableness or system connected to network obstacle with exploiting various packet information. Many experts in a field of security are making an effort to develop the various security solutions to respond against these threats, but existing solutions have a lot of problems such as lack of storage capacity and performance degradation along with the massive increase of packet data volume. Therefore we propose the packet analysis model to apply issuing Big Data technology in the field of security. That is, we used NoSQL which is technology of massive data storage to collect the packet data growing massive and implemented the packet analysis model based on K-means clustering using MapReudce which is distributed programming framework, and then we have shown its high performance by experimenting.

A Study on the Flow Changes around Building Construction Area Using a GIS Data (GIS 자료를 활용한 신축 건물 주변 지역의 흐름 변화 연구)

  • Mun, Da-Som;Kim, Jae-Jin
    • Korean Journal of Remote Sensing
    • /
    • v.34 no.6_1
    • /
    • pp.879-891
    • /
    • 2018
  • In this study, the effects of urban redevelopment and building construction on the change of the detailed flows around the Pukyong National University (PKNU) campus located in the building-congested area was investigated using a CFD (computational fluid dynamics) model and GIS (geographic information system). For the analysis of the detailed flows before and after the constructions of the buildings around and within the campus, numerical simulations for the 16 inflow directions were performed before and after the construction. We used, as reference wind speeds at the inflow boundaries, the averaged wind speeds observed at the Gwangan light beacon (962) where there is no surrounding obstacle (i.e., building and terrain) acting as friction. We analyzed the area fractions in which wind speeds at z = 2.5 m changed after the construction for 16 inflow directions. The area fractions were relatively large in the east-south-easterly and southerly cases, because of the high-rise buildings constructed at the east and the apartment complex and the Engineering buildings constructed at the south of the PKNU campus. In the case of the easterly of which frequency is highest among the wind directions observed at the Daeyeon AWS (AWS 942) located inside the PKNU campus, the wind-speed change was not significant even after the constructions. It is shown that the building construction has affected the detailed flows around as well as even in the far downwind region of the constructed buildings. Also, it is shown that the GIS and CFD model are useful for analyzing the detailed flows in planning the urban redevelopment and/or building construction.

Investigating meso-scale low-temperature fracture mechanisms of recycled asphalt concrete (RAC) via peridynamics

  • Yuanjie Xiao;Ke Hou;Wenjun Hua;Zehan Shen;Yuliang Chen;Fanwei Meng;Zuen Zheng
    • Computers and Concrete
    • /
    • v.33 no.5
    • /
    • pp.605-619
    • /
    • 2024
  • The increase of reclaimed asphalt pavement (RAP) content in recycled asphalt concrete (RAC) is accompanied by the degradation of low-temperature cracking resistance, which has become an obstacle to the development of RAC. This paper aims to reveal the meso-scale mechanisms of the low-temperature fracture behavior of RAC and provide a theoretical basis for the economical recycling of RAP. For this purpose, micromechanical heterogeneous peridynamic model of RAC was established and validated by comparing three-point bending (TPB) test results against corresponding numerical simulation results of RAC with 50% RAP content. Furthermore, the models with different aggregate shapes (i.e., average aggregates circularity (¯Cr=1.00, 0.75, and 0.50) and RAP content (i.e., 0%, 15%, 30%, 50%, 75%, and 100%) were constructed to investigate the effect of aggregate shape and RAP content on the low-temperature cracking resistance. The results show that peridynamic models can accurately simulate the low-temperature fracture behavior of RAC, with only 2.9% and 13.9% differences from the TPB test in flexural strength and failure strain, respectively. On the meso-scale, the damage in the RAC is mainly controlled by horizontal tensile stress and the stress concentration appears in the interface transition zone (ITZ). Aggregate shape has a significant effect on the low-temperature fracture resistance, i.e., higher aggregate circularity leads to better low-temperature performance. The large number of microcracks generated during the damage evolution process for the peridynamic model with circular aggregates contributes to slowing down the fracture, whereas the severe stress concentration at the corners leads to the fracture of the aggregates with low circularity under lower stress levels. The effect of RAP content below 30% or above 50% is not significant, but a substantial reduction (16.9% in flexural strength and 16.4% in failure strain) is observed between the RAP content of 30% and 50%. This reduction is mainly attributed to the fact that the damage in the ITZ region transfers significantly to the aggregates, especially the RAP aggregates, when the RAP content ranges from 30% to 50%.

Modeling of Flame Acceleration Considering Complex Confinement Effects in Combustible Gas Mixture (가연성 기체 혼합물에서 복잡한 구조에 따른 화염 가속 모델링)

  • Gwak, Min-Cheol;Yoh, Jai-Ick
    • Transactions of the Korean Society of Mechanical Engineers B
    • /
    • v.36 no.3
    • /
    • pp.315-324
    • /
    • 2012
  • This paper presents a numerical investigation of the deflagration-to-detonation transition (DDT) of flame acceleration by a shock wave filled with an ethylene/air mixture as the combustible gas, considering geometrical changes by using obstacles and bent tubes. The model used consists of the reactive compressible Navier-Stokes equations and the ghost fluid method (GFM) for complex boundary treatment. Simulations with a variety of bent tubes with obstacles show the generation of hot spots through flame and strong shock-wave interactions, and restrained or accelerated flame propagation due to geometrical effects. In addition, the simulation results show that the DDT occurs with a nearly constant chemical heat-release rate of 20 MJ/(gs) in our numerical setup. Furthermore, the DDT triggering time can be delayed by the absence of unreacted material together with insufficient pressures and temperatures induced by different flame shapes, although hot spots are formed in the same positions.

On the Applications of the Genetic Decomposition of Mathematical Concepts -In the Case of Zn in Abstract Algebra- (수학적 개념의 발생적 분해의 적용에 대하여 -추상대수학에서의 Zn의 경우-)

  • Park Hye Sook;Kim Suh-Ryung;Kim Wan Soon
    • The Mathematical Education
    • /
    • v.44 no.4 s.111
    • /
    • pp.547-563
    • /
    • 2005
  • There have been many papers reporting that the axiomatic approach in Abstract Algebra is a big obstacle to overcome for the students who are not trained to think in an abstract way. Therefore an instructor must seek for ways to help students grasp mathematical concepts in Abstract Algebra and select the ones suitable for students. Mathematics faculty and students generally consider Abstract Algebra in general and quotient groups in particular to be one of the most troublesome undergraduate subjects. For, an individual's knowledge of the concept of group should include an understanding of various mathematical properties and constructions including groups consisting of undefined elements and a binary operation satisfying the axioms. Even if one begins with a very concrete group, the transition from the group to one of its quotient changes the nature of the elements and forces a student to deal with elements that are undefined. In fact, we also have found through running abstract algebra courses for several years that students have considerable difficulty in understanding the concept of quotient groups. Based on the above observation, we explore and analyze the nature of students' knowledge about Zn that is the set of congruence classes modulo n. Applying the genetic decomposition method, we propose a model to lead students to achieve the correct concept of Zn.

  • PDF

GA-BASED PID AND FUZZY LOGIC CONTROL FOR ACTIVE VEHICLE SUSPENSION SYSTEM

  • Feng, J.-Z.;Li, J.;Yu, F.
    • International Journal of Automotive Technology
    • /
    • v.4 no.4
    • /
    • pp.181-191
    • /
    • 2003
  • Since the nonlinearity and uncertainties which inherently exist in vehicle system need to be considered in active suspension control law design, this paper proposes a new control strategy for active vehicle suspension systems by using a combined control scheme, i.e., respectively using a genetic algorithm (GA) based self-tuning PID controller and a fuzzy logic controller in two loops. In the control scheme, the PID controller is used to minimize vehicle body vertical acceleration, the fuzzy logic controller is to minimize pitch acceleration and meanwhile to attenuate vehicle body vertical acceleration further by tuning weighting factors. In order to improve the adaptability to the changes of plant parameters, based on the defined objectives, a genetic algorithm is introduced to tune the parameters of PID controller, the scaling factors, the gain values and the membership functions of fuzzy logic controller on-line. Taking a four degree-of-freedom nonlinear vehicle model as example, the proposed control scheme is applied and the simulations are carried out in different road disturbance input conditions. Simulation results show that the present control scheme is very effective in reducing peak values of vehicle body accelerations, especially within the most sensitive frequency range of human response, and in attenuating the excessive dynamic tire load to enhance road holding performance. The stability and adaptability are also showed even when the system is subject to severe road conditions, such as a pothole, an obstacle or a step input. Compared with conventional passive suspensions and the active vehicle suspension systems by using, e.g., linear fuzzy logic control, the combined PID and fuzzy control without parameters self-tuning, the new proposed control system with GA-based self-learning ability can improve vehicle ride comfort performance significantly and offer better system robustness.

Performance Characteristic of satellite Wibro system in the high-speed Railroad Channel Environment

  • Song, Seung-Won;Cho, Hyun-Myung;Lee, Byung-Seub;Shin, Min-Su;Ryu, Joon-Gyu;Chang, Dae-Ig
    • Journal of Satellite, Information and Communications
    • /
    • v.2 no.2
    • /
    • pp.1-9
    • /
    • 2007
  • In this paper, we describe the performance degradation of satellite Wibro system and compensation method in the high-speed railroad channel environment. High-speed railroad channel environment is divided into LOS channel and tunnel. In the LOS channel, signal blocking caused by railroad power feeder structures can be a critical problem which is can be solved with antenna diversity. On the other hand, multi path interference phenomenon, representable by propagation model of Optic Fiber, occurred in the tunnel may be another obstacle. These satellite Wibro system performance degradations in railroad channel environment are addressed and adequate compensation methods are proposed and verified through computer simulation. In addition, the ICI caused by Doppler shift in OFDM system is analyzed with its compensation method.

  • PDF