• Title/Summary/Keyword: 보행자 분류

Search Result 80, Processing Time 0.03 seconds

Study of Adversarial Attack and Defense Deep Learning Model for Autonomous Driving (자율주행을 위한 적대적 공격 및 방어 딥러닝 모델 연구)

  • Kim, Chae-Hyeon;Lee, Jin-Kyu;Jung, Eun;Jung, Jae-Ho;Lee, Hyun-Jung;Lee, Gyu-Young
    • Annual Conference of KIPS
    • /
    • 2022.11a
    • /
    • pp.803-805
    • /
    • 2022
  • 자율주행의 시대가 도래함에 따라, 딥러닝 모델에 대한 적대적 공격 위험이 함께 증가하고 있다. 카메라 기반 자율주행차량이 공격받을 경우 보행자나 표지판 등에 대한 오분류로 인해 심각한 사고로 이어질 수 있어, 자율주행 시스템에서의 적대적 공격에 대한 방어 및 보안 기술 연구가 필수적이다. 이에 본 논문에서는 GTSRB 표지판 데이터를 이용하여 각종 공격 및 방어 기법을 개발하고 제안한다. 시간 및 정확도 측면에서 성능을 비교함으로써, 자율주행에 최적인 모델을 탐구하고 더 나아가 해당 모델들의 완전자율주행을 위한 발전 방향을 제안한다.

Methodology of Selecting Criteria for Pedestrian only Street (차없는 거리 선정기준 수립을 위한 방법론 정립 연구)

  • Kim, Yoomi;Park, Jejin;Lee, Junyoung;Ha, Taejun
    • KSCE Journal of Civil and Environmental Engineering Research
    • /
    • v.36 no.5
    • /
    • pp.867-879
    • /
    • 2016
  • Since the 1970s, the region of its own pedestrian center and environmental pollution caused by exhaust gases have been reduced gradually in a continuous increase of the vehicle, school route the central business district, around the school, the sidewalk where the vehicle do not pass, facilities of minimum for the safety of pedestrians and systematic management of an area where an unspecified number and alleys impassable is insufficient. Recently, in response to the "Law for convenience enhancing safety and walking" is enforced in Korea, research on Pedestrian only Street has been actively about the government, the standard for calculating the weights of evaluation associated with it. it is a actuality, however, there are insufficient, evaluation for business promotion is being conducted evaluation polite manner by using, for example, scale residence time and purpose of the passengers as there is no car that has been carried out on a voluntary basis through the municipality have. In this study, by suggesting a method for the selection of the street without a car, make a survey by placing a purpose in the selection method presentation of the street with no car to be construction future, was researching. F.G.I (Focus Group Interview) survey, professors, staff in urban, traffic field of experts in order to present the weights for the evaluation of the Pedestrian only Street by using the evaluation index by type of Pedestrian only Street, was interviewed about the evaluation index for the conducted for professionals engaged in the engineering company, and randomly selected 200 peoples, weighted evaluation of the street with Pedestrian only Street was proposed. By classifying the items purpose and goals of the evaluation type by this by applying the weight, and present the weight of the detailed indicators each corresponding to each item, and scored on the basis of the result, in this paper it can be so that one methodology for the selection standard for the construction as Pedestrian only Street, and the weight of the evaluation of the type that has been derived, the selection and evaluation methods and then added to these criteria to settle careful study of the reference should be performed further.

Development of A Multi-sensor Fusion-based Traffic Information Acquisition System with Robust to Environmental Changes using Mono Camera, Radar and Infrared Range Finder (환경변화에 강인한 단안카메라 레이더 적외선거리계 센서 융합 기반 교통정보 수집 시스템 개발)

  • Byun, Ki-hoon;Kim, Se-jin;Kwon, Jang-woo
    • The Journal of The Korea Institute of Intelligent Transport Systems
    • /
    • v.16 no.2
    • /
    • pp.36-54
    • /
    • 2017
  • The purpose of this paper is to develop a multi-sensor fusion-based traffic information acquisition system with robust to environmental changes. it combines the characteristics of each sensor and is more robust to the environmental changes than the video detector. Moreover, it is not affected by the time of day and night, and has less maintenance cost than the inductive-loop traffic detector. This is accomplished by synthesizing object tracking informations based on a radar, vehicle classification informations based on a video detector and reliable object detections of a infrared range finder. To prove the effectiveness of the proposed system, I conducted experiments for 6 hours over 5 days of the daytime and early evening on the pedestrian - accessible road. According to the experimental results, it has 88.7% classification accuracy and 95.5% vehicle detection rate. If the parameters of this system is optimized to adapt to the experimental environment changes, it is expected that it will contribute to the advancement of ITS.

A Study on the elements of Life Safety Environment in the exterior Space of the University neighborhood One-room village -Focused on the case of 'O' university neighborhood One-room village in Chungcheongbukdo- (대학가 원룸촌 외부공간의 생활안전 기능요소에 관한 연구 -충청북도 소재 'O' 대학교 원룸촌 사례를 중심으로-)

  • Kim, Hwan-Sik
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.19 no.12
    • /
    • pp.321-331
    • /
    • 2018
  • This study examined the life safety factor of residents living in a university village. The results of the study were as follows. First, previous research results and social safety-related research and practical system for a wide range of exterior space, including the driveway of the living space was a relative lack. Based on the survey results, the psychological factors that affect the life safety environment of the living space was found in the exterior space environment. Second, the living safety factors in the exterior space of a one-room residence can be shown by four types, such as occupant monitoring, residential surveillance and area classification, external public space utilization, and pleasant environment maintenance in the architectural planning dimension. Third, the results of research on the exterior space of the university one-room village, and life safety environment of exterior space, such as design of pedestrian street, revealed a very poor resident population and one-room buildings in most areas.

A Study on the Parking Space and Space of Detached Housing Area in Misagangbyeon-City (미사강변도시 단독주택지의 주차공간과 가구의 특성에 관한 연구)

  • Hwang, Yong-Woon
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.18 no.10
    • /
    • pp.785-793
    • /
    • 2017
  • The guidelines for the district unit planning(DUP) of detached houses in the area of Misagangbyeon-City (MISA) do not consider the characteristics of the region. Therefore, this study was conducted to analyze the relationship between the blocks and parking lots of the detached houses area. The research results can be summarized as follows: 1) Detailed design guidelines are provided for apartment homes in MISA, but not for detached houses. 2) Apartment home and multi-family house parking lot equivaluation calculations exist in the DUP guidelines, however there are no regulations related to detached houses and the problem of parking for these residents is worsening which causes tension. 3) The DUP guidelines stipulate that the outer wall material of multi-family houses must be glass, however this is a dangerous material for use on the first floor, because cars that park close to this wall. 4) There is a significant risk to elementary and kindergarten students who must walk along the road in the inner blocks where cars are driving quickly. 5) There are a number of issues involved when planning parking lots without considering the characteristics of the area. The local government uses the traditional parking lot codes without considering the current regional characteristics, whereas the number of cars has dramatically increased. 6) The pedestrian mall is not currently being used for pedestrians, because it is full of parked cars due to the lack of parking space.

Enhanced Indoor Localization Scheme Based on Pedestrian Dead Reckoning and Kalman Filter Fusion with Smartphone Sensors (스마트폰 센서를 이용한 PDR과 칼만필터 기반 개선된 실내 위치 측위 기법)

  • Harun Jamil;Naeem Iqbal;Murad Ali Khan;Syed Shehryar Ali Naqvi;Do-Hyeun Kim
    • Journal of Internet of Things and Convergence
    • /
    • v.10 no.4
    • /
    • pp.101-108
    • /
    • 2024
  • Indoor localization is a critical component for numerous applications, ranging from navigation in large buildings to emergency response. This paper presents an enhanced Pedestrian Dead Reckoning (PDR) scheme using smartphone sensors, integrating neural network-aided motion recognition, Kalman filter-based error correction, and multi-sensor data fusion. The proposed system leverages data from the accelerometer, magnetometer, gyroscope, and barometer to accurately estimate a user's position and orientation. A neural network processes sensor data to classify motion modes and provide real-time adjustments to stride length and heading calculations. The Kalman filter further refines these estimates, reducing cumulative errors and drift. Experimental results, collected using a smartphone across various floors of University, demonstrate the scheme's ability to accurately track vertical movements and changes in heading direction. Comparative analyses show that the proposed CNN-LSTM model outperforms conventional CNN and Deep CNN models in angle prediction. Additionally, the integration of barometric pressure data enables precise floor level detection, enhancing the system's robustness in multi-story environments. Proposed comprehensive approach significantly improves the accuracy and reliability of indoor localization, making it viable for real-world applications.

Pedestrian and Vehicle Distance Estimation Based on Hard Parameter Sharing (하드 파라미터 쉐어링 기반의 보행자 및 운송 수단 거리 추정)

  • Seo, Ji-Won;Cha, Eui-Young
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.26 no.3
    • /
    • pp.389-395
    • /
    • 2022
  • Because of improvement of deep learning techniques, deep learning using computer vision such as classification, detection and segmentation has also been used widely at many fields. Expecially, automatic driving is one of the major fields that applies computer vision systems. Also there are a lot of works and researches to combine multiple tasks in a single network. In this study, we propose the network that predicts the individual depth of pedestrians and vehicles. Proposed model is constructed based on YOLOv3 for object detection and Monodepth for depth estimation, and it process object detection and depth estimation consequently using encoder and decoder based on hard parameter sharing. We also used attention module to improve the accuracy of both object detection and depth estimation. Depth is predicted with monocular image, and is trained using self-supervised training method.

A Basic Study on the Fall Direction Recognition System Using Smart phone (스마트폰을 이용한 낙상 방향 검출 시스템의 기초 연구)

  • Na, Ye-Ji;Lee, Sang-Jun;Wang, Chang-Won;Jeong, Hwa-Young;Ho, Jong-Gab;Min, Se-Dong
    • Annual Conference of KIPS
    • /
    • 2015.10a
    • /
    • pp.1384-1387
    • /
    • 2015
  • 고령화 사회로 진입하면서 노인들은 노화과정에 의한 보행능력의 감소 및 근력 약화와 같은 신체적 변화로 인해 잦은 낙상을 경험한다. 이에 따라 낙상 사고를 감지하는 연구가 활발히 진행되고 있다. 낙상은 사전 예방도 중요하지만 사고 발생 후의 신속한 대처도 중요하다. 낙상을 감지하고 의료진에게 즉시 낙상정보를 제공하여 후속적 조치를 취하는 것은 사고 후 대처의 핵심이다. 본 논문에서는 스마트폰 환경에서 사용자의 낙상 후 방향을 판별하기 위해 두 가지 센서 데이터의 특정 값들을 추출하였으며, 이에 5 가지 기계학습 알고리즘을 적용하였다. 사용자는 스마트폰을 착용한 상태로 전후좌우 4 방향 낙상 실험을 진행하며 스마트폰 내에 내장된 3 축 가속도 센서와 3 축 자이로 센서값을 측정한다. 피험자 11 명을 대상으로 낙상 실험 결과, 5 가지의 분류기 중 k-NN에서 98.6%의 인식률을 나타내었다. 뽑아낸 특징 값과 분류 알고리즘은 낙상의 방향 검출에 유용한 것으로 판단된다.

Human Tracking Technology using Convolutional Neural Network in Visual Surveillance (서베일런스에서 회선 신경망 기술을 이용한 사람 추적 기법)

  • Kang, Sung-Kwan;Chun, Sang-Hun
    • Journal of Digital Convergence
    • /
    • v.15 no.2
    • /
    • pp.173-181
    • /
    • 2017
  • In this paper, we have studied tracking as a training stage of considering the position and the scale of a person given its previous position, scale, as well as next and forward image fraction. Unlike other learning methods, CNN is thereby learning combines both time and spatial features from the image for the two consecutive frames. We introduce multiple path ways in CNN to better fuse local and global information. A creative shift-variant CNN architecture is designed so as to alleviate the drift problem when the distracting objects are similar to the target in cluttered environment. Furthermore, we employ CNNs to estimate the scale through the accurate localization of some key points. These techniques are object-independent so that the proposed method can be applied to track other types of object. The capability of the tracker of handling complex situations is demonstrated in many testing sequences. The accuracy of the SVM classifier using the features learnt by the CNN is equivalent to the accuracy of the CNN. This fact confirms the importance of automatically optimized features. However, the computation time for the classification of a person using the convolutional neural network classifier is less than approximately 1/40 of the SVM computation time, regardless of the type of the used features.

A Study on the Surveillance System of Multiple Object's Dangerous Behaviors (다중 객체의 위험 행동 감시 시스템 연구)

  • Shim, Young-Bin;Park, Hwa-Jin
    • Journal of Digital Contents Society
    • /
    • v.14 no.4
    • /
    • pp.455-462
    • /
    • 2013
  • This paper proposes a detection system that, by determining whether a dangerous act is being carried out among other pedestrians in the images captured using CCTV, provides pre-warnings and establishes emergency measures. To determine the presence of a dangerous act, after setting zones of interest and danger zones within those zones of interest, the danger level is determined in accordance with the range of encroachment upon detecting an object. Especially, this research aims at detecting a suicide jump from the bridge and extends to detecting a dangerous act among pedestrians from detecting a dangerous act of only one person with no one in the previous research. This system classifies the status into 3 levels as safe, alert, and danger according to the amount of part being over the bridge railing. If a situation is deemed as warning-worthy and emergency, the integrated control center is immediately alerted to facilitate prevention in advance.