• 한국주거학회논문집
• /
• 제26권3호
• /
• pp.1-9
• /
• 2015

This study aims to estimate the perception of mothers of infant and toddler on the child-rearing environment and compare the recognition of parents who live in APT and multi-family housing. This study investigates the mothers in order to survey the level of importance and satisfaction on the neighborhood environment factors for child-rearing. The result of questionnaire is analyzed by Importance-Performance Analysis (IPA). According to the result of IPA by housing types, it was found that the improvement of pedestrian environment, separation of pedestrian and vehicle, natural environment and playground is required particularly in the multi-family housing area. the mothers need soundproofing of house and management of unwanted facilities in neighborhood in common. In the apartment, improvement of child-care facilities and children's library is required. The results of IPA on the mothers of infant and toddler may be important foundation for future strategies for child-rearing environment improvement.

• 드라이브 ㆍ 컨트롤
• /
• 제19권4호
• /
• pp.110-116
• /
• 2022

Recently, various studies have been conducted to apply deep learning and AI to various fields of autonomous driving, such as recognition, sensor processing, decision-making, and control. This paper proposes a controller applicable to path following, static obstacle avoidance, and pedestrian avoidance situations by utilizing reinforcement learning in autonomous vehicles. For repetitive driving simulation, a reinforcement learning environment was constructed using virtual environments. After learning path following scenarios, we compared control performance with Pure-Pursuit controllers and Stanley controllers, which are widely used due to their good performance and simplicity. Based on the test case of the KNCAP test and assessment protocol, autonomous emergency steering scenarios and autonomous emergency braking scenarios were created and used for learning. Experimental results from zero collisions demonstrated that the reinforcement learning controller was successful in the stationary obstacle avoidance scenario and pedestrian collision scenario under a given condition.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.175-177
• /
• 2021

장애인 주차구역은 보행장애인을 위한 주차시설로써, 장애인의 보행 안전 통로를 확보하기 위한 주차공간이다. 하지만 장애인 전용구역에 대한 사회적인 인식 부족으로 실제 주차구역을 이용해야 하는 장애인의 이용이 제한되고 불법 주차 행위 및 주차 방해 행위 등 위반사례들이 매년 급증하고 있다. 따라서, 본 연구에서는 장애인 주차 구역의 불법 주차 차량 및 주차공간 내부에서 주차를 방해하는 행위를 개선하기 위해 딥러닝 객체 인식 모델인 YOLOv5 모델을 적용한 장애인 주차구역 불법행위 단속시스템을 제안한다.

• 한국ITS학회 논문지
• /
• 제23권2호
• /
• pp.69-78
• /
• 2024

최근 CCTV 영상을 기반으로 인파사고를 예방하는 방안이 추진되고 있다. 그러나 CCTV는 공간적 한계점이 있어 이를 보완하기 위한 연구가 필요한 실정이다. 본 연구에서는 드론 영상을 사용하여 보행자의 밀도를 측정하는 연구를 수행하였다. 기존 연구문헌을 통해 군중의 인파사고 임계값인 1m²당 6.7명을 위험수준으로 선정하였다. 또한 드론의 파라미터를 도출하기 위해 선행연구를 수행한 결과, 고도 20m, 각도 60°에서 보행자의 인식률이 높은 것으로 나타났다. 이후 선행연구를 기반으로 보행자가 밀집한 대상지를 선정하여 밀집도를 측정한 결과, 단위 면적당 0.27~0.30명 수준으로 나타났다. 본 연구를 통해 드론 영상을 사용하여 대상지의 보행자 밀집도에 따른 위험수준 측정이 가능한 것으로 확인되었으며, 향후 인파사고 안전관리 대체 수단으로 활용이 가능할 것으로 판단된다.

• 대한교통학회지
• /
• 제24권6호
• /
• pp.119-127
• /
• 2006

최근 도시의 급속한 발전과 시민들의 교통문화 의식이 향상되어 물리적인 요인뿐만 아니라 정서적인 측면을 동시에 고려한 보다 나은 보행환경을 요구하고 있는 실정이다. 또한 최소의 물리적인 설계 기준만을 충족시킨 기존의 보행공간이 보행 기피의 한 원인이 되고 있으므로 보행환경의 개선이 필요한 실정이다. 보행환경 개선을 위해서는 우리나라 보행자들이 편안하고 쾌적하게 느끼는 보행환경이 무엇인지를 파악하는 것이 매우 중요하다고 볼 수 있다. 이에 본 연구에서는 SD 척도의 조사기법을 이용하여 인간의 정서적인 측면을 고려할 수 있는 감성공학을 적용한 보행환경 실험을 실시하였다 그리고 SD 척도에 의한 감성형용사의 감성인지를 분석하는데 유용한 LISREL 모형을 이용하여 보도경관의 인지평가 모형과 보도 설계요소의 감성인지 모형을 구축하였다 그 결과 보도 설계시 감성공학을 도입함으로써 쾌적하고 편안한 보도환경 구현이 가능하며 가로수 등의 식재를 통한 녹색환경을 조화롭게 구성하는 것이 무엇보다 중요함을 알 수 있었다

• 한국멀티미디어학회논문지
• /
• 제22권12호
• /
• pp.1457-1465
• /
• 2019

3D convolution is to stack multiple consecutive frames to form a cube, and then apply the 3D convolution kernel in the cube. In this structure, each feature map of the convolutional layer is connected to multiple adjacent sequential frames in the previous layer, thus capturing the motion information. However, due to the changes of pedestrian posture, motion and position, the convolution at the same place is inappropriate, and when the 3D convolution kernel is convoluted in the time domain, only time domain features of three consecutive frames can be extracted, which is not a good enough to get action information. This paper proposes an action recognition method based on feature fusion of 3D convolutional neural network. Based on the VGG16 network model, sending a pre-acquired optical flow image for learning, then get the time domain features, and then the feature of the time domain is extracted from the features extracted by the 3D convolutional neural network. Finally, the behavior classification is done by the SVM classifier.

• 방송공학회논문지
• /
• 제18권4호
• /
• pp.535-542
• /
• 2013

본 논문에서는 고속 및 고인식률의 성능을 갖는 영상인식 엔진 구조를 제안한다. 본 엔진은 2단계의 특징점 추출 및 분류 알고리즘을 수행하여 자동차와 보행자를 인식할 수 있다. 엔진의 인식률을 높이기 위해 HOG 특징점 값과 LBP 특징점 값을 같이 사용하여 알고리즘을 구성하였으며, 처리 속도를 높이기 위해 병렬 구조를 개선하여 하드웨어를 설계하였다. 실험결과를 통해 설계한 엔진이 초당 90프레임의 인식 처리가 가능하며 FPPW $10^{-4}$ 하에서 97.7%의 보행자 인식률을 가짐을 보인다.

• Smart Structures and Systems
• /
• 제24권5호
• /
• pp.617-630
• /
• 2019

Currently most of the vision-based structural identification research focus either on structural input (vehicle location) estimation or on structural output (structural displacement and strain responses) estimation. The structural condition assessment at global level just with the vision-based structural output cannot give a normalized response irrespective of the type and/or load configurations of the vehicles. Combining the vision-based structural input and the structural output from non-contact sensors overcomes the disadvantage given above, while reducing cost, time, labor force including cable wiring work. In conventional traffic monitoring, sometimes traffic closure is essential for bridge structures, which may cause other severe problems such as traffic jams and accidents. In this study, a completely non-contact structural identification system is proposed, and the system mainly targets the identification of bridge unit influence line (UIL) under operational traffic. Both the structural input (vehicle location information) and output (displacement responses) are obtained by only using cameras and computer vision techniques. Multiple cameras are synchronized by audio signal pattern recognition. The proposed system is verified with a laboratory experiment on a scaled bridge model under a small moving truck load and a field application on a footbridge on campus under a moving golf cart load. The UILs are successfully identified in both bridge cases. The pedestrian loads are also estimated with the extracted UIL and the predicted weights of pedestrians are observed to be in acceptable ranges.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.162-164
• /
• 2022

Efforts are being made to prevent traffic accidents within the child protection zone. Efforts are being made to prevent accidents by enacting safety facilities and laws to prevent traffic accidents in the school zone. However, traffic accidents in school zones continue to occur. If the driver can know the situation in the child protection zone in advance, accidents can be reduced. In this paper, we design a camera that eliminates blind spots in school zones and a number recognition camera system that can collect pre-traffic information. Design a LIDAR system that recognizes vehicle speed and pedestrians. Design an LED guidance system that delivers information to drivers without smart devices. We study time series analysis and artificial intelligence algorithms that collect and process pedestrian and vehicle information recognized by cameras and LIDAR. In the artificial intelligence traffic accident prevention system learned by deep learning, before entering the school zone, the school zone information is sent to the driver through the Force Push Service and the school zone information is delivered to the driver on the LED sign. try to reduce accidents.

• 로봇학회논문지
• /
• 제12권2호
• /
• pp.217-227
• /
• 2017

Crosswalk detection is an important part of the Pedestrian Protection System in autonomous vehicles. Different methods of crosswalk detection have been introduced so far using crosswalk edge features, the distance between crosswalk blocks, laser scanning, Hough Transformation, and Fourier Transformation. However, most of these methods failed to detect crosswalks accurately, when they are damaged, faded away or partly occluded. Furthermore, these methods face difficulties when applying on real road environment where there are lot of vehicles. In this paper, we solve this problem by first using a region based binarization technique and x-axis histogram to detect the candidate crosswalk areas. Then, we apply Support Vector Machine (SVM) based classification method to decide whether the candidate areas contain a crosswalk or not. Experiment results prove that our method can detect crosswalks in different environment conditions with higher recognition rate even they are faded away or partly occluded.