서울시 가로경관 이미지에 대한 주관적 인지에 영향을 미치는 가로환경 요인 분석 : Deep Learning 의미론적 분할과 YOLOv3 객체 검출기법을 적용하여

다국어 초록 (Multilingual Abstract)

This study aims to demonstrate the relation between streetscape features and six different individual perceptions, which includes pedestrian satisfaction. Two deep learning techniques—semantic segmentation and object detection—were applied on Google Street View imagery; these techniques captured the streetscape factors from a pedestrian perspective and subsequently extracted various visual elements. In this study, independent variables include not only eight segmented object categories and two features detected from the streetscape images of community roads in Seoul but also factors relevant to the built environment and individual characteristics. In addition, human perceptions were measured through an online survey based on a 5-point Likert scale from 1 (“very dissatisfied”) to 5 (“very satisfied”) (n = 240). Subsequently, by using a multilevel ordered logistic regression model, we examined the factors’ discrete impacts on six different perceptual indicators: vitality, safety, beauty, boring, depression, and overall pedestrian satisfaction. The main results of this study are as follows. Among the segmented objects, sky, vegetation, wall, sidewalk, and pavement have important ramifications as perceptual indicators. In such a case, sky, vegetation, sidewalk, and pavement positively affect overall pedestrian satisfaction, vitality, safety, and beauty; however, the wall has an adverse impact on them. Moreover, the number of pedestrians and vehicles detected from the YOLOv3 algorithm is significantly associated with most perceptual indicators. Pedestrian volume is positively correlated with overall pedestrian satisfaction, vitality, and safety, whereas the effect of the number of vehicles is the opposite. Overall, though this study, we proposed policy implications to improve the walking environment.

참고문헌 (Reference)

1 정연희, "환경특성과 보행행태 분석에 근거한 보행공간 연구" 성균관대학교 디자인대학원 2009

2 김동영, "판교테크노밸리 사무직 종사자의 보행만족도 및 보행행태에 영향을 미치는 보행환경 요인 분석" 서울대학교 환경대학원 2013

3 이호준, "생활도로 노상주차 식별을 위한 Google Street View API와 딥러닝 모형의 적용" 대한공간정보학회 27 (27): 3-12, 2019

4 지우석, "보행환경 만족도 연구" 경기개발연구원 2008

5 이수기, "보행자 연령대별 보행만족도에 영향을 미치는 가로환경의 특성분석" 대한국토·도시계획학회 49 (49): 91-105, 2014

6 김규리, "보행공간 요소에 대한 보행자의 인지 및 보행만족도에 관한 연구" 한국도시설계학회 17 (17): 89-103, 2016

7 김창국, "보행 목적별 보행자 만족도에 영향을 미치는 근린 건조환경 구성요소 특성 분석" 대한국토·도시계획학회 51 (51): 145-159, 2016

8 변지혜, "물리적 보행환경이 보행만족도에 미치는 영향 - 진해시를 사례지역으로 -" 한국조경학회 37 (37): 57-65, 2010

9 김정호, "도시지역의 녹지경관 조망이 도시민의 스트레스 완화에 미치는 영향" 한국환경생태학회 27 (27): 516-523, 2013

10 이제승, "기계학습 알고리즘을 이용한 보행만족도 예측모형 개발" 대한국토·도시계획학회 54 (54): 106-118, 2019

11 이수기, "근린환경특성이 보행만족도에 미치는 영향 분석 - 서울서베이 2013년 자료를 중심으로" 대한국토·도시계획학회 51 (51): 169-187, 2016

12 김경환, "국내 보행 서비스수준의 평가기준" 17 (17): 31-46, 1998

13 성현곤, "구조방정식을 활용한 보행환경 계획요소의 이용만족도 평가에 관한 연구 - 종로 및 강남일대를 대상으로" 대한국토·도시계획학회 46 (46): 275-288, 2011

14 길호평, "검출 성능 향상 및 불확실성 추정을 위한 다목적 객체 검출 알고리즘" 360-366, 2020

15 박근덕, "가로공간 보행만족도 예측을 위한 딥러닝 모형의적용과 검증" 한국도시설계학회 19 (19): 19-34, 2018

16 Noble, W. S., "What is a Support Vector Machine?" 24 (24): 1565-1567, 2006

17 Lu, Y., "Using Google Street View to Investigate the Association between Street Greenery and Physical Activity" 191 : 103435-, 2019

18 Middel, A., "Urban Form and Composition of Street Canyons: A Human-centric Big Data and Deep Learning Approach" 183 : 122-132, 2019

19 Wang, R., "The Relationship Between Visual Enclosure for Neighbourhood Street Walkability and Elders’ Mental Health in China: Using Street View Images" 13 : 90-102, 2019

20 Lu, Y., "The Effect of Street-level Greenery on Walking Behavior: Evidence from Hong Kong" 208 : 41-49, 2018

21 Jacobs, J., "The Death and Life of Great American Cities" Random House 1961

22 Naik, N., "Streetscore-predicting the Perceived Safety of One Million Streetscapes" 779-785, 2014

23 Liu, J., "Research on Vehicle Object Detection Algorithm Based on Improved YOLOv3 Algorithm" 1575 (1575): 012150-, 2020

24 Stradling, S. G., "Performance, Importance and User Disgruntlement: A Six-step Method for Measuring Satisfaction with Travel Modes" 41 (41): 98-106, 2007

25 Schroeder, H.W., "Perception of Personal Safety in Urban Recreation Sites" 16 (16): 178-194, 1984

26 Fruin, J. J., "Pedestrian Planning and Design" Metropolitan Association of Urban Designer and Environmental Planner 1971

27 Roth, M., "Online Visual Landscape Assessment Using Internet Survey Techniques Trends in Online Landscape Architecture" 121-130, 2005

28 Nagata, S., "Objective Scoring of Streetscape Walkability Related to Leisure Walking: Statistical Modeling Approach with Semantic Segmentation of Google Street View Images" 66 : 102428-, 2020

29 Yuan, Y., "Object-contextual Representations for Semantic Segmentation"

30 Kim, S., "Meso-or Micro-scale Environmental Factors Influencing Pedestrian Satisfaction" 30 : 10-20, 2014

31 Yin, L., "Measuring Visual Enclosure for Street Walkability Using Machine Learning Algorithms and Google Street View Imagery" 76 : 147-153, 2016

32 Zhang, F., "Measuring Human Perceptions of a Largescale Urban Region Using Machine Learning" 180 : 148-160, 2018

33 Oh, I. S., "Machine Learning" Hanbit Academy 194-221, 2017

34 Wang, M., "Life Between Buildings from a Street View Image: What Do Big Data Analytics Reveal about Neighbourhood Organisational Vitality?" 2020

35 Wang, S. C., "Interdisciplinary Computing in Java Programming" Springer 81-100, 2003

36 Buduma, N., "Fundamentals of Deep Learning:Designing Next-Generation Machine Intelligence Algorithms" O’Reilly Media 2017

37 Berto, R., "Exposure to Restorative Environments Helps Restore Attentional Capacity" 25 (25): 249-259, 2005

38 Chen, L. C., "Deeplab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected Crfs" 40 (40): 834-848, 2017

39 문성철, "Deep Learning Object Detection to Clearly Differentiate Between Pedestrians and Motorcycles in Tunnel Environment Using YOLOv3 and Kernelized Correlation Filters" 한국방송∙미디어공학회 24 (24): 1266-1275, 2019

40 Valtchanov, D., "Cognitive and Affective Responses to Natural Scenes: Effects of Low Level Visual Properties on Preference, Cognitive Load and Eye-movements" 43 : 184-195, 2015

41 유성훈, "CNN을 이용한 고해상도 위성사진에서의 객체검출에 관한 연구" 1608-1609, 2019

42 Liu, P., "Building Footprint Extraction from High-resolution Images via Spatial Residual Inception Convolutional Neural Network" 11 (11): 1-19, 2019

43 Quercia, D., "Aesthetic Capital: What Makes London Look Beautiful, Quiet, and Happy?" 945-955, 2014

44 Ammar, A., "Aerial Images Processing for Car Detection Using Convolutional Neural Networks: Comparison between Faster R-CNN and YOLOv3"

45 Hao, S., "A Brief Survey on Semantic Segmentation with Deep Learning" 406 : 302-321, 2020