Research on the scale of pedestrian space in underground shopping streets based on VR experiment

Yao, Gang; Yuan, Tingting; Yao, Rui; Chen, Wanjing; Duan, Zhongcheng; Sun, Liang; Si, Xianzhi; Zhang, Meng; Chen, Kaiyun; Zhu, Yusong; Chen, Yiying

doi:10.1080/13467581.2020.1782215

Cited by 11 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Analyze the current students' understanding of virtual reality, based on the deep learning model, combine virtual reality and English courses, follow the basic principles of teaching design, and construct a virtual reality environmentbased English mixed teaching curriculum design framework (Figure 4) [18][19][20]. rough the case of a VR educational game called "In Order To Dr.," an experimental class and a control class were set up, and the traditional teaching methods and the teaching methods with the help of VR educational games were used to conduct comparative experimental teaching in the English mixed teaching classroom.…”

Section: Deep Learning Eorymentioning

confidence: 99%

Deep Learning Analysis of English Education Blended Teaching in Virtual Reality Environment

Qiu

2022

Scientific Programming

View full text Add to dashboard Cite

The rapid development of computer software and hardware, network technology, and various Internet platforms has brought mankind into a new era. In recent years, “virtual reality” can be regarded as a huge hot spot, whether in the field of industry, education, or research. At present, although the heat has subsided a little, the technical teams involved in various fields are also working collectively to continuously innovate. Based on the mixed teaching mode of English education, this article conducts in-depth research on deep learning and virtual reality technology, integrates deep learning and virtual reality learning environment, and builds a learning model of English education learning environment based on virtual reality. The teaching design of the course aims to fully combine the main content of deep learning with the virtual reality environment. Through experimental research, it is explored whether the learning environment based on virtual reality can promote deep learning. The relevant data of the experimental class and the control class are collected through questionnaires, starting from the four dimensions of motivation dimension, investment dimension, strategy dimension, and result dimension, and conduct a comparative analysis, and use the auxiliary interview method to understand the experience of students and teachers on virtual reality equipment and put forward relevant suggestions.

show abstract

Section: Deep Learning Eorymentioning

confidence: 99%

Deep Learning Analysis of English Education Blended Teaching in Virtual Reality Environment

Qiu

2022

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…Researchers at the regional scale have applied variables to analyze urban forms on a macroscopic scale, including city size, building density, centrality [38], polycentricity [39,40], location quotient [41], and Gini coefficients. Other researchers with neighborhood-scale perspectives have analyzed urban forms with building-and block-scale variables, such as building footprint size, building coverage ratio [42,43], width-length ratio of buildings and blocks [44], compactness [45], entropy index [46], and spatial integration calculated by space syntax [47].…”

Section: Urban Form and Restaurant Locationmentioning

confidence: 99%

Novel CNN-Based Approach for Reading Urban Form Data in 2D Images: An Application for Predicting Restaurant Location in Seoul, Korea

Yang,

Kwon

2023

IJGI

View full text Add to dashboard Cite

Artificial intelligence (AI) has demonstrated its ability to complete complex tasks in various fields. In urban studies, AI technology has been utilized in some limited domains, such as control of traffic and air quality. This study uses AI to better understand diverse urban studies data through a novel approach that uses a convolutional neural network (CNN). In this study, a building outline in the form of a two-dimensional image is used with its corresponding metadata to test the applicability of CNN in reading urban data. MobileNet, a high-efficiency CNN model, is trained to predict the location of restaurants in each building in Seoul, Korea. Consequently, using only 2D image data, the model satisfactorily predicts the locations of restaurants (AUC = 0.732); the model with 2D images and their metadata has higher performance but has an overfitting problem. In addition, the model using only 2D image data accurately predicts the regional distribution of restaurants and shows some typical urban forms with restaurants. The proposed model has several technical limitations but shows the potential to provide a further understanding of urban settings.

show abstract

“…The whole street space is in the visual field of the walker, and the aspect ratio of the street is the walker's direct perception of the visual field. More specifically, the imbalance between the street width D and the height H of buildings along the street will affect the way walkers look at the street environment and the walkers' viewing range [58,59]. When the ratio of D/H is greater than 2, the vertical viewing angle of buildings within the visual range will be less than 26 • .…”

Section: Street Aspect Ratiomentioning

confidence: 99%

Evaluating Pedestrian Environment Using DeepLab Models Based on Street Walkability in Small and Medium-Sized Cities: Case Study in Gaoping, China

et al. 2022

View full text Add to dashboard Cite

In small and medium-sized cities of China, walking plays an important role as a green and healthy way to travel. However, the intensification of motorized travel and poor planning of pedestrian transportation systems have resulted in poor travel experiences for residents. To encourage residents to change their mode of travel from motorized transport to greener modes, it is necessary to consider the characteristics of walking travel, design good walking street environments, and increase the advantages of walking in the downtown areas of small and medium-sized cities. In this study, a spatial environment model of a pedestrian street was constructed based on the walking score. Visual perception elements, street function elements, and walking scale elements were acquired by semantic segmentation of Baidu street view images obtained with the DeepLab model. Points of interest (POI) were obtained based on surveys, measurements, and the space syntax. Considering walking distances for small and medium-sized cities, the attenuation coefficient of a reasonable facility distance was adopted to modify the walking score. Based on the comprehensive score obtained, walking paths were divided into four categories: functionally preferred, visually preferred, scale preferred, and environmentally balanced. This categorization provides theoretical support for the design of pedestrian street space environments. Taking the pedestrian street in the city center of Gaoping in Shanxi Province, China as an example, the feasibility of the method and model was verified.

show abstract

Research on the scale of pedestrian space in underground shopping streets based on VR experiment

Cited by 11 publications

References 14 publications

Deep Learning Analysis of English Education Blended Teaching in Virtual Reality Environment

Deep Learning Analysis of English Education Blended Teaching in Virtual Reality Environment

Novel CNN-Based Approach for Reading Urban Form Data in 2D Images: An Application for Predicting Restaurant Location in Seoul, Korea

Evaluating Pedestrian Environment Using DeepLab Models Based on Street Walkability in Small and Medium-Sized Cities: Case Study in Gaoping, China

Contact Info

Product

Resources

About