Large-Scale Street Space Quality Evaluation Based on Deep Learning Over Street View Image

Liu, Mei; Han, Longmei; Xiong, Shanbai; Qing, Linbo; Ji, Haohao; Peng, Yonghong

doi:10.1007/978-3-030-34110-7_58

Cited by 11 publications

(13 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu et al [18] proposed a computer vision method including three machine learning models, to use street view images to evaluate the urban environmental quality from the architectural level on a large scale. Liu et al [19] proposed a deep learning approach to estimate the street quality score. Zhang et al [26] investigated a data-driven machine learning approach to measure how people perceive the urban region.…”

Section: Application Of Street View Imagery To Evaluate Urban Spacementioning

confidence: 99%

“…Liu et al [18] evaluated the qualities of urban appearance using machine learning, but it was limited to architectural level analysis. Liu et al [19] used deep learning to estimate street space quality based on three quantitative indices (i.e., cleanliness, comfort and traffic) they defined and labelled themselves; there may be a gap between their opinions and the public's preference. Zhang et al [26] employed street view image as a proxy for the urban environment to evaluate human perceptions of a city by using a deep convolutional neural network (DCNN), but they only used the positive confidence of a binary classification model as the perception scores, without proving the consistency between their results with the ground truth.…”

Section: Application Of Street View Imagery To Evaluate Urban Spacementioning

confidence: 99%

“…The imagery data provides an efficient means for the analysis of visual elements and physical appearance at a city scale. The fast development of computer vision, on the other hand, has attracted much attention and achieved a great success in obtaining the visual information of the urban appearance at a large scale when it is combined with street-view imagery [17][18][19][20][21][22][23][24][25][26][27][28]. Although the above work has made great progress in the evaluation of urban space, the performance of their methods in terms of accuracy and the level of supported analysis are still very limited, which hindles the accuracy and comprehension to understand the human perception of urban space.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A New Data-Enabled Intelligence Framework for Evaluating Urban Space Perception

Qing

Han³

et al. 2021

IJGI

Self Cite

View full text Add to dashboard Cite

The urban environment has a great impact on the wellbeing of citizens and it is of great significance to understand how citizens perceive and evaluate places in a large scale urban region and to provide scientific evidence to support human-centered urban planning with a better urban environment. Existing studies for assessing urban perception have primarily relied on low efficiency methods, which also result in low evaluation accuracy. Furthermore, there lacks a sophisticated understanding on how to correlate the urban perception with the built environment and other socio-economic data, which limits their applications in supporting urban planning. In this study, a new data-enabled intelligence framework for evaluating human perceptions of urban space is proposed. Specifically, a novel classification-then-regression strategy based on a deep convolutional neural network and a random-forest algorithm is proposed. The proposed approach has been applied to evaluate the perceptions of Beijing and Chengdu against six perceptual criteria. Meanwhile, multi-source data were employed to investigate the associations between human perceptions and the indicators for the built environment and socio-economic data including visual elements, facility attributes and socio-economic indicators. Experimental results show that the proposed framework can effectively evaluate urban perceptions. The associations between urban perceptions and the visual elements, facility attributes and a socio-economic dimension have also been identified, which can provide substantial inputs to guide the urban planning for a better urban space.

show abstract

Section: Application Of Street View Imagery To Evaluate Urban Spacementioning

confidence: 99%

Section: Application Of Street View Imagery To Evaluate Urban Spacementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A New Data-Enabled Intelligence Framework for Evaluating Urban Space Perception

Qing

Han³

et al. 2021

IJGI

Self Cite

View full text Add to dashboard Cite

show abstract

“…Therefore, as a source factor that affects the vitality of street space and economic benefits, visual attraction begins to enter the field of academic research.Visual attraction has changed from a little-noticed behavior in the past to a new direction in academic research.From the current studies, researchers mainly try to construct the basic methods of spatial visual quality evaluation of commercial streets from different perspectives.For example, the visual attraction behavior of commercial streets is evaluated from three aspects of subjective, objective and visual influencing factors [9] .Provide design guidance through perceptual visual quality and detailed mapping of key elements in the street [10] ;Based on the characteristics of visual attraction behavior, the lighting design elements and requirements of commercial streets are discussed [11] .By collecting the data of the impact of street scenery on street space, the visual perception quality was evaluated [12] .A user-centered visual evaluation of the facades in the streets of historic blocks [13] ;Based on Street View image analysis, the visual quality of street space is scored [14] , etc.…”

Section: Evolution Of Evaluation Methods Of Commercial Street Space Designmentioning

confidence: 99%

Research on dynamic visual attraction evaluation method of commercial street based on eye movement perception

Guo

Weiqiang²,

et al. 2021

Journal of Asian Architecture and Building Engineering

View full text Add to dashboard Cite

Commercial streets play an essential role in urban public life, and their appearance constitutes an important visual attraction, which can attract people to form high-quality and active public spaces. However, in the traditional design analysis methods, limited by the existing evaluation tools, the key content of visual attractiveness analysis under dynamic conditions has rarely been paying attention to. Given this, this research adopts both objectivity and real-time eye movement perception technology to construct an evaluation method based on dynamic visual attractiveness-through the application of virtual reality technology to construct a virtual scene of a typical commercial street and detect the user's actions in it Eye movement at a time and physiological parameters such as the number of fixation points, fixation duration, and pupil diameter changes.This paper takes the main commercial street in Huanggaihu Town in Hubei Province of China as an example to analyze the visual attraction caused by different design methods.Therefore, from the four aspects of material, shape, line, and vegetation, design suggestions for the reasonable distribution of visual attractiveness in the commercial street space design are proposed to provide useful enlightenment for the vast towns' commercial street space design.

show abstract

“…From the perspective of urban planning and spatial design, inclusiveness, accessibility, user-friendly, and just right-of-way (ROW) are the principal qualities of future roads. Studies by Middel et al (2019), Cadamuro et al (2019) and Liu et al (2019) applied Deep Learning (DL) techniques to measure walkability, connectivity, greenery and other qualities of the street space. Equipped with advanced critical techniques from ITS, such as Roadside Units (RSUs) and fast-charging facilities, the future road space is likely to realise a wide range of automated scenes that used to be described in science fiction.…”

Section: Future Road Space and Complete Street Schemementioning

confidence: 99%

A Reinforcement Learning-based Adaptive Control Model for Future Street Planning An Algorithm and A Case Study

Ye¹,

Feng²,

Stettler³

et al. 2021

Proceedings of the 57th ISOCARP World Planning Congress

View full text Add to dashboard Cite

With the emerging technologies in Intelligent Transportation System (ITS), the adaptive operation of road space is likely to be realised within decades. An intelligent street can learn and improve its decision-making on the right-of-way (ROW) for road users, liberating more active pedestrian space while maintaining traffic safety and efficiency. However, there is a lack of effective controlling techniques for these adaptive street infrastructures. To fill this gap in existing studies, we formulate this control problem as a Markov Game and develop a solution based on the multi-agent Deep Deterministic Policy Gradient (MADDPG) algorithm. The proposed model can dynamically assign ROW for sidewalks, autonomous vehicles (AVs) driving lanes and on-street parking areas in realtime. Integrated with the SUMO traffic simulator, this model was evaluated using the road network of the South Kensington District against three cases of divergent traffic conditions: pedestrian flow rates, AVs traffic flow rates and parking demands. Results reveal that our model can achieve an average reduction of 3.87% and 6.26% in street space assigned for on-street parking and vehicular operations. Combined with space gained by limiting the number of driving lanes, the average proportion of sidewalks to total widths of streets can significantly increase by 10.13%.

show abstract

Large-Scale Street Space Quality Evaluation Based on Deep Learning Over Street View Image

Cited by 11 publications

References 16 publications

A New Data-Enabled Intelligence Framework for Evaluating Urban Space Perception

A New Data-Enabled Intelligence Framework for Evaluating Urban Space Perception

Research on dynamic visual attraction evaluation method of commercial street based on eye movement perception

A Reinforcement Learning-based Adaptive Control Model for Future Street Planning An Algorithm and A Case Study

Contact Info

Product

Resources

About