Smart curbs: Measuring street activities in real-time using computer vision

Miranda, Arianna Salazar; Zhang, Fan; Sun, Maoran; Leoni, Pietro; Duarte, Fábio; Ratti, Carlo

doi:10.1016/j.landurbplan.2023.104715

Cited by 12 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It represents a combination of spatial and temporal attributes at a particular moment. While the application of this analysis in the interior environment is relatively less common compared to other scenarios like urban transport, tourism, climate environment and public health [52][53][54][55], there exists significant potential for employing this method to analyse spatial and temporal patterns of human behaviour within indoor environments, as demonstrated in this study.…”

Section: Plos Onementioning

confidence: 99%

Future workspace needs flexibility and diversity: A machine learning-driven behavioural analysis of co-working space

Pan,

Cho,

Sun

et al. 2023

PLoS ONE

Self Cite

View full text Add to dashboard Cite

The future of workspace is significantly shaped by the advancements in technologies, changes in work patterns and workers’ desire for an improved well-being. Co-working space is an alternative workspace solution, for cost-effectiveness, the opportunity for diverse and flexible design and multi-use. This study examined the human-centric design choices using spatial and temporal variation of occupancy levels and user behaviour in a flexible co-working space in London. Through a machine-learning-driven analysis, we investigated the time-dependent patterns, decompose space usage, calculate seat utilisation and identify spatial hotspots. The analysis incorporated a large dataset of sensor-detected occupancy data spanning 477 days, comprising more than 140 million (145×106) data points. Additionally, on-site observations of activities were recorded for 13 days spanning over a year, with 110 time instances including more than 1000 snapshots of occupants’ activities, indoor environment, working behaviour and preferences. Results showed that the shared working areas positioned near windows or in more open, connected and visible locations are significantly preferred and utilised for communication and working, and semi-enclosed space on the side with less visibility and higher privacy are preferred for focused working. The flexibility of multi-use opportunity was the most preferred feature for hybrid working. The findings offer data-driven insights for human-centric space planning and design of office spaces in the future, particularly in the context of hybrid working setups, hot-desking and co-working systems.

show abstract

Section: Plos Onementioning

confidence: 99%

Future workspace needs flexibility and diversity: A machine learning-driven behavioural analysis of co-working space

Pan,

Cho,

Sun

et al. 2023

PLoS ONE

Self Cite

View full text Add to dashboard Cite

show abstract

“…It allows automated and large-scale street quality research [3,[14][15][16]. The emergence of high-precision open data such as road networks [17], points of interest [18], and three-dimensional (3D) buildings [19,20] also provides new methods for quantitative analysis of street quality. In addition, the development of machine learning, deep learning and other technologies in the computer science field further provides the possibility for quantitative study of street space.…”

Section: Introductionmentioning

confidence: 99%

Spatial Quality Measurement and Characterization of Daily High-Frequency Pedestrian Streets in Xi’an City

Liu,

Tu,

Sun

et al. 2024

Land

Self Cite

View full text Add to dashboard Cite

Street space plays a crucial role in human activity and social life, forming an essential component of a livable and sustainable built environment. Consequently, its quality has garnered significant attention from researchers, designers, and policymakers who aim to achieve precise assessments of street infrastructure and conditions. This study presents a multi-dimensional framework for evaluating street space, considering factors such as access frequency, environmental quality, and amenity richness. By utilizing city-level path planning data, street view imagery, point of interest data, and social media check-in data, this framework assesses each street and assigns scores across these dimensions. These scores facilitate a human-centered analysis of the disparities in street usage and quality. The aggregation of results by administrative regions supports effective policy formulation and implementation. Application of this framework in Xi’an, China, reveals that only 6.95% of frequently visited streets exhibit high environmental quality and functional richness. This study underscores the potential of leveraging public data for detailed street space assessments to inform urban renewal policies.

show abstract

“…The objective and quantitative evaluation of the SPF and the observation of the SPU are of great significance in the process of reshaping street walking space and improving the resilience of urban space in the new era of urban space creation [14,15]. However, the reality is that the imperfect quantitative evaluation system of SPF and the lack of evaluation system of SPU hinder the understanding of what unfriendly elements exist in streets, what is not usable and how to improve street walkable spaces to build humane cities.…”

Section: Introductionmentioning

confidence: 99%

Quantitative Evaluation of Friendliness in Streets’ Pedestrian Networks Based on Complete Streets: A Case Study in Wuhan, China

Ma,

Jiao

2023

Sustainability

View full text Add to dashboard Cite

In recent years, with the rapid growth in the number of cars, the safe and convenient street pedestrian traffic network in cities has been broken by motor vehicle lanes. The pedestrian traffic function of streets as an important urban public space has been lost, and the pedestrian friendliness of streets needs urgent improvement. However, the existing pedestrian-friendly street space assessment has not yet formed a set of full-factor quantitative evaluation systems, making the construction of pedestrian-friendly streets still in the conceptual stage and lacking practical significance. The complete streets design concept clarifies the goal of street pedestrian space construction and proposes the full elements of street pedestrian space design, which provides important support for the construction of the street pedestrian friendliness evaluation system. Based on the complete streets design concept, this study constructs a complete set of quantitative evaluation systems of street walkability from three aspects of street space: traffic, environment and function. Meanwhile, a street pedestrian usability evaluation method is proposed to further explore the actual demand of streets. Combined with the comprehensive evaluation matrix of street pedestrian friendliness and usability, the areas where the planning of street pedestrian space does not match with the actual space are explored. The case study in Wuhan found that the overall pedestrian friendliness was high in the area, but there was significant variability. The study area is dominated by streets in need of improvement, with medium demand–low friendliness, and both the pedestrian friendliness and usability of the streets need to be improved.

show abstract

Smart curbs: Measuring street activities in real-time using computer vision

Cited by 12 publications

References 18 publications

Future workspace needs flexibility and diversity: A machine learning-driven behavioural analysis of co-working space

Future workspace needs flexibility and diversity: A machine learning-driven behavioural analysis of co-working space

Spatial Quality Measurement and Characterization of Daily High-Frequency Pedestrian Streets in Xi’an City

Quantitative Evaluation of Friendliness in Streets’ Pedestrian Networks Based on Complete Streets: A Case Study in Wuhan, China

Contact Info

Product

Resources

About