Quantifying Urban Surroundings Using Deep Learning Techniques: A New Proposal

Verma, Deepank; Jana, Arnab; Ramamritham, Krithi

doi:10.3390/urbansci2030078

Cited by 11 publications

(5 citation statements)

References 43 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As street view images reflect the street space environment from eye-level perspective, online data acquisition can replace other data collection methods that are limited by weather, time and place. Street view data can be analysed using machine learning techniques using SegNet (Badrinarayanan et al, 2017;Verma et al, 2018), semantic annotation tools that identify green, sky, buildings, roads and vehicles. These urban elements can then be represented and assessed through interactive visual analysis systems.…”

Section: Quantitative Evaluation Of Street Qualitiesmentioning

confidence: 99%

Proceedings of the 27th Conference on Computer Aided Architectural Design Research in Asia (CAADRIA) [Volume 1]

2022

CAADRIA Proceedings

View full text Add to dashboard Cite

The work collected in these volumes has been produced during extraordinary circumstances, as the Covid-19 pandemic has continued to impact working and living conditions. Papers have been written, reviewed and edited throughout lockdowns, challenging family situations and health crises. The high number of submissions and quality of the papers is a testament to the resilience and strength of the CAADRIA community.The papers in this publication have been selected through a two-stage, doubleblind peer review process. All reviews and papers have been evaluated by the Paper Selection Committee. After receiving an initial 488 abstract submissions, a final set of 150 full papers has been selected for publication. We thank all authors for their contributions to the process and congratulate the accepted paper authors.The papers in these proceedings are specifically selected for their contribution to this year's conference theme, following the conference organisers' call for authors to position their work in relation to the United Nations Sustainable Development Goals (SDGs). As the world is experiencing the increasing impacts of climate change, there is an urgent need to reflect on the potential of the latest research in architecture, urbanism and construction to address these global challenges.Our special thanks go out to our more than 180 international reviewers, who volunteered their valuable time and effort. We also thank the organising team in Sydney for developing the 2022 CAADRIA Conference as a strong collaborative effort between academic institutions, industry and practice. We thank Gabriel Wurzer for his support during the proceedings' final production stage, and for facilitating their publication via the open access database CumInCAD.org. Finally, we sincerely thank the CAADRIA community for offering us the honour to serve as members of the paper selection committee for Post-Carbon, the 27 th International CAADRIA Conference 2022.

show abstract

Section: Quantitative Evaluation Of Street Qualitiesmentioning

confidence: 99%

Proceedings of the 27th Conference on Computer Aided Architectural Design Research in Asia (CAADRIA) [Volume 1]

2022

CAADRIA Proceedings

View full text Add to dashboard Cite

show abstract

“…Chen et al [6] extracted and integrated features of inner London using geotagged Flickr photographs, and explored the characteristic differences and the dynamics of areas where more people assemble [7]. Verma et al [8,9] developed a mobile application to collect visual and audio datasets including the characteristics of the urban street fluctuating with time, and extracted the attributes of urban areas using various computer algorithms. Kim et al [10] used a Tobit regression model to analyze the physical environmental factors affecting walking.…”

Section: Introductionmentioning

confidence: 99%

Spatial Image-Based Walkability Evaluation Using Regression Model

Hwang,

Nam,

Lee

2024

Applied Sciences

View full text Add to dashboard Cite

Governments worldwide have invested considerable money and time into creating pedestrian-oriented urban environments. However, generalizing arbitrary standards for walking environments is challenging. Therefore, this study presents a method for predicting walkability scores of evaluations using five regression models, including Multiple linear, Ridge, LASSO regression, SVR, and XGBoost. The models were trained using semantic segmentation, walkability evaluations based on crowdsourcing, and image scores obtained using the TrueSkill algorithm, and their performances were compared. Feature selection was employed to improve the accuracies of the models, which were retrained using the importance of extracted features. Among the five regression models, XGBoost, a tree-based regression model, exhibited the lowest error rate, high accuracy, and greatest performance improvement after retraining. This study is expected to generalize the walking environments preferred by various people and demonstrate that objective walkability evaluations are possible through a computer system rather than through subjective human judgment.

show abstract

“…Machine learning plays a pivotal role in urban planning and development [1][2][3]. Particularly, semantic segmentation [4,5] can serve as a foundational technology in applications ranging from smart city design to environmental monitoring.…”

Section: Introductionmentioning

confidence: 99%

Urban Aquatic Scene Expansion for Semantic Segmentation in Cityscapes

Yue,

Lo,

et al. 2024

Urban Science

View full text Add to dashboard Cite

In urban environments, semantic segmentation using computer vision plays a pivotal role in understanding and interpreting the diverse elements within urban imagery. The Cityscapes dataset, widely used for semantic segmentation in urban scenes, predominantly features urban elements like buildings and vehicles but lacks aquatic elements. Recognizing this limitation, our study introduces a method to enhance the Cityscapes dataset by incorporating aquatic classes, crucial for a comprehensive understanding of coastal urban environments. To achieve this, we employ a dual-model approach using two advanced neural networks. The first network is trained on the standard Cityscapes dataset, while the second focuses on aquatic scenes. We adeptly integrate aquatic features from the marine-focused model into the Cityscapes imagery. This integration is carefully executed to ensure a seamless blend of urban and aquatic elements, thereby creating an enriched dataset that reflects the realities of coastal cities more accurately. Our method is evaluated by comparing the enhanced Cityscapes model with the original on a set of diverse urban images, including aquatic views. The results demonstrate that our approach effectively maintains the high segmentation accuracy of the original Cityscapes dataset for urban elements while successfully integrating marine features. Importantly, this is achieved without necessitating additional training, which is a significant advantage in terms of resource efficiency.

show abstract

Quantifying Urban Surroundings Using Deep Learning Techniques: A New Proposal

Cited by 11 publications

References 43 publications

Proceedings of the 27th Conference on Computer Aided Architectural Design Research in Asia (CAADRIA) [Volume 1]

Proceedings of the 27th Conference on Computer Aided Architectural Design Research in Asia (CAADRIA) [Volume 1]

Spatial Image-Based Walkability Evaluation Using Regression Model

Urban Aquatic Scene Expansion for Semantic Segmentation in Cityscapes

Contact Info

Product

Resources

About