Protik Bose Pranto
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Protik Bose Pranto has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Abimelec Mercado Rivera
Arizona State University, Tempe, Arizona, USA
1 shared publication Ariane Middel
Arizona State University
1 shared publicationIsaac Buo
Arizona State University
1 shared publication- Minhazul Islam
Arizona State University
1 shared publication - Namig Abbasov
School of Politics and Global Studies, Arizona State University, Tempe, AZ, USA
1 shared publication - Ripon Kumar Saha
Computer Engineering, Arizona State University, Tempe, Arizona, USA
1 shared publication
Latest Publications
- Open Access
- 17 November 2025
- Published by Wiley
WalkNet: A Vision-Based Framework for Mapping Urban Pedestrian Infrastructure
Pedestrian infrastructure is inadequately or inconsistently mapped in most cities, limiting efforts to assess walkability, accessibility, and equitable transportation systems. This study introduces WalkNet , a city-wide scalable framework that generates detailed, georeferenced pedestrian networks by integrating street-level imagery with open geospatial data. The framework applies a semantic segmentation model on panoramic images to extract sidewalks and roads, then computes a sidewalk-to-road height ratio as a geometric proxy for road type. It classifies roads as arterial, collector, or residential using the ratio, aligning with U.S. transportation codes. We implemented WalkNet in Phoenix, Arizona, a city with a diverse urban form. Using the Segment Anything model, Google Street View imagery, and OpenStreetMap, WalkNet achieved 78.2% overall road classification accuracy, 98.05% and 78.19% for arterial and residential roads, respectively. Collector roads showed high recall ( 96.43% ) but lower precision due to overlap with residential features. A manual evaluation confirmed that the representation of crosswalks, park trails, and informal footways in OpenStreetMap often does not match real-world conditions, highlighting key gaps in existing open pedestrian maps. The results show that visually derived metrics can support city-scale infrastructure mapping. Researchers and city planners can use the resulting data to support thermal comfort routing, walkability analyses, and climate-responsive urban planning. In addition, Walknet is a low-cost alternative to comprehensively map pedestrian infrastructure compared to classical field-surveying methods.
- 17 November 2025
- Published by Wiley
Open AccessWalkNet: A Vision-Based Framework for Mapping Urban Pedestrian Infrastructure
Pedestrian infrastructure is inadequately or inconsistently mapped in most cities, limiting efforts to assess walkability, accessibility, and equitable transportation systems. This study introduces WalkNet , a city-wide scalable framework that generates detailed, georeferenced pedestrian networks by integrating street-level imagery with open geospatial data. The framework applies a semantic segmentation model on panoramic images to extract sidewalks and roads, then computes a sidewalk-to-road height ratio as a geometric proxy for road type. It classifies roads as arterial, collector, or residential using the ratio, aligning with U.S. transportation codes. We implemented WalkNet in Phoenix, Arizona, a city with a diverse urban form. Using the Segment Anything model, Google Street View imagery, and OpenStreetMap, WalkNet achieved 78.2% overall road classification accuracy, 98.05% and 78.19% for arterial and residential roads, respectively. Collector roads showed high recall ( 96.43% ) but lower precision due to overlap with residential features. A manual evaluation confirmed that the representation of crosswalks, park trails, and informal footways in OpenStreetMap often does not match real-world conditions, highlighting key gaps in existing open pedestrian maps. The results show that visually derived metrics can support city-scale infrastructure mapping. Researchers and city planners can use the resulting data to support thermal comfort routing, walkability analyses, and climate-responsive urban planning. In addition, Walknet is a low-cost alternative to comprehensively map pedestrian infrastructure compared to classical field-surveying methods.
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6-16
From Hubs to Deserts: Urban Cultural Accessibility Patterns with Explainable AI
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6-16
Open AccessFrom Hubs to Deserts: Urban Cultural Accessibility Patterns with Explainable AI