PathwayBench: Assessing Routability of Pedestrian Pathway Networks Inferred from Multi-City Imagery
Abstract: Applications to support pedestrian mobility in urban areas require a complete, and routable graph representation of the built environment. Globally available information, including aerial imagery provides a scalable source for constructing these path networks, but the associated learning problem is challenging: Relative to road network pathways, pedestrian network pathways are narrower, more frequently disconnected, often visually and materially variable in smaller areas, and their boundaries are broken up by driveway incursions, alleyways, marked or unmarked crossings through roadways. Existing algorithms to extract pedestrian pathway network graphs are inconsistently evaluated and tend to ignore routability, making it difficult to assess utility for mobility applications: Even if all path segments are available, discontinuities could dramatically and arbitrarily shift the overall path taken by a pedestrian. In this paper, we describe a first standard benchmark for the pedestrian pathway graph extraction problem, comprising the largest available dataset equipped with manually vetted ground truth annotations (covering $3,000 km2$ land area in regions from 8 cities), and a family of evaluation metrics centering routability and downstream utility. By partitioning the data into polygons at the scale of individual intersections, we compute local routability as an efficient proxy for global routability. We consider multiple measures of polygon-level routability and compare predicted measures with ground truth to construct evaluation metrics. Using these metrics, we show that this benchmark can surface strengths and weaknesses of existing methods that are hidden by simple edge-counting metrics over single-region datasets used in prior work, representing a challenging, high-impact problem in computer vision and machine learning.
- Zebra crossing spotter: Automatic population of spatial databases for increased safety of blind travelers. In Proceedings of the 17th International ACM SIGACCESS Conference on Computers & Accessibility. 251–258.
- Performance evaluation of building detection and digital surface model extraction algorithms: Outcomes of the PRRS 2008 algorithm performance contest. In 2008 IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS 2008). IEEE, 1–12.
- Nicholas Bolten and Anat Caspi. 2021. Towards routine, city-scale accessibility metrics: Graph theoretic interpretations of pedestrian access using personalized pedestrian network analysis. PLoS one 16, 3 (2021), e0248399.
- Nicholas Bolten and Anat Caspi. 2022. Towards operationalizing the communal production and management of public (open) data: a pedestrian network case study: A pedestrian network case study in operationalizing communal open data. In ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies (COMPASS). 232–247.
- Nicholas Bolten and Anat Caspi. 2023. The OpenSidewalks Schema. https://github.com/opensidewalks/OpenSidewalks-Schema
- A pedestrian-centered data approach for equitable access to urban infrastructure environments. IBM Journal of Research and Development 61, 6 (2017), 10–1.
- Ulrik Brandes. 2001. A faster algorithm for betweenness centrality. Journal of mathematical sociology 25, 2 (2001), 163–177.
- Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017).
- DeepGlobe 2018: A Challenge to Parse the Earth Through Satellite Images. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops.
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv preprint arXiv:2010.11929 (2020).
- Crosswalk localization from low resolution satellite images to assist visually impaired people. IEEE computer graphics and applications 38, 1 (2016), 30–46.
- Mordechai Haklay and Patrick Weber. 2008. Openstreetmap: User-generated street maps. IEEE Pervasive Computing 7, 4 (2008), 12–18.
- Mapping the walk: A scalable computer vision approach for generating sidewalk network datasets from aerial imagery. Computers, Environment and Urban Systems 101 (2023), 101950.
- Qing Hou and Chengbo Ai. 2020. A network-level sidewalk inventory method using mobile LiDAR and deep learning. Transportation research part C: emerging technologies 119 (2020), 102772.
- ISPRS. 2022. ISPRS Test Project on Urban Classification, 3D Building Reconstruction and Semantic Labeling. https://www.isprs.org/education/benchmarks/UrbanSemLab/default.aspx
- Eun Seo Jo and Timnit Gebru. 2020. Lessons from archives: Strategies for collecting sociocultural data in machine learning. In Proceedings of the 2020 conference on fairness, accountability, and transparency. 306–316.
- Hassan A Karimi and Piyawan Kasemsuppakorn. 2013. Pedestrian network map generation approaches and recommendation. International Journal of Geographical Information Science 27, 5 (2013), 947–962.
- A semi-automated method to generate GIS-based sidewalk networks for asset management and pedestrian accessibility assessment. Transportation research record 2672, 44 (2018), 1–9.
- A generalized framework for measuring pedestrian accessibility around the world using open data. Geographical Analysis 54, 3 (2022), 559–582.
- GAMSNet: Globally aware road detection network with multi-scale residual learning. ISPRS Journal of Photogrammetry and Remote Sensing 175 (2021), 340–352.
- Deeproadmapper: Extracting road topology from aerial images. In Proceedings of the IEEE international conference on computer vision. 3438–3446.
- HDMapGen: A hierarchical graph generative model of high definition maps. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 4227–4236.
- Sidewalk extraction using aerial and street view images. Environment and Planning B: Urban Analytics and City Science 49, 1 (2022), 7–22.
- A generic FCN-based approach for the road-network extraction from VHR remote sensing images–using openstreetmap as benchmarks. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 14 (2021), 2662–2673.
- Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014).
- Leveraging crowdsourced GPS data for road extraction from aerial imagery. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7509–7518.
- Antonio Torralba and Alexei A Efros. 2011. Unbiased look at dataset bias. In CVPR 2011. IEEE, 1521–1528.
- Torontocity: Seeing the world with a million eyes. arXiv preprint arXiv:1612.00423 (2016).
- Predictive inequity in object detection. arXiv preprint arXiv:1902.11097 (2019).
- Road extraction from very high resolution images using weakly labeled OpenStreetMap centerline. ISPRS International Journal of Geo-Information 8, 11 (2019), 478.
- APE: An Open and Shared Annotated Dataset for Learning Urban Pedestrian Path Networks. arXiv preprint arXiv:2303.02323 (2023).
- Collecting Sidewalk Network Data at Scale for Accessible Pedestrian Travel. In The 23rd International ACM SIGACCESS Conference on Computers and Accessibility. 1–4.
- FuNet: A novel road extraction network with fusion of location data and remote sensing imagery. ISPRS International Journal of Geo-Information 10, 1 (2021), 39.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.