Dynamic Grid-Based Spatial Density Visualization and Rail Transit Station Prediction

Cai, Zhi; Ji, Meilin; Mi, Qing; Yang, Bowen; Su, Xing; Guo, Limin; Ding, Zhiming

doi:10.3390/ijgi10120804

Cited by 4 publications

(1 citation statement)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By "vector road mapping", it refers to a process of converting the road features presented in satellite-borne remote sensing images into vector-based and symbolic graph representations, which is also known as road graph extraction or road network extraction within the community of remote sensing and plays a fundamental role in numerous downstream tasks including navigation (Zhang et al 2021;Cai et al 2023), urban planning (Shi et al 2019;Xu et al 2023a), and autonomous driving (Xu, Sun, and Liu 2021;He and Balakrishnan 2022;Büchner et al 2023).…”

Section: Introductionmentioning

confidence: 99%

Patched Line Segment Learning for Vector Road Mapping

Xu,

Xia

et al. 2024

AAAI

View full text Add to dashboard Cite

This paper presents a novel approach to computing vector road maps from satellite remotely sensed images, building upon a well-defined Patched Line Segment (PaLiS) representation for road graphs that holds geometric significance. Unlike prevailing methods that derive road vector representations from satellite images using binary masks or keypoints, our method employs line segments. These segments not only convey road locations but also capture their orientations, making them a robust choice for representation. More precisely, given an input image, we divide it into non-overlapping patches and predict a suitable line segment within each patch. This strategy enables us to capture spatial and structural cues from these patch-based line segments, simplifying the process of constructing the road network graph without the necessity of additional neural networks for connectivity. In our experiments, we demonstrate how an effective representation of a road graph significantly enhances the performance of vector road mapping on established benchmarks, without requiring extensive modifications to the neural network architecture. Furthermore, our method achieves state-of-the-art performance with just 6 GPU hours of training, leading to a substantial 32-fold reduction in training costs in terms of GPU hours.

show abstract