Multimodal Urban Areas of Interest Generation via Remote Sensing Imagery and Geographical Prior

TL;DR

This paper introduces AOITR, a multimodal deep learning framework that accurately detects urban AOI boundaries using remote sensing imagery and geographical priors, addressing the need for precise, real-time AOI data for O2O businesses.

Contribution

The paper presents a novel transformer-based multimodal approach for AOI detection that integrates remote sensing and geographical data, outperforming traditional segmentation methods.

Findings

Achieves higher IoU scores than previous methods.

Effectively validates AOI reliability using dynamic human mobility data.

Provides precise AOI boundaries suitable for O2O business needs.

Abstract

Urban area-of-interest (AOI) refers to an integrated urban functional zone with defined polygonal boundaries. The rapid development of urban commerce has led to increasing demands for highly accurate and timely AOI data. However, existing research primarily focuses on coarse-grained functional zones for urban planning or regional economic analysis, and often neglects the expiration of AOI in the real world. They fail to fulfill the precision demands of Mobile Internet Online-to-Offline (O2O) businesses. These businesses require accuracy down to a specific community, school, or hospital. In this paper, we propose a comprehensive end-to-end multimodal deep learning framework designed for simultaneously detecting accurate AOI boundaries and validating the reliability of AOI by leveraging remote sensing imagery coupled with geographical prior, titled AOITR. Unlike conventional AOI generation methods, such as the Road-cut method that segments road networks at various levels, our approach diverges from semantic segmentation algorithms that depend on pixel-level classification. Instead, our AOITR begins by selecting a point-of-interest (POI) of specific category, and uses it to retrieve corresponding remote sensing imagery and geographical prior such as entrance POIs and road nodes. This information helps to build a multimodal detection model based on transformer encoder-decoder architecture to regress the AOI polygon. Additionally, we utilize the dynamic features from human mobility, nearby POIs, and logistics addresses for AOI reliability evaluation via a cascaded network module. The experimental results reveal that our algorithm achieves a significant improvement on Intersection over Union (IoU) metric, surpassing previous methods by a large margin.