Revisiting Convolutional Neural Networks for Urban Flow Analytics

by   Yuxuan Liang, et al.
National University of Singapore

Convolutional Neural Networks (CNNs) have been widely adopted in raster-based urban flow analytics by virtue of their capability in capturing nearby spatial context. By revisiting CNN-based methods for different analytics tasks, we expose two common critical drawbacks in the existing uses: 1) inefficiency in learning global context, and 2) overlooking latent region functions. To tackle these challenges, in this paper we present a novel framework entitled DeepLGR that can be easily generalized to address various urban flow analytics problems. This framework consists of three major parts: 1) a local context module to learn local representations of each region; 2) a global context module to extract global contextual priors and upsample them to generate the global features; and 3) a region-specific predictor based on tensor decomposition to provide customized predictions for each region, which is very parameter-efficient compared to previous methods. Extensive experiments on two typical urban analytics tasks demonstrate the effectiveness, stability, and generality of our framework.


page 1

page 2

page 3

page 4


Urban Region Profiling via A Multi-Graph Representation Learning Framework

Urban region profiling can benefit urban analytics. Although existing st...

A Contextual Master-Slave Framework on Urban Region Graph for Urban Village Detection

Urban villages (UVs) refer to the underdeveloped informal settlement fal...

Efficient Hybrid Transformer: Learning Global-local Context for Urban Sence Segmentation

Semantic segmentation of fine-resolution urban scene images plays a vita...

Scene Parsing with Global Context Embedding

We present a scene parsing method that utilizes global context informati...

Permutohedral Attention Module for Efficient Non-Local Neural Networks

Medical image processing tasks such as segmentation often require captur...

Extremal Region Analysis based Deep Learning Framework for Detecting Defects

A maximally stable extreme region (MSER) analysis based convolutional ne...

Urban Analytics: History, Trajectory, and Critique

Urban analytics combines spatial analysis, statistics, computer science,...

Please sign up or login with your details

Forgot password? Click here to reset