• Corpus ID: 238215381

Road Network Guided Fine-Grained Urban Traffic Flow Inference

@article{Liu2021RoadNG,
  title={Road Network Guided Fine-Grained Urban Traffic Flow Inference},
  author={Lingbo Liu and Mengmeng Liu and Guanbin Li and Ziyi Wu and Liang Lin},
  journal={ArXiv},
  year={2021},
  volume={abs/2109.14251}
}
Accurate inference of fine-grained traffic flow from coarse-grained one is an emerging yet crucial problem, which can help greatly reduce the number of traffic monitoring sensors for cost savings. In this work, we notice that traffic flow has a high correlation with road network, which was either completely ignored or simply treated as an external factor in previous works. To facilitate this problem, we propose a novel RoadAware Traffic Flow Magnifier (RATFM) that explicitly exploits the prior… 

Aerial Images Meet Crowdsourced Trajectories: A New Approach to Robust Road Extraction.

TLDR
A novel neural network framework termed cross-modal message propagation network (CMMPNet) is introduced, which fully benefits the complementary different modal data (i.e., aerial images and crowdsourced trajectories), and outperforms current state-of-the-art methods by large margins.

Deep Learning in Traffic Flow Control and Prediction for Traffic Management

TLDR
It was concluded that the improved FCM clustering approach works exceptionally well in determining urban traffic state and is very much feasible.

Online Metro Origin-Destination Prediction via Heterogeneous Information Aggregation

TLDR
A novel neural network module termed Heterogeneous Information Aggregation Machine (HIAM) is proposed, which fully exploits heterogeneous information of historical data to jointly learn the evolutionary patterns of OD andDO ridership, and a unified Seq2Seq network is developed to forecast the future OD and DO ridership simultaneously.

References

SHOWING 1-10 OF 46 REFERENCES

UrbanFM: Inferring Fine-Grained Urban Flows

TLDR
This paper aims to infer the real-time and fine-grained crowd flows throughout a city based on coarse- grained observations, and develops a method entitled UrbanFM based on deep neural networks that achieves state-of-the-art performance on this problem.

Fine-Grained Urban Flow Inference

TLDR
UrbanPy is presented, a cascading model for progressive inference of fine-grained urban flows by decomposing the original tasks into multiple subtasks that demonstrates favorable performance for larger-scale inference tasks.

Fine-Grained Urban Flow Prediction

TLDR
This work presents a Spatio-Temporal Relation Network (STRN), a Global Relation Module (GloNet) that captures global spatial dependencies much more efficiently compared to existing methods, and a Meta Learner that takes external factors and land functions as inputs to produce meta knowledge and boost model performances.

Attentive Crowd Flow Machines

TLDR
A unified neural network module, called Attentive Crowd Flow Machine~ (ACFM), which is able to infer the evolution of the crowd flow by learning dynamic representations of temporally-varying data with an attention mechanism, and achieves significant improvements over the state-of-the-art methods.

Dynamic Spatial-Temporal Representation Learning for Traffic Flow Prediction

TLDR
Two deep learning frameworks are developed to predict citywide short-term/long-term traffic flow by adaptively incorporating the sequential and periodic data as well as other external influences using the proposed Attentive Traffic Flow Machine.

Deep Spatial–Temporal 3D Convolutional Neural Networks for Traffic Data Forecasting

TLDR
A novel end-to-end deep learning model, called ST-3DNet, is proposed, which introduces 3D convolutions to automatically capture the correlations of traffic data in both spatial and temporal dimensions and a novel recalibration block is proposed to explicitly quantify the difference of the contributions of the correlations in space.

Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting

TLDR
It is argued that learning node-specific patterns is essential for traffic forecasting while the pre-defined graph is avoidable, and two adaptive modules for enhancing Graph Convolutional Network (GCN) with new capabilities are proposed.

Learning Dynamics and Heterogeneity of Spatial-Temporal Graph Data for Traffic Forecasting

TLDR
A novel self-attention mechanism that is capable of utilizing the local context and specialized for numerical sequence representation transformation enables the prediction model to capture the temporal dynamics of traffic data and to enjoy global receptive elds that is beneficial for long-term forecast.

Efficient Crowd Counting via Structured Knowledge Transfer

TLDR
A novel Structured Knowledge Transfer (SKT) framework, which fully exploits the structured knowledge of a well-trained teacher network to generate a lightweight but still highly effective student network that can derive the layer-wise and cross-layer knowledge from the teacher networkto learn compact yet effective features.

Traffic Incident Detection: A Trajectory-based Approach

TLDR
This paper studies how to obtain incident patterns from trajectories and devise a new solution (called Filter-Discovery-Match (FDM) to detect anomalies in sparse traffic data and shows that FDM is more effective than state-of-the-art ID solutions on sparse trafficData.