Hybrid Congestion Classification Framework Using Flow-Guided Attention and Empirical Mode Decomposition

TL;DR

This paper introduces FLO-EMD, a hybrid traffic congestion classification framework that combines motion-guided attention with empirical mode decomposition to improve accuracy and robustness across diverse conditions.

Contribution

It presents a novel unified approach that links motion evidence to spatial feature selection and uses data-driven temporal decomposition for congestion classification.

Findings

Achieves 97.5% overall test accuracy on surveillance data.

Outperforms established baseline methods in congestion classification.

Demonstrates robustness across diverse environmental conditions.

Abstract

Accurate traffic congestion classification requires models that jointly capture roadway scene context and non-stationary traffic motion, yet most prior work treats these requirements in isolation. Vision-based methods often depend on appearance cues with standard temporal pooling, which can bias predictions toward static infrastructure, whereas signal-based approaches characterize temporal dynamics but lack the spatial context needed for scene-level localization. These complementary limitations motivate a unified framework that links motion evidence to spatial feature selection while preserving data-adaptive temporal characterization. This study therefore proposes FLO-EMD, a hybrid approach that couples motion-guided attention with empirical, data-driven temporal decomposition. Dense optical flow guides channel and spatial attention so that RGB features are refined toward motion-relevant regions. In parallel, aggregated flow statistics form compact motion traces that are decomposed using Empirical Mode Decomposition (EMD) to extract intrinsic temporal components. The resulting EMD embedding is fused with learned spatiotemporal representations to classify light, medium, and heavy congestion. Experiments on 1,050 five-second clips from four surveillance networks show that FLO-EMD achieves 97.5% overall test accuracy (weighted F1 = 0.9742), outperforming established baselines and remaining robust across diverse environmental conditions; ablation and sensitivity analyses further quantify the contributions of EMD, the number of intrinsic mode functions, and the selected motion descriptors.