FlowDet: Overcoming Perspective and Scale Challenges in Real-Time End-to-End Traffic Detection

TL;DR

FlowDet introduces a high-speed, efficient traffic detection model that effectively handles perspective and scale challenges in real-time, outperforming existing methods on a new challenging dataset.

Contribution

The paper proposes FlowDet, a novel traffic detector with geometric and scale-aware modules, and introduces the Intersection-Flow-5k dataset for rigorous evaluation.

Findings

Achieves 1.5% higher AP than RT-DETR on Intersection-Flow-5k.

Reduces GFLOPs by 63.2%, increasing inference speed.

Performs well under severe occlusion and high object density.

Abstract

End-to-end object detectors offer a promising NMS-free paradigm for real-time applications, yet their high computational cost remains a significant barrier, particularly for complex scenarios like intersection traffic monitoring. To address this challenge, we propose FlowDet, a high-speed detector featuring a decoupled encoder optimization strategy applied to the DETR architecture. Specifically, FlowDet employs a novel Geometric Deformable Unit (GDU) for traffic-aware geometric modeling and a Scale-Aware Attention (SAA) module to maintain high representational power across extreme scale variations. To rigorously evaluate the model's performance in environments with severe occlusion and high object density, we collected the Intersection-Flow-5k dataset, a new challenging scene for this task. Evaluated on Intersection-Flow-5k, FlowDet establishes a new state-of-the-art. Compared to the strong RT-DETR baseline, it improves AP(test) by 1.5% and AP50(test) by 1.6%, while simultaneously reducing GFLOPs by 63.2% and increasing inference speed by 16.2%. Our work demonstrates a new path towards building highly efficient and accurate detectors for demanding, real-world perception systems. The Intersection-Flow-5k dataset is available at https://github.com/AstronZh/Intersection-Flow-5K.