Spatial-Temporal Multi-Cuts for Online Multiple-Camera Vehicle Tracking

TL;DR

This paper presents a novel spatial-temporal clustering method for online multi-camera vehicle tracking that improves accuracy and efficiency without scene-specific training, outperforming state-of-the-art methods on benchmark datasets.

Contribution

Introduces a unified graph-based clustering approach for online multi-camera vehicle tracking that combines spatial and temporal data in a single step, reducing errors and computational costs.

Findings

Outperforms online state-of-the-art on CityFlow dataset by over 14% in IDF1.

Achieves more than 25% improvement on Synthehicle dataset.

Does not require scene-specific training or additional annotations.

Abstract

Accurate online multiple-camera vehicle tracking is essential for intelligent transportation systems, autonomous driving, and smart city applications. Like single-camera multiple-object tracking, it is commonly formulated as a graph problem of tracking-by-detection. Within this framework, existing online methods usually consist of two-stage procedures that cluster temporally first, then spatially, or vice versa. This is computationally expensive and prone to error accumulation. We introduce a graph representation that allows spatial-temporal clustering in a single, combined step: New detections are spatially and temporally connected with existing clusters. By keeping sparse appearance and positional cues of all detections in a cluster, our method can compare clusters based on the strongest available evidence. The final tracks are obtained online using a simple multicut assignment procedure. Our method does not require any training on the target scene, pre-extraction of single-camera tracks, or additional annotations. Notably, we outperform the online state-of-the-art on the CityFlow dataset in terms of IDF1 by more than 14%, and on the Synthehicle dataset by more than 25%, respectively. The code is publicly available.