CityTrack: Improving City-Scale Multi-Camera Multi-Target Tracking by Location-Aware Tracking and Box-Grained Matching

TL;DR

CityTrack is a novel multi-camera multi-target tracking framework that enhances urban traffic analysis by integrating location-aware tracking and box-grained matching, achieving state-of-the-art results on CityFlowV2.

Contribution

The paper introduces CityTrack, a systematic MCMT framework with a location-aware tracker and a novel box-grained matching method for improved accuracy in urban traffic scenes.

Findings

Achieved an IDF1 of 84.91% on CityFlowV2 dataset.

Ranked 1st in the 2022 AI CITY CHALLENGE.

Demonstrated effectiveness in complex urban traffic scenarios.

Abstract

Multi-Camera Multi-Target Tracking (MCMT) is a computer vision technique that involves tracking multiple targets simultaneously across multiple cameras. MCMT in urban traffic visual analysis faces great challenges due to the complex and dynamic nature of urban traffic scenes, where multiple cameras with different views and perspectives are often used to cover a large city-scale area. Targets in urban traffic scenes often undergo occlusion, illumination changes, and perspective changes, making it difficult to associate targets across different cameras accurately. To overcome these challenges, we propose a novel systematic MCMT framework, called CityTrack. Specifically, we present a Location-Aware SCMT tracker which integrates various advanced techniques to improve its effectiveness in the MCMT task and propose a novel Box-Grained Matching (BGM) method for the ICA module to solve the aforementioned problems. We evaluated our approach on the public test set of the CityFlowV2 dataset and achieved an IDF1 of 84.91%, ranking 1st in the 2022 AI CITY CHALLENGE. Our experimental results demonstrate the effectiveness of our approach in overcoming the challenges posed by urban traffic scenes.