A Large Scale Urban Surveillance Video Dataset for Multiple-Object Tracking and Behavior Analysis

TL;DR

This paper introduces USVD, a large-scale, well-annotated urban surveillance video dataset designed to advance multiple-object tracking and behavior analysis in complex urban environments.

Contribution

The paper presents the largest and most comprehensive urban surveillance video dataset with extensive annotations across diverse scenarios for improved algorithm evaluation.

Findings

USVD contains over 200k frames and 3.7 million object bounding boxes.

The dataset enables evaluation of tracking and behavior analysis algorithms in congested urban scenes.

Performance of typical algorithms is assessed, highlighting robustness challenges in urban environments.

Abstract

Multiple-object tracking and behavior analysis have been the essential parts of surveillance video analysis for public security and urban management. With billions of surveillance video captured all over the world, multiple-object tracking and behavior analysis by manual labor are cumbersome and cost expensive. Due to the rapid development of deep learning algorithms in recent years, automatic object tracking and behavior analysis put forward an urgent demand on a large scale well-annotated surveillance video dataset that can reflect the diverse, congested, and complicated scenarios in real applications. This paper introduces an urban surveillance video dataset (USVD) which is by far the largest and most comprehensive. The dataset consists of 16 scenes captured in 7 typical outdoor scenarios: street, crossroads, hospital entrance, school gate, park, pedestrian mall, and public square. Over 200k video frames are annotated carefully, resulting in more than 3:7 million object bounding boxes and about 7:1 thousand trajectories. We further use this dataset to evaluate the performance of typical algorithms for multiple-object tracking and anomaly behavior analysis and explore the robustness of these methods in urban congested scenarios.