An Indoor Crowd Movement Trajectory Benchmark Dataset

TL;DR

This paper introduces a comprehensive indoor crowd movement trajectory dataset collected during a large academic conference, enabling improved research in indoor positioning, navigation, and behavior analysis.

Contribution

The paper provides a new publicly available benchmark dataset of indoor crowd trajectories, including diverse activities and anomalous events, with detailed ground truth and application insights.

Findings

Dataset covers over 5000 participants and various activities.

Evaluation of 75 contest entries demonstrates dataset's effectiveness.

Feedback indicates high usability and completeness of the dataset.

Abstract

In recent years, technologies of indoor crowd positioning and movement data analysis have received widespread attention in the fields of reliability management, indoor navigation, and crowd behavior monitoring. However, only a few indoor crowd movement trajectory datasets are available to the public, thus restricting the development of related research and application. This paper contributes a new benchmark dataset of indoor crowd movement trajectories. This dataset records the movements of over 5000 participants at a three day large academic conference in a two story indoor venue. The conference comprises varied activities, such as academic seminars, business exhibitions, a hacking contest, interviews, tea breaks, and a banquet. The participants are divided into seven types according to participation permission to the activities. Some of them are involved in anomalous events, such as loss of items, unauthorized accesses, and equipment failures, forming a variety of spatial temporal movement patterns. In this paper, we first introduce the scenario design, entity and behavior modeling, and data generator of the dataset. Then, a detailed ground truth of the dataset is presented. Finally, we describe the process and experience of applying the dataset to the contest of ChinaVis Data Challenge 2019. Evaluation results of the 75 contest entries and the feedback from 359 contestants demonstrate that the dataset has satisfactory completeness, and usability, and can effectively identify the performance of methods, technologies, and systems for indoor trajectory analysis.