In this project, we introduce an indoor crowd trajectory benchmark dataset, called ICMTD-2019. The background of the dataset is set in a three-day large fictitious international cyber security academic conference, which is well-referenced to academic conferences in the real-world. The conference comprises varied academic and social activities, such as academic seminars, business exhibitions, a hacking contest, interviews, tea breaks, and a banquet. This dataset captures the movements of over 5000 participants in a two-story indoor conference venue collected by smart badges worn by them. The participants are divided into seven types according to participation permissions to activities. Moreover, some of the participants are involved in anomalous events, such as loss of items, unauthorized accesses, and equipment failures, forming a variety of spatial–temporal movement patterns. Some of these events involve fine-grained spatial–temporal patterns and complex correlations. The dataset was used in ChinaVis Data Challenge 2019, with a total of 75 entries submitted by 359 contestants. Feedback from the contestants showed that the ICMTD-2019 dataset can effectively identify the performance of methods, techniques and systems for indoor crowd trajectory analysis.
A relevant study has been conducted by [Ying Zhao, Xin Zhao, Siming Chen, Zhuo Zhang, Xin Huang. An Indoor Crowd Movement Trajectory Benchmark Dataset[J]. IEEE Transactions on Reliability, Published 09/2021]. In addition, the paper and supplementary materials of this study are also provided.
- ICMTD-2019 dataset.
- Ground truth of the ICMTD-2019 dataset. (Note: Chapter 5 provides some samples of trajectory visualizations, which are added with additional random disturbances to make the visualizations realistic.)
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.
- Ying Zhao, Xin Zhao, Siming Chen, Zhuo Zhang, Xin Huang. An Indoor Crowd Movement Trajectory Benchmark Dataset[J]. IEEE Transactions on Reliability, 70(4):1368-1380,2021. DOI: 10.1109/TR.2021.3109122.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent