Duke MTMC
[ page under development ]
The Duke Multi-Target, Multi-Camera Tracking Dataset (MTMC) is a dataset of video recorded on Duke University campus for research and development of networked camera surveillance systems. MTMC tracking is used for citywide dragnet surveillance systems such as those used throughout China by SenseTime 1 and the oppressive monitoring of 2.5 million Uyghurs in Xinjiang by SenseNets 2. In fact researchers from both SenseTime 4 5 and SenseNets 3 used the Duke MTMC dataset for their research.
The Duke MTMC dataset is unique because it is the largest publicly available MTMC and person re-identification dataset and has the longest duration of annotated video. In total, the Duke MTMC dataset provides over 14 hours of 1080p video from 8 synchronized surveillance cameras. 6 It is among the most widely used person re-identification datasets in the world. The approximately 2,700 unique people in the Duke MTMC videos, most of whom are students, are used for research and development of surveillance technologies by commercial, academic, and even defense organizations.
The creation and publication of the Duke MTMC dataset in 2016 was originally funded by the U.S. Army Research Laboratory and the National Science Foundation 6. Since 2016 use of the Duke MTMC dataset images have been publicly acknowledged in research funded by or on behalf of the Chinese National University of Defense 7 8, IARPA and IBM 9, and U.S. Department of Homeland Security 10.
The 8 cameras deployed on Duke's campus were specifically setup to capture students "during periods between lectures, when pedestrian traffic is heavy". 6 Camera 7 and 2 capture large groups of prospective students and children. Camera 5 was positioned to capture students as they enter and exit Duke University's main chapel. Each camera's location is documented below.
Who used Duke MTMC Dataset?
This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries.
Biometric Trade Routes
To help understand how Duke MTMC Dataset has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Duke Multi-Target, Multi-Camera Tracking Project was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location.
- Academic
- Commercial
- Military / Government
Dataset Citations
The dataset citations used in the visualizations were collected from Semantic Scholar, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms.
Supplementary Information
Notes
The Duke MTMC dataset paper mentions 2,700 identities, but their ground truth file only lists annotations for 1,812
- a
- a
https://foreignpolicy.com/2019/03/19/962492-orwell-china-socialcredit-surveillance/
- a
"Attention-Aware Compositional Network for Person Re-identification". 2018. Source
- a
"End-to-End Deep Kronecker-Product Matching for Person Re-identification". 2018. source
- a
"Person Re-identification with Deep Similarity-Guided Graph Neural Network". 2018. Source
- abc
"Performance Measures and a Data Set for
- a
"Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers". 2018. Source
- a
"Unsupervised Multi-Object Detection for Video Surveillance Using Memory-Based Recurrent Attention Networks". 2018. Source
- a
"Horizontal Pyramid Matching for Person Re-identification". 2019. Source
- a
"Re-Identification with Consistent Attentive Siamese Networks". 2018. Source