ChokePoint Dataset

Overview · Example · Protocol · Licence · Download · Contacts · Publications · Acknowledgement

Overview

We collected a video dataset, termed ChokePoint, designed for experiments in person identification/verification under real-world surveillance conditions using existing technologies. An array of three cameras was placed above several portals (natural choke points in terms of pedestrian traffic) to capture subjects walking through each portal in a natural way (see example). While a person is walking through a portal, a sequence of face images (ie. a face set) can be captured. Faces in such sets will have variations in terms of illumination conditions, pose, sharpness, as well as misalignment due to automatic face localisation/detection. Due to the three camera configuration, one of the cameras is likely to capture a face set where a subset of the faces is near-frontal.

The dataset consists of 25 subjects (19 male and 6 female) in portal 1 and 29 subjects (23 male and 6 female) in portal 2. The recording of portal 1 and portal 2 are one month apart. The dataset has frame rate of 30 fps and the image resolution is 800X600 pixels. In total, the dataset consists of 54 video sequences and 64,204 labelled face images. In all sequences, only one subject is presented in the image at a time. The first 100 frames of each sequence are for background modelling where no foreground objects were presented.

Each sequence was named according to the recording conditions (eg. P2E_S1_C3) where P, S, and C stand for portal, sequence and camera, respectively. E and L indicate subjects either entering or leaving the portal. The numbers indicate the respective portal, sequence and camera label. For example, P2L_S1_C3 indicates that the recording was done in Portal 2, with people leaving the portal, and captured by camera 3 in the first recorded sequence.

To pose a more challenging real-world surveillance problems, two seqeunces (P2E_S5 and P2L_S5) were recorded with crowded scenario. In additional to the aforementioned variations, the sequences were presented with continuous occlusion. This phenomenon presents challenges in identidy tracking and face verification.

This dataset can be applied, but not limited, to the following research areas:

person re-identification
image set matching
face quality measurement
face clustering
3D face reconstruction
pedestrian/face tracking
background estimation and substraction

Example

An example of the recording setup used for the ChokePoint dataset. A camera rig contains 3 cameras placed just above a door, used for simultaneously recording the entry of a person from 3 viewpoints. The variations between viewpoints allow for variations in walking directions, facilitating the capture of a near-frontal face by one of the cameras.

Camera Rig

Camera 1

Camera 2

Camera 3

Example shots from the ChokePoint dataset, showing portals with various backgrounds.

P1E - Camera 1

P1L - Camera 1

P2E - Camera 2

P2L - Camera 2

P2E_S5 - Camera 2

P2L_S5 - Camera 2

Example video sequences for the ChokePoint dataset: camera 1, camera 2, camera 3

Protocol

We designed a baseline verification protocol (protocol_baseline) for this dataset. In this protocol, video sequences are divided into two groups (G1 and G2), where each group played the role of development set and evaluation set in turn. In each group, all possible genuine and imposter pairs were generated. Parameters and threshold are first learned on the development set and then applied on the evaluation set. The average verification rate is used for reporting results.

P1E_S1_C1		P1E_S2_C2		P2E_S2_C2		P2E_S1_C3
P1L_S1_C1		P1L_S2_C2		P2L_S2_C2		P2L_S1_C1

P1E_S3_C3		P1E_S4_C1		P2E_S4_C2		P2E_S3_C1
P1L_S3_C3		P1L_S4_C1		P2L_S4_C2		P2L_S3_C3

We also encourage the experiments to be conducted with two evaluation conditions:

single camera (SC)
- using faces from the camera with most frontal view (listed in above tables).
multiple camera (MC)
- using faces from all three cameras. For example, images for portal 1E and sequence 1 will are taken from P1E_S1_C1, P1E_S1_C2 and P1E_S1_C3.

Licence

This dataset ('Licensed Material') is made available to the scientific community for non-commercial research purposes such as academic research, teaching, scientific publications or personal experimentation. Permission is granted by National ICT Australia Limited (NICTA) to you (the 'Licensee') to use, copy and distribute the Licensed Material in accordance with the following terms and conditions:

Licensee must include a reference to NICTA and the following publication in any published work that makes use of the Licensed Material:

Y. Wong

Patch-based probabilistic image quality assessment for face selection and improved video-based face recognition

Computer Vision and Pattern Recognition Workshops (CVPRW)

@INPROCEEDINGS{wong_cvprw_2011,
   AUTHOR    = {Yongkang Wong and Shaokang Chen and Sandra Mau and Conrad Sanderson and Brian C. Lovell},
   TITLE     = {Patch-based probabilistic image quality assessment for face selection and improved video-based face recognition},
   BOOKTITLE = {Computer Vision and Pattern Recognition Workshops (CVPRW)},
   PAGE	     = {74-81},
   YEAR      = {2011}
}

If Licensee alters the content of the Licensed Material or creates any derivative work, Licensee must include in the altered Licensed Material or derivative work prominent notices to ensure that any recipients know that they are not receiving the original Licensed Material.

Licensee may not use or distribute the Licensed Material or any derivative work for commercial purposes including but not limited to, licensing or selling the Licensed Material or using the Licensed Material for commercial gain.

The Licensed Material is provided 'AS IS', without any express or implied warranties. NICTA does not accept any responsibility for errors or omissions in the Licensed Material.

This original license notice must be retained in all copies or derivatives of the Licensed Material.

All rights not expressly granted to the Licensee are reserved by NICTA.

Download

Notes

The entire ChokePoint dataset is about 12 Gb. Each tar.xz file is on average around 200 Mb

Brief description of the data can be found in README

The cropped face images were extracted using the manually labelled eye location. The faces has the size of 96x96 pixels

Please download only one file at a time -- this is so the server is not overloaded

Microsoft Windows user can extract the *.tar.xz files with 7-Zip

High Resolution Mug Shot:

Still.tar.xz

Original files:

Cropped face images:

Contacts

If you have any questions regarding to the dataset, please contact:

Publications

A selected publications referring to the ChokePoint dataset:

Acknowledgement

The chokepoint dataset is sponsored by NICTA. NICTA is funded by the Australian Government as represented by the Department of Broadband, Communications and the Digital Economy, as well as the Australian Research Council through the ICT Centre of Excellence program.