To access the data in this page please contact Prof. Sergio A Velastin who will send you a username and a password that you must not share. Access is granted for the purpose of research only and not for commercial use. We only collect names/emails of people using this data to form a community of users, to make announcements of improvements to the dataset, relevant research events, etc. We do not share the list with any third parties. All we ask in return is for you to cite our work in your publications:

Velastin, Sergio A.; Fernández, Rodrigo; Espinosa, Jorge E.; Bay, Alessandro. 2020. "Detecting, Tracking and Counting People Getting On/Off a Metropolitan Train Using a Standard Video Camera" Sensors 20, no. 21: 6251.

  title={Detecting, tracking and counting people getting on/off a metropolitan train using a standard video camera},
  author={Velastin, Sergio A and Fern{\'a}ndez, Rodrigo and Espinosa, Jorge E and Bay, Alessandro},
  publisher={Multidisciplinary Digital Publishing Institute}

Please send us the bibliographic citation of any publication of yours that use this dataset so we can list it on this web site.

If you prefer to download whole sections of the dataset at once without having to click on each file, please see instructions in Whole dataset

Using a set of 15 videos (those enclosed by the red boxes below), peoples heads have been manually annotated for each frame (therefore, not all videos are annotated as that would be a major task). Each separate individual is given a unique identifier (to allow testing people tracking approaches). For each frame, each individual is represented by a rectangle (centroid coordinates, width and height in pixels). The annotations are contained in *.xgtf (xml) files (they were prepared using the Viper-GT annotation tool). Each XML file is organised by person. To convert this format to simpler CSVs files, you can use the software provided here (this is provided "as is" with no support). These CSV files are also provided in this website for convenience. Each line in a CSV file contains on a frame-by-frame basis bounding box coordinates for each head (<class> is always "head"):

<frame_number> <person_id> <class> <top_x> <top_y> <width> <height>

where the top left corner of each image has coordinates 0, 0

The videos are taken from the 2008/Overview/0mm (floor height)/800mm(door width) section of the full dataset.

A=Alight (get off), B=Board (get on)

To download the videos from this section of the dataset, please click on the the links below.
Ground-truthed videos from PAMELA-UANDES dataset
(indicated by red boxes)

Ground truthed data: alight
Process Door width Height Video VIPER-GT
Alight 800mm 0mm A_d800mm_R1 * A_d800mm_R1 A_d800mm_R1
Alight 800mm 0mm A_d800mm_R2 * A_d800mm_R2 A_d800mm_R2
Alight 800mm 0mm A_d800mm_R3 * A_d800mm_R3 A_d800mm_R3
Alight 800mm 0mm A_d800mm_R4 * A_d800mm_R4 A_d800mm_R4
Alight 800mm 0mm A_d800mm_R5 A_d800mm_R5 A_d800mm_R5
Alight 800mm 0mm A_d800mm_R6 A_d800mm_R6 A_d800mm_R6
Alight 800mm 0mm A_d800mm_R7 A_d800mm_R7 A_d800mm_R7
Alight 800mm 0mm A_d800mm_R8 A_d800mm_R8 A_d800mm_R8

Groud truthed data: board 
Process Door width Height Video Ground truth CSV
800mm 0mm B_No_d800mm_R1 * B_No_d800mm_R1 B_No_d800mm_R1
800mm 0mm B_No_d800mm_R2 * B_No_d800mm_R2 B_No_d800mm_R2
800mm 0mm B_No_d800mm_R3 * B_No_d800mm_R3 B_No_d800mm_R3
800mm 0mm B_No_d800mm_R4 * B_No_d800mm_R4 B_No_d800mm_R4
800mm 0mm B_No_d800mm_R5 B_No_d800mm_R5 B_No_d800mm_R5
Board 800mm 0mm B_No_d800mm_R6 B_No_d800mm_R6 B_No_d800mm_R6
800mm 0mm B_No_d800mm_R7 B_No_d800mm_R7 B_No_d800mm_R7