PIROPO Database

News
  • (2016-Oct-13) Added calibration information for the omnidirecional camera in Room B. The file "calib_cameras.zip" contains now all the calibration data for the omnidirectional cameras. 
  • (2016-Sep-30) Added calibration information for the omnidirecional cameras in Room A, and the floor plan. See section "How to get the PIROPO database" below.
About the database


The PIROPO database (People in Indoor ROoms with Perspective and Omnidirectional cameras) comprises multiple sequences recorded in two different indoor rooms, using both omnidirectional and perspective cameras. The sequences contain people in a variety of situations, including people walking, standing, and sitting. Both annotated and non-annotated sequences are provided, where ground truth is point-based (each person in the scene is represented by the point located in the center of its head). In total, more than 100,000 annotated frames are available.



Rooms, cameras, and video sequences


Room A is a rectangular-shaped open area, with an approximate size of 15 x 10 meters, and it is covered by 8 different cameras. Three of the cameras are omnidirectional (omni_1A, omni_2A, and omni_3A), and are ceiling-mounted. The other five cameras are perspective ones (conv_4A to conv_8A), and are installed in wall-ceiling edges. The image dimensions are 800 x 600 pixels for all cameras, and the frame rate is approximately 10 fps.

Room B is a smaller rectangular-shaped room of 8 x 5 meters, with a more cluttered background including multiple tables, chairs, and computers. Two cameras installed in the room have been used. One of them is omnidirectional (omni_1B), and it is ceiling-mounted, and the other is a perspective one (conv_2B). The image dimensions are 800 x 600 pixels for the omnidirectional camera, and 704 x 576 for the perspective one. The frame rate is approximately 10 fps.

Sample images of the cameras captured scenes can be found here. In both rooms, all the cameras have been used to record the same sequences. Therefore, there are as many sequences as number of cameras per recording case. However, notice that the sequences are not synchronized.

Description of the sequences

Several sequences have been captured, showing people in a variety of situations. The following table provides a brief description of the contents all the sequences. Sample videos showing the sequences for two of the database cameras can be found here.

SEQUENCE ID
DESCRIPTION OF THE SEQUENCE CONTENTS
 training 1 person exhaustively walking around room (in total, 3 people repeating the action)
 test11 person (present in the training) walking (in total, 3 people repeating the action)
 test2Up to 3 people simultaneously walking
 test31 person (new to the system, not present in training sequences) walking (in total, 2 people repeating the action)
 test41 person walking and standing still (in total, 2 people repeating the action)
 test5Up to 5 people simultaneously walking
 test6Up to 10 people simultaneously walking
 training_seats1 person sitting in some defined locations (in total, 3 people repeating the action)
 test71 person sitting (in total, 2-3 people repeating the action)
 test81 person sitting and 1 person walking
 training_illumempty frames with changed illumination conditions
 test91 person walking with changed illumination conditions (in total, 3 people repeating the action)
 training_bgempty frames with changed background conditions
 test10Up to 3 people walking with changed scene background
 test111 person changing background
 test121 person walking and leaving new object
 training_centersequence showing a person near the center of an omnidirectional camera
 training_additional_bgshort sequence with additional background conditions (empty frames)


Ground Truth Annotations

The PIROPO database includes ground truth annotations for some of the sequences (see table below). The annotations are contained in Comma Separated Values (.csv) files. Each row of the file represents one image of the corresponding sequence. Then, the first column indicates the number of the image within the sequence (1-indexed). The following column are organized in pairs, indicating the x-coordinate (image column) and the y-coordinate (image row) of the point belonging to the center of the head of each person in scene. Points (0,0) represent non-annotations for convenience purposes.

 · Example of .csv annotation file contents for a sequence with at most one person in scene:

119,0,0                          //frame 119; empty frame

120,0,0                          //frame 120; empty frame

121,718,241                   //frame 121; person (head) at x = 718 pixels, y = 241 pixels

 · Example of .csv annotation file contents for a sequence with more than one person in scene:

11225,225,141,0,0,0,0                    //frame 11225; person #1 at x = 225, y = 141; no more people in scene

11226,213,130,53,564,0,0              //frame 11226; person #1 at x = 213, y = 130; person #2 at x = 53, y = 564

  (two complete .csv sample files can be found here and here)

· Available sequences and ground truth (GT) annotations in the database.- some sequences are not available for certain cameras, since the action takes place out of their field of view. Also, some sequences have not been annotated due to time restrictions. The following table provides information about the availability of sequences and annotations.

 

omni_1A

omni_2A

omni_3A

conv_4A

conv_5A

conv_6A

conv_7A

conv_8A

omni_1B

conv_2B

training

 

 

 

 

 

 

 

 

 

 

training_center

 

 

 

 

 

 

 

 

 

 

training_seat1

 

 

 

 

 

 

 

 

 

 

training_seat2

 

 

 

 

 

 

 

 

 

 

test1

 

 

 

 

 

 

 

 

 

 

test2

 

 

 

 

 

 

 

 

 

 

test3

 

 

 

 

 

 

 

 

 

 

test4

 

 

 

 

 

 

 

 

 

 

test5

 

 

 

 

 

 

 

 

 

 

test6

 

 

 

 

 

 

 

 

 

 

test7

 

 

 

 

 

 

 

 

 

 

test8

 

 

 

 

 

 

 

 

 

 

test9

 

 

 

 

 

 

 

 

 

 

test10

 

 

 

 

 

 

 

 

 

 

test11

 

 

 

 

 

 

 

 

 

 

test12

 

 

 

 

 

 

 

 

 

 

training_illum

 

 

 

 

 

 

 

 

 

 

training_bg

 

 

 

 

 

 

 

 

 

 

training_additional_bg

 

 

 

 

 

 

 

 

 

 





































 

GT available

 

No GT available, but sequence exists

 

Sequence does NOT exist

 

Empty sequence (no GT)








How to get the PIROPO
 database


The whole set of video sequences and associated data (ground truth) can be downloaded from:
The PIROPO database is available and free for research purposes. Contact cda@gti.ssr.upm.es, pcl@gti.ssr.upm.es, or lgl@gti.ssr.upm.es for more information.