Category: Evaluation

Apr 06

ViSEvAl result comparison

The goal of this script is to compare different result files of the same sequence.

To run the script, use the following command :

python resultComparison.py <resultFile1.txt> ... <resultFileN.txt>

The result files must be ViSEvAl output file generated by the ViSEvAlEvaluation binary.


The script displays useful information of the result files and the best configuration for each metrics is highlighted in green. The “Show all” switch toggles the display between global results and detected object metrics.

Apr 05

XML1 Viewer

XML1 Viewer is a Python script showing statistics and information about XML1 output of SUP.

To run the script, use the following command :

python XML1Viewer.py <XML1file>

With only an XML1 file as input, the script displays all the detected object with the following statistics :

  • number of frames
  • total duration (last frame – first frame)
  • average 2D dimension (in pixels)
  • average 3D dimension (in meters)

 

If the directory  containing the sequence images is added as input, the images of each detected object appear.


Feb 02

SUP daily evaluation

The daily evaluation aims to guaranty the proper functioning of SUP by detecting crashes and bugs due to last commits and showing if the results of the different algorithms are improving day after day.

Evaluation is performed as follows :

  • update of SUP core and SUP plugins to the latest version
  • full compilation of SUP core and SUP plugins
  • processing of the reference sequences
  • computation of the results using ViSEvAl
  • an e-mail is sent the the sup_dlevel team with the results

The results are computed by comparing today metrics with the reference metrics computed from a default XML1 result file.

At the moment, only sequences are processed : one from ETISEO (ETI-BC-11-C1) to evaluate SUP standard processing chain (MOG segmentation, physical object constructor, F2F tracking and LTT) and one from Nice CHU (2011-01-11a) to evaluate events detection. The next sequence to be added will test person detection.

If you are working on a new plugin or improving an old one, you may want to add a sequence to the daily evaluation. In that case, you should send me :

  • the SUP parameter file
  • the context file (camera calibration)
  • the ground-truth file
  • the ViSEvAl configuration file with the metrics to be tested (optional)

Daily evaluation is usually performed everyday of the week at 0:55 AM. If you do not want to be spammed by the e-mails sent everyday, I suggest you add a filter in zimbra for that.

Feb 02

ViSEvAl software

ViSEvAl graphical user interface

ViSEvAl is under GNU Affero General Public License (AGPL)

At INRIA, an evaluation framework has been developed to assess the performance of Gerontechnologies and Videosurveillance. This framework aims at better understanding the added values of new technologies for home-care monitoring and other services. This platform is available to the scientific community and contains a set of metrics to evaluate automatically the performance of software given some ground-truth.

Description

The software ViSEvAl (ViSualisation and EvAluation) provides a GUI interface to visualise results of video processing algorithms (such as detection of object of interest, tracking or event recognition). Moreover this software can compute metrics to evaluate specific tasks (such as detection, classification, tracking or event recognition). The software is composed of two binaries (ViSEvAlGUI and ViSEvAlEvaluation), and several plugins. The users can add their own plugins to define a new metric for instance.

General schema of an evaluation platform

Installation

  • OS: Linux (tested on Fedora 12) and gcc 4.4.4
  • Three libraries are mandatory: QT4 (for GUI facilities and plugin facilities), and libxerces-c (for automatic xml parser)
  • xsdcxx must be installed on your computer (for automatic xml parser)
  • FFMpeg is optional (only use in the plugin to load .ASF video)
  1. Go in the ViSEvAl directory (call SoftwareDirectory in the next)
  2. Launch the script ./install.sh. The script will create all the makefile needed by the application and the plugins, and will compile all the code. If all is ok, you will find the executables in SoftwareDirectory/bin/appli directory
  3. Type the bash command:
    setenv LD_LIBRARY_PATH $SoftwareDirectory/lib:/usr/local/lib$LD_LIBRARY_PATH (to tell to the applicatin where is the ViSEvAlLib, and the optional libs for ffmpeg)
  4. Go in the directory bin/appli
  5. Run ViSEvAlGUI for the GUI tool or run ViSEvAlEvaluation for the command line tool
  • ViSEvAlGUI In the menu: File -> Open…, select the desired .conf file
  • ViSEvAlEvaluation file.conf result.res [0-1] [0-1]
  1. file.conf the desired configuration file
  2. result.res the file where the results while be wrote
  3. [0-1] optional value 0: the results are printed for each frame, 1: only the global results are printed
  4. [0-1] the evaluation of the detection (XML1) and of the fusion (XML2) is only done on the common frames

More details

ViSEvAl overview

XSD files

The XSD files describe the XML format of the different input files for the ViSEvAl software

  • Description of the data provided by video sensor: camera detection, fusion detection and event detection data.xsd
  • Description of the data provided by non video sensor: contact sensor, wearable sensor,… sensor.xsd
  • Description of the camera parameters: calibration, position,… camera.xsd

Download

This platform is available on demand to the scientific community (contact Annie.Ressouche @ inria.fr).

Dec 21

Evaluation description

Involved people:

  • Bernard Boulay
  • Julien Badie
  • Swaminathan Sankaranarayanan

Topics:

Evaluation is an important task to better understand the added values of new algorithms or technologies for intelligent video platform.

Main issues:

  • Criteria : which criteria is used according the task to evaluate?
  • Multi-criteria : how two combine several criteria to qualify a system?
  • Data set : how to select/create a meaning data set according teh task to evaluate?