tools - Inria

Report
ViSEvAl
ViSualisation
and
EvAluation
http://team.inria.fr/stars/fr/2012/02/02/viseval-software/
Overview


What is evaluation?

Evaluation process

Metric definition
ViSEvAl

Description

Installation

Configuration

Functionalities
Evaluation process
General overview
Metric definition

Metric = distance + filter + criteria

Distance: associate detected and annotated objects


Spatial: compare bonding boxes area

Temporal: compare time intervals
Filter: selects which object to evaluate


Specific type, distance to the camera, ...
Criteria: how the property of detected and
annotated objects is similar?

4 tasks: detection, classification, tracking,
event detection
ViSEvAl platform description
ViSEvAlGUI
ViSEvAl:
Interfaces
 All functionalities
(synchronisation,
display,...)

ViSEvAlEvaluation
Core library
Loading Video
Frame Metric
Distance
Tool
Temporal Metric
Event Metric
Object Filter
Plugin
ViSEvAl plugins 1/2

Loading video


Distance


ASF-Videos, Caviar-Images, JPEGImages, Kinect-Images (hospital),
OpenCV-Videos (Vanhaeim), PNG-Images
Bertozzi, dice coefficient, overlapping
Filter

CloseTo, FarFrom, Identity, TypeGroup
ViSEvAl plugins 2/2

Criteria

Detection: M1.X


Classification: M2.X


2 criteria (M2.1: type, M2.2: sub type)
Tracking: M3.X


2 criteria (M1.1: area, M1.2: silhouette)
6 criteria (M3.1: F2F, M3.2: persistence, M3.4
(tracking time), M3.5: confusion, M3.6, M3.7:
confusion + tracking time, M3.8: frame detection
accuracy)
Event: M4.X

4 criteria (M4.1, M4.2: begin and end time, M4.3:
common frame, M4.4: common time)
ViSEvAl: inputs

A set of XML files

Detection: XML1 file -> sup platform

Recognised event: XML3 file -> sup platform

Ground truth: xgtf file -> Viper tool

Time stamp file for time synchronisation : xml file ->
createTimeStampFile.sh script provided by ViSEvAl
ViSEvAl installation


Get the sources

sup svn repository

cd sup/evaluation/ViSEvAl/
Run intall.sh at the root of ViSEvAl folder

Dependence:


Librairies: QT4 (graphical user interface, plugin
management), gl and glu (opengl 3D view), xerces-c
(XML read), opencv (video read)
Tool: xsdcxx (automatically compute C++ classes for
reading XML files)

cd bin/appli; setenv LD_LIBRARY_PATH ../../lib

Run ./ViSEvAlGUI chu.conf
ViSEvAl folder organisation

src : appli, plugins (Cdistance, CeventMetric, CframeMetric,
CloadingVideoInterface, CobjectFilter, CTemporalMetric)

include : header files

install.sh, clean.sh

doc : documentation

lib : core library, plugins

scripts : createTimeStampFile.sh makeVideoFile.sh splitxml12-3file.sh

bin : ViSEvAlGUI, ViSEvAlEvaluation

tools : CaviarToViseval, QuasperToViseval

xsd : xml schemas
ViSEvAl: configuration file
Configuration file based on Keyword-Parameter
SequenceLoadMethod "JPEG-Images” #"ASF-Videos“
SequenceLocation "0:../../example/CHU/Scenario_02.vid"
TrackingResult "0:../../example/CHU/Scenario_02_Global_XML1.xml"
EventResult "../../example/CHU/Scenario_02_Global_XML3.xml"
GroundTruth "0:../../example/CHU/gt_2011-11-15a_mp.xgtf"
XMLCamera "0:../../example/CHU/jai4.xml"
MetricTemporal "Mono:M3.4:M3.4:DiceCoefficient:0.5:TypeGroup"
MetricEvent "M4.2:M4.2.1:Duration:10
ViSEvAl run trace
Mon, 11:15> ./ViSEvAlGUI
Load all the plugins
-----------------------------------Loading video interfaces:
ASF-Videos
Caviar-Images
JPEG-Images
Kinect-Images
OpenCV-Videos
PNG-Images
-----------------------------------Loading distance:
3DBertozzi
3DDiceCoefficient
3DOverlapping
Bertozzi
DiceCoefficient
Overlapping
-----------------------------------Loading object filter:
CloseTo
FarFrom
Identity
TypeGroup
Loading frame metric:
M1.1
M1.2
M2.1
M2.2
M3.1
-----------------------------------Loading temporal metric:
M3.2
M3.4
M3.5
M3.6
M3.7
M3.8
-----------------------------------Loading event metric:
M4.1
M4.2
M4.3
M4.4
------------------------------------
ViSEvAl: two tools



ViSEvAlGUI

Graphical user interface

Visualise detection and ground truth on the images

User can easily select parameters (e.g. distance,
threshold,...)

Frame metrics results are computed in live
ViSEvAlEvaluation

Generate a .res file containing the results of the metrics

Frame, temporal and event metrics are computed

User can evaluate several experiments
Same configuration file for the both tools
ViSEvAl: result file (.res)
camera: 0
Tracking result file: /user/bboulay/home/work/svnwork/sup/evaluation/ViSEvAl/example/vanaheim/res.xml1.xml
Fusion result file:
Event result file:
Ground truth file: /user/bboulay/home/work/svnwork/sup/evaluation/ViSEvAl/example/vanaheim/Tornelli-2011-01 28T07_00_01_groups.xgtf
Common frames with ground-truth:
Detection results:
7978 7979 7980 7981 7983 7984 7985
*****
====================================================
Metric M1.1.1
====================================================
Frame;Precision;Sensitivity 0;True Positive;False Positive;False Negative 0;Couples
8004;0.500000;1.000000;1;1;0;(100;170;0.737438)
8005;0.500000;1.000000;1;1;0;(100;170;0.721577)
8006;0.500000;1.000000;1;1;0;(100;170;0.706809)
8007;0.500000;1.000000;1;1;0;(100;170;0.713584)
====================================================
Final Results:
Global results:
Number of True Positives : 1789
Number of False Positives : 1597
Number of False Negatives 0: 2254
Precision (mean by frame) : 0.523071
Sensitivity 0 (mean by frame) : 0.477763
Precision (global) : 0.528352
Sensitivity 0 (global) : 0.442493
--------------------------------------------Results for GT Object 2
Number of True Positives : 0
Number of False Positives : 0
Number of False Negatives 0: 0
Precision (global) : 0.000000
Sensitivity 0 (global) : 0.000000
---------------------------------------------

similar documents