daily_activity_dataset_imta_ensta

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Next revision		 Previous revision
daily_activity_dataset_imta_ensta [2021/07/07 10:29] – created maidaily_activity_dataset_imta_ensta [2023/10/02 16:25] (current) – mai
Line 3: Line 3:
  
 Sensors :  Sensors : 
-* Kinect 360 v2 + 
-* Optris IR camera +  * Kinect 360 v2 
-* Flir IR Camera +  * Optris IR camera 
-* xsens +  * Flir IR Camera 
-* smarthome sensors  +  * xsens 
-   * sensefloor to detect localisation wrt each room +  * FishEye camera 
-   * motion sensors for each room +  * smarthome sensors  
-   * opening/closing cupboards +    * sensefloor to detect localisation wrt each room 
-   * lights +    * motion sensors for each room 
-   * power consumption of stove, oven, boiler, plugs, tv +    * opening/closing cupboards 
-   * pressure sensor for bed, sofa+    * lights 
 +    * power consumption of stove, oven, boiler, plugs, tv 
 +    * pressure sensor for bed, sofa
  
 ===== Data Location ===== ===== Data Location =====
-Recorded on the drive 10To La Cie/dataset. + 
-The folders are organised as : s1/experiment2 for the subjectNumber and recording number +The latest working folder is on backup1, in folder DatasetVirtualSmartHome2023, with the reoganisation and renaming of the files by hiParis. 
-In each folder are files :+ 
 +Data before renaming is in backup1, folder DatasetVirtualSmartHome2021. 
 +Original data with xaal data is in  dataset_avecxaal and dataset_2021.tar.gz. 
 + 
 + 
 +The dataset was first recorded on the drive 10To La Cie/dataset. The folders are organised as : s1/experiment2 for the subjectNumber and recording number. 
 + 
 +==== DatasetVirtualSmartHome2023 Folder content ==== 
 + 
 +  * Folder Code2020_by_TP/Vhome-doc : contains a documentation for virtual home simulator 
 +  * Folder Code2020_by_TP/LivraisonVSHome/Projet_code : contains the code for bluring faces in videos, drawing the skeletons, renaming the files and folders. and for the simulator Virtual Smart Home 
 +  * Folder codeRecordingDataset is a copy of the code used to record the dataset, from https://github.com/dbouchabou/Experiment_HAAL_dataset 
 +  * Folder config_xsens contains the measurements of the subjects skeleton for x-sens.  
 +  * Folder VirtualHome contains by sensor modality the data for each subject and each experiment : 
 +      * IOT : xaal data 
 +      * IR: the infrared cameras : small resolution and Optris. Currently the content is only symbolic links to the contents in DatasetVirtualSmartHome2021 
 +      * Skeletons : x-sens and kinect, but also the processed openpose. 
 +      * Videos : RGB anonymised videos. There are also videos with audio and fisheyecamera videos that have not yet been added. 
  
  
Line 24: Line 44:
 ==== Documents describing the dataset ==== ==== Documents describing the dataset ====
  
-* list of all recordings are on the document DatasetRecordings2021Log https://docs.google.com/spreadsheets/d/1W0DqjJVarbkoAUHT3j2Q7lVogSw5QohR092B2tZ4iks/edit?usp=sharing  +The folder https://drive.google.com/drive/folders/1D2UvNDFBL7e-PAb0IffjIEFkR9oYmkTK?usp=drive_link contains information about how the dataset was designed and recorded, including : 
-* Rules for the setup and design of the recording sessions https://docs.google.com/document/d/17Z-UU5QdpVliK1zFvtqa-svI1SIBw9suLfvPhSxTlKE/edit?usp=sharing+ 
 +  * list of all recordings are on the document DatasetRecordings2021Log https://docs.google.com/spreadsheets/d/1W0DqjJVarbkoAUHT3j2Q7lVogSw5QohR092B2tZ4iks/edit?usp=sharing  
 +  * Rules for the setup and design of the recording sessions https://docs.google.com/document/d/17Z-UU5QdpVliK1zFvtqa-svI1SIBw9suLfvPhSxTlKE/edit?usp=sharing 
 +  * The scripts to launch and synchronize all activities are on https://github.com/dbouchabou/Experiment_HAAL_dataset 
 +  * Folder Illustrations contains pictures of the setup with the position of the Kinect. 
  
 ==== Recording procedure ==== ==== Recording procedure ====
  
-describe how we launch the scripts, which programs to open, OS requirement+describe how we launch the scripts, which programs to open
  
 === Set up the hardware === === Set up the hardware ===
  
 +Computers :
 +  * A linux computer with USB 3 (for the Optris IR camera) with
 +      * ROS and http://wiki.ros.org/optris_drivers
 +      * xaal installed  
 +  * a Windows computer with USB 3 (for the Kinect v2 360) with
 +      * Microsoft Kinect Studio
 +      * MVN Studio Biomech     
 +  * a macos computer to record the videos via the network (ffmpeg)
 +
 +
 +Pluging of the sensors :
 +
 +  * Plug the Optris IR Camera with USB 3 on computer1 with ROS.
 +  * The Flir IR Camera is connected to the smart home system and can be streamed via the network with RJ45. For instance, ffmpeg can record the stream into a file with the command ''ffmpeg -i rtsp:/// ///xaal-c.enstb.org:8554/flir1  filename210701.mp4''. 
 +  * The Kinect v2 360 is connected via USB 3 to the ZED computer with windows and Microsoft Kinect Studio installed.
 +  * The FishEye camera is connected via wifi and can be streamed via the network.
 +  * The power, pressure, door, motion detectors are connected via xaal
 +  * The x-sens hub is connected via usb to the ZED computer with windows with MVN Studio Biomech installed
  
 === Launch the programs === === Launch the programs ===
 +
 +
 +  - Move the previous recordings to the right folder
 +    - Move xsens recording .mvn file from folder Desktop/Xsens/ to the folder dataset/subject_tmp  
 +    - Move the folder dataset/subject_tmp to /dataset/sN so that the data does not get erased
 +  - Create folder dataset/subject_tmp
 +  - Push on button ''Start''
 +  - To end, push on button ''Stop''
 + 
  
 ==== Post-processing procedure ==== ==== Post-processing procedure ====
  
 === Kinect data === === Kinect data ===
 +    *<code>xefextract.exe "path_to_file.xef"</code>
 +    *On utilise le code de github <https://github.com/Isaac-W/KinectXEFTools>. 
 +    *S'on ne pourrait pas avoir le bon resultat, on pourrait modifier le code dans "\examples\XEFExtract\XEFWriters" et utiliser le bulid bat comme "build_win10-x64.bat" dans "\examples\XEFExtract" pour le compiler.
 === X-sens data === === X-sens data ===
 +    *On exporte le fichier xxx.mvnx, donc on pourrait le porgrammer.
 === IR camera data === === IR camera data ===
 +    *C'est déjà fait dans le ROS
 === xaal data === === xaal data ===
  
Line 48: Line 105:
  
  
 +
 +==== Troubleshooting ====
 +
 +  * ffmeg on windows computer ZED does not work well 
 +
 +===== Avant l'enregistrement =====
 +
 +  * Les ordinateurs doivent être au maximum connecté en Ethernet 
 +  * Activer l'environnement python xaal, ouvrir dans powershell et exécuter :  .\xaal_env/Scripts/activate
 +  * Exécuter ces 2 commandes dans 2 fenêtres de terminal différentes : 
 +      * roscore
 +      * roslaunch optais_drivers optais_drivers.launch
 +      * rosrun optais_drivers camera.py, s'on veut démarrer le caméra Optris tous seule
 +  * Lancer les scripts : 
 +      * python xaal_btn_base.py
 +      * python xaal_activity_fish_eye.py : vérifier que le path du script correspond à l'ordinateur utiliser
 +      * python xaal_activity_IR_cams.py
 +      * python xaal_activity_kinect_xsens.py (à lancer dans l'ordinateur avec la kinect studio et xsens studio)
 +
 +
 +
 +  * Porter les capteurs Xsens avec du sparadra pour pas que ça bouge pendant les scénarios
 +  * Faire le calibrage dans l'angle de l'entrée du LivingLab pour la position absolu pour Xsens. 
 +
 +  * Ne pas commencer à enregistrer (appui sur bouton start), si tous les capteurs ne sont pas dans l'état souhaité. Exemple : capteur de mouvement D-Room - attendre 180 secondes pour qu'il revient à l'état False)
 +
 +
 +===== Pendant l'enregistrement =====
 +
 +   * Dire à haute voix ce que l'on va faire avant de le faire et attendre un retour par ses collègues que l'appui sur le bouton d'activité est fait 
 +   * Faire attention aux dalles mortes (cuisine/salle de bain : trop proche de la fenêtre ou trop proche des meubles/frigo) 
 +   * Dans le fauteuil et dans le lit : bien s'asseoir et vérifier sur l'écran Graffana que le capteur de pression est bien activé
 +   * Ne pas allumer les plaques en même temps que le four, car cela fait sauter les plombs 
  
  
 +===== Après l'enregistrement =====
  
 +   * Fermer Kinect Studio
 +   * Renommer subject_tmp par le nom de dossier experiment souhaité et déplacer le dossier dans le dossier du sujet 
 +   * Déplacer le fichier mvn (C://Users/zed/Desktop/Xsens) dans le dossier du sujet (E://dataset/) : s1, s2, s3 ..
  
  • daily_activity_dataset_imta_ensta.1625653790.txt.gz
  • Last modified: 2021/07/07 10:29
  • by mai