├── .gitignore └── README.md /.gitignore: -------------------------------------------------------------------------------- 1 | # This .gitignore file should be placed at the root of your Unity project directory 2 | # 3 | # Get latest from https://github.com/github/gitignore/blob/master/Unity.gitignore 4 | # 5 | /[Ll]ibrary/ 6 | /[Tt]emp/ 7 | /[Oo]bj/ 8 | /[Bb]uild/ 9 | /[Bb]uilds/ 10 | /[Ll]ogs/ 11 | /[Mm]emoryCaptures/ 12 | 13 | # Asset meta data should only be ignored when the corresponding asset is also ignored 14 | !/[Aa]ssets/**/*.meta 15 | 16 | # Uncomment this line if you wish to ignore the asset store tools plugin 17 | # /[Aa]ssets/AssetStoreTools* 18 | 19 | # Autogenerated Jetbrains Rider plugin 20 | [Aa]ssets/Plugins/Editor/JetBrains* 21 | 22 | # Visual Studio cache directory 23 | .vs/ 24 | 25 | # Gradle cache directory 26 | .gradle/ 27 | 28 | # Autogenerated VS/MD/Consulo solution and project files 29 | ExportedObj/ 30 | .consulo/ 31 | *.csproj 32 | *.unityproj 33 | *.sln 34 | *.suo 35 | *.tmp 36 | *.user 37 | *.userprefs 38 | *.pidb 39 | *.booproj 40 | *.svd 41 | *.pdb 42 | *.mdb 43 | *.opendb 44 | *.VC.db 45 | 46 | # Unity3D generated meta files 47 | *.pidb.meta 48 | *.pdb.meta 49 | *.mdb.meta 50 | 51 | # Unity3D generated file on crash reports 52 | sysinfo.txt 53 | 54 | # Builds 55 | *.apk 56 | *.unitypackage 57 | 58 | # Crashlytics generated file 59 | crashlytics-build.properties 60 | 61 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # PoseOnTheGo: Approximating User Pose with Smartphone Sensor Fusion and Inverse Kinematics 2 | 3 | Pose-on-the-Go is a full-body pose estimation system that uses sensors already found in today’s smartphones. This stands in contrast to prior systems, which require worn or external sensors. We achieve this result via extensive sensor fusion, leveraging a phone’s front and rear cameras, the user-facing depth camera, touchscreen, and IMU. Even still, we are missing data about a user’s body (e.g., angle of the elbow joint), and so we use inverse kinematics to estimate and animate probable body poses. 4 | 5 | We have now released our app on the iOS App Store. You can download it here: https://apps.apple.com/us/app/pose-on-the-go/id1635810011 6 | 7 | More details about the project: https://karan-ahuja.com/poseotg.html 8 | 9 | 10 | 11 | 12 | 13 | --------------------------------------------------------------------------------