diff options
Diffstat (limited to 'docs/user_guide/aruco_marker_pipeline/aoi_3d_frame.md')
-rw-r--r-- | docs/user_guide/aruco_marker_pipeline/aoi_3d_frame.md | 133 |
1 files changed, 133 insertions, 0 deletions
diff --git a/docs/user_guide/aruco_marker_pipeline/aoi_3d_frame.md b/docs/user_guide/aruco_marker_pipeline/aoi_3d_frame.md new file mode 100644 index 0000000..cf4a07e --- /dev/null +++ b/docs/user_guide/aruco_marker_pipeline/aoi_3d_frame.md @@ -0,0 +1,133 @@ +Define a 3D AOI as a frame +========================== + +When an 3D AOI of the scene contains others coplanar 3D AOI, like a screen with GUI elements displayed on, it is better to described them as 2D AOI inside 2D coordinates system related to the containing 3D AOI. + +![3D AOI frame](../../img/aruco_camera_aoi_frame.png) + +## Add ArFrame to ArUcoScene + +The [ArFrame](../../argaze.md/#argaze.ArFeatures.ArFrame) class defines a rectangular area where timestamped gaze positions are projected in and inside which they need to be analyzed. + +Here is the previous extract where "Left_Screen" and "Right_Screen" AOI are defined as a frame into [ArUcoScene](../../argaze.md/#argaze.ArUcoMarkers.ArUcoScene) configuration: + +```json +{ + "name": "My FullHD camera", + "size": [1920, 1080], + ... + "scenes": { + "MyScene" : { + "aruco_markers_group": { + ... + }, + "layers": { + "MyLayer": { + "aoi_scene": { + "Left_Screen": [[0, 0, 0], [15, 0, 0], [0, 18.963333, -6.355470], [15, 18.963333, -6.355470]], + "Right_Screen": [[20, 0, 0], [35, 0, 0], [20, 18.963337 ,-6.355472], [35, 18.963337, -6.355472]], + "Control_Panel": [[49.5, 30, 18.333333], [55.5, 30, 18.333333], [49.5, 38, 18.333333], [55.5, 38, 18.333333]], + "Window": [[-57.8, 5.5, -33.5], [46, 15.5, -35], [1.5, 53, -1], [50.2, 61, 6], [-35.85, 35, -15]] + } + } + }, + "frames": { + "Left_Screen": { + "size": [768, 1024], + "layers": { + "MyLayer": { + "aoi_scene": { + "LeftPanel": { + "Rectangle": { + "x": 0, + "y": 0, + "width": 768, + "height": 180 + } + }, + "CircularWidget": { + "Circle": { + "cx": 384, + "cy": 600, + "radius": 180 + } + } + } + } + } + }, + "Right_Screen": { + "size": [768, 1024], + "layers": { + "MyLayer": { + "aoi_scene": { + "GeoSector": [[724, 421], [537, 658], [577, 812], [230, 784], [70, 700], [44, 533], [190, 254], [537, 212]] + } + } + } + } + } + } + } + ... +} +``` +Now, let's understand the meaning of each JSON entry. + +### *frames* + +An [ArUcoScene](../../argaze.md/#argaze.ArUcoMarkers.ArUcoScene) instance can contains multiples [ArFrames](../../argaze.md/#argaze.ArFeatures.ArFrame) stored by name. + +### Left_Screen & Right_Screen + +The names of 3D AOI **and** their related [ArFrames](../../argaze.md/#argaze.ArFeatures.ArFrame). Basically useful for visualisation purpose. + +!!! warning "AOI / Frame names policy" + + An [ArUcoScene](../../argaze.md/#argaze.ArUcoMarkers.ArUcoScene) layer 3D AOI is defined as an [ArUcoScene](../../argaze.md/#argaze.ArUcoMarkers.ArUcoScene) frame, **provided they have the same name**. + +!!! warning "Layer name policy" + + An [ArUcoScene](../../argaze.md/#argaze.ArUcoMarkers.ArUcoScene) frame layer is projected into [ArUcoScene](../../argaze.md/#argaze.ArUcoMarkers.ArUcoScene) layer, **provided they have the same name**. + +!!! note + + [ArUcoScene](../../argaze.md/#argaze.ArUcoMarkers.ArUcoScene) frame layers are projected into their dedicated [ArUcoScene](../../argaze.md/#argaze.ArUcoMarkers.ArUcoScene) layers when the JSON configuration file is loaded. + +## Pipeline execution + +### Map ArUcoCamera image into ArUcoScenes frames + +After camera image is passed to [ArUcoCamera.watch](../../argaze.md/#argaze.ArFeatures.ArCamera.watch) method, it is possible to apply a perpective transformation in order to project watched image into each [ArUcoScenes](../../argaze.md/#argaze.ArUcoMarkers.ArUcoScene) [frames background](../../argaze.md/#argaze.ArFeatures.ArFrame) image. + +```python +# Assuming that Full HD (1920x1080) timestamped images are available +...: + + # Detect ArUco markers, estimate scene pose then, project 3D AOI into camera frame + aruco_camera.watch(image, timestamp=timestamp) + + # Map watched image into ArUcoScenes frames background + aruco_camera.map(timestamp=timestamp) +``` + +### Analyse timestamped gaze positions into ArUcoScenes frames + +[ArUcoScenes](../../argaze.md/#argaze.ArUcoMarkers.ArUcoScene) frames benefits from all the services described in [gaze analysis pipeline section](../gaze_analysis_pipeline/introduction.md). + +!!! note + + Timestamped gaze positions passed to [ArUcoCamera.look](../../argaze.md/#argaze.ArFeatures.ArFrame.look) method are projected into [ArUcoScenes](../../argaze.md/#argaze.ArUcoMarkers.ArUcoScene) frames if applicable. + +### Display each ArUcoScenes frames + +All [ArUcoScenes](../../argaze.md/#argaze.ArUcoMarkers.ArUcoScene) frames image can be displayed as any [ArFrame](../../argaze.md/#argaze.ArFeatures.ArFrame). + +```python + ... + + # Display all ArUcoScenes frames + for frame in aruco_camera.scene_frames: + + ... frame.image() +```
\ No newline at end of file |