Edit and execute pipeline

The ArFrame class defines a rectangular area where timestamped gaze positions are projected in and inside which they need to be analyzed.

Once defined, a gaze analysis pipeline needs to embedded inside a context that will provides it gaze positions to process.

Edit JSON configuration

Here is a simple JSON ArFrame configuration example:

{
    "argaze.ArFeatures.ArFrame": {
        "name": "My FullHD screen",
        "size": [1920, 1080],
        "gaze_movement_identifier": {
            "argaze.GazeAnalysis.DispersionThresholdIdentification.GazeMovementIdentifier": {
                "deviation_max_threshold": 50,
                "duration_min_threshold": 200
            }
        },
        "scan_path": {
            "duration_max": 30000
        },
        "scan_path_analyzers": {
            "argaze.GazeAnalysis.Basic.ScanPathAnalyzer": {},
            "argaze.GazeAnalysis.ExploreExploitRatio.ScanPathAnalyzer": {
                "short_fixation_duration_threshold": 0
            }
        }
    }
}

Let's understand the meaning of each JSON entry.

argaze.ArFeatures.ArFrame

The class name of the object being loaded.

name

The name of the ArFrame. Basically useful for visualization purposes.

size

The size of the ArFrame defines the dimension of the rectangular area where gaze positions are projected. Be aware that gaze positions have to be in the same range of value to be projected.

gaze_movement_identifier

The first ArFrame pipeline step is to identify fixations or saccades from consecutive timestamped gaze positions.

The identification algorithm can be selected by instantiating a particular GazeMovementIdentifier from the GazeAnalysis submodule or from another Python package.

In the example file, the chosen identification algorithm is the Dispersion Threshold Identification (I-DT) which has two specific deviation_max_threshold and duration_min_threshold attributes.

scan_path

The second ArFrame pipeline step aims to build a ScanPath defined as a list of ScanSteps made by a fixation and a consecutive saccade.

Once fixations and saccades are identified, they are automatically appended to the ScanPath if required.

The ScanPath.duration_max attribute is the duration from which older scan steps are removed each time new scan steps are added.

scan_path_analyzers

Finally, the last ArFrame pipeline step consists of passing the previously built ScanPath to each loaded ScanPathAnalyzer.

Each analysis algorithm can be selected by instantiating a particular ScanPathAnalyzer from the GazeAnalysis submodule or from another Python package.

In the example file, the chosen analysis algorithms are the Basic module and the ExploreExploitRatio module, which has one specific short_fixation_duration_threshold attribute.

Pipeline execution

A pipeline needs to be embedded into a context to be executed.

Copy the gaze analysis pipeline configuration defined above inside the following context configuration.

{
    "argaze.utils.contexts.Random.GazePositionGenerator": {
        "name": "Random gaze position generator",
        "range": [1920, 1080],
        "pipeline": JSON CONFIGURATION
    }
}

Then, use the load command to execute the context.

python -m argaze load CONFIGURATION

This command should open a GUI window with a random yellow dot and identified fixations circles.