Scan path analyzers

ArGaze provides ready-to-use scan path analysis algorithms.

Definition

A ScanPath is defined as a list of ScanSteps made by a fixation and a consecutive saccade.

The JSON samples have to be included inside ArFrame configuration scan_path_analyzers entry to select an algorithm.

"scan_path_analyzers": {
    JSON sample
}

Read more about ScanPathAnalyzer base class in code reference.

Note

The members indicated as property are what returns the analyzer.

Basic metrics

Bases: GazeFeatures.ScanPathAnalyzer

Basic scan path analysis.

path_duration: float property

Scan path duration.

step_fixation_durations_average: float property

Scan path step fixation durations average.

steps_number: float property

Scan path steps number.

JSON sample

"argaze.GazeAnalysis.Basic.ScanPathAnalyzer": {}

Explore/Exploit ratio

Bases: GazeFeatures.ScanPathAnalyzer

Implementation of explore vs exploit ratio algorithm as described in:

Dehais F., Peysakhovich V., Scannella S., Fongue J., Gateau T. (2015).
Automation surprise in aviation: Real-time solutions.
Proceedings of the 33rd annual ACM conference on Human Factors in Computing Systems (2525–2534).
https://doi.org/10.1145/2702123.2702521

explore_exploit_ratio: float property

Explore/Exploit ratio.

short_fixation_duration_threshold: float property writable

Time below which a fixation is considered to be short and so as exploratory.

JSON sample

"argaze.GazeAnalysis.ExploreExploitRatio.ScanPathAnalyzer": {
    "short_fixation_duration_threshold": 0
}

K coefficient

Bases: GazeFeatures.ScanPathAnalyzer

Implementation of the K coefficient algorithm as described in:

Krejtz K., Duchowski A., Krejtz I., Szarkowska A., & Kopacz A. (2016).
Discerning ambient/focal attention with coefficient K.
ACM Transactions on Applied Perception (TAP, 1–20).
https://doi.org/10.1145/2896452

K: float property

K coefficient.

JSON sample

"argaze.GazeAnalysis.KCoefficient.ScanPathAnalyzer": {}

Nearest neighbor index

Bases: GazeFeatures.ScanPathAnalyzer

Implementation of Nearest Neighbor Index algorithm as described in:

Di Nocera F., Terenzi M., Camilli M. (2006).
Another look at scan path: distance to nearest neighbour as a measure of mental workload. Developments in Human Factors in Transportation, Design, and Evaluation.
https://www.researchgate.net

nearest_neighbor_index: float property

Nearest Neighbor Index.

size: tuple[float, float] property writable

Frame dimension.

JSON sample

"argaze.GazeAnalysis.NearestNeighborIndex.ScanPathAnalyzer": {}