Edge Impulse Visual Anomaly

Judges normal versus abnormal states with a visual anomaly detection model trained in Edge Impulse. The frame is divided into a grid, each cell receives an anomaly score, and the mean and maximum over the grid are provided. The model is uploaded in the analyzer setting Model Path (.eim).

Commands

Command	Description
Get Result	Writes the mean score, max score, and anomaly verdict to variables.
Is Anomaly?	Checks whether the result is an anomaly by the threshold.
Get Grid Info	Writes the anomaly score of every grid cell as JSON.

Settings

Setting	Description
Anomaly Threshold (%)	Scores above this value are judged as anomalies. 0 to 100, default 50.

Output Variables

Field	Type	Value
Mean Score	Number	Mean anomaly score over all grid cells, 0 to 100.
Max Score	Number	Highest anomaly score among the grid cells, 0 to 100.
Is Anomaly	Digital	True when judged as an anomaly.
Output (JSON Text)	Text	A JSON object with the mean, max, and grid.

JSON Output

A single object, not an array. Each cell in grid has its position x and y, size width and height, and anomaly score value (0 to 100).

{
  "mean": 45,
  "max": 78,
  "grid": [
    { "x": 0, "y": 0, "width": 32, "height": 32, "value": 12 },
    { "x": 32, "y": 0, "width": 32, "height": 32, "value": 67 },
    { "x": 64, "y": 0, "width": 32, "height": 32, "value": 78 }
  ]
}