Scores

The scores object contains the raw output probabilities produced by the classification model.

Each score is a floating-point value between 0.0 and 1.0, representing the model’s confidence that a given concept is present in the analyzed video segment.

Example:

"scores": {
  "intrusion": 0.918744163159948,
  "person": 0.12695148061787767,
  "vehicule": 0.8928721973019503,
  "animal": 0.06220918576737605,
  "flag": 0.8295322694836862,
  "plant": 0.049358549524389075,
  "rain": 0.004554292405135713,
  "wind": 0.007171697000292765,
  "text": 0.000977604282076755,
  "other": 0.020228226668765597,
  "NOTHING": 0.00025552011262380115
}

⚠️ Important:

While multiple scores are exposed for observability and debugging, risk evaluation is based exclusively on the intrusion score.

Risk Levels

The system exposes three and only three risk levels:

• safe
• danger
• intrusion

These risk levels are directly derived from the intrusion score, using two configurable thresholds.

Thresholds

Typical configuration example:

low_threshold  = 0.2
high_threshold = 0.8

Risk Derivation Logic