Common Items
Analyzer and Type
Select the analyzer to use in AI Analyzer. Analyzers can be added, edited, and deleted directly in the selection popup, and also managed in Settings > AI Analyzer. The analysis type is determined by the analyzer's AI Model, so the action dialog shows only the commands and fields of the model that the selected analyzer uses.
The analysis types available depend on the analyzer's Media Type. A Video (Camera) analyzer uses Object Detection, Face Detection, Face Recognition, Pose Estimation, Hand Tracking, Color Tracking, QR / Barcode, OCR (Text Recognition), Line Tracking, Line Crossing Counter, Fire Detection, Action Recognition, Hand Motion Recognition, License Plate Recognition, Teachable Machine Classification, Edge Impulse Classification, Edge Impulse Object Detection, and Edge Impulse Visual Anomaly. An Audio (Mic/Speaker) analyzer uses Sound Classification and Edge Impulse Classification.
The Type field decides what this action does to the analyzer.
| Type | Description |
|---|---|
| Add Analysis | Adds an analysis to the AI analyzer. A single analyzer can hold several analyses. The command, setting, and output fields below are shown only for this type. |
| Clear Analyses / Clear All Analyses | Removes every analysis registered on this analyzer. Shown as Clear Analyses for video analyzers and Clear All Analyses for audio analyzers. |
| Start Analysis | Starts audio capture and analysis. Audio analyzers only. |
| Stop Analysis | Stops audio capture and analysis. Audio analyzers only. |
Command
The Command differs per analysis type and decides what is computed and which variables receive it. Choosing a command shows only the settings and outputs that the command needs. The commands of each type are listed in the tables of the sections below.
Common Settings
These fields have the same meaning across several types. Where a range or default differs per type, it is noted in that type's section.
| Setting | Description |
|---|---|
| Confidence (%) | Only detections at or above this value are used. The range is 0 to 100; raising it keeps only certain results, lowering it misses fewer. The default is 50 for most types and 70 for face detection. Fields labeled Threshold, Min Confidence, or Detection Threshold have the same meaning. |
| Detection Zone | Drag on the camera preview to define a rectangular area. Without one, the whole frame is analyzed; with one, only results inside it are used. |
| Select By | Decides which detection is written to the variables when several are found. Object Detection and Face Detection offer Highest Confidence, By Confidence Index (0-based), Largest Size, and Closest From Ref. Point; Color Tracking offers Largest, Closest, and By Index; QR / Barcode offers Largest Area, Nearest, and By Index; Edge Impulse Object Detection offers Best Confidence, Index, Largest, and Closest. |
| Index (0-based) | The position to pick when Select By is index-based. Object Detection and Face Detection order by confidence (0, 1, 2… from the highest); Color Tracking and QR / Barcode order by area (0, 1, 2… from the largest); Edge Impulse Object Detection uses the model's detection order. The range is 0 to 15 for objects and faces and 0 to 100 for colors. |
| Reference Point | The reference coordinates, set by clicking on the camera preview, used when Select By is the closest detection. |
Output Variables and Value Conventions
A variable bound to an output field is updated continuously while the analysis runs. Unbound outputs are not written, so bind variables only to the fields you need. The variable type of each field is fixed.
- Digital: true/false fields such as Detected, Matched, and Is Match.
- Number: counts, coordinates, width and height, confidence, probability, angle, and distance. Coordinates and sizes are in pixels of the camera frame, and a center point is the center of the detection box. Confidence and probability are 0 to 100 (OCR is the exception, see its section).
- Text: class names, recognized names, data, and JSON output.
- Color: the average color of Color Tracking.
The value written when nothing is detected is defined per type: text becomes none or an
empty string, and numbers become -1 or 0, as listed in each section's output table.
The Output (JSON Text) field writes the whole detection result as a JSON string to a text
variable. Types that return several results use an array, which is empty ([]) when
nothing is detected. The key names and samples are given under JSON Output in each section;
parse the string in block coding to pick out values.