Object Classification Example
HuskyLens 2 object classification lets micro:bit projects detect up to 1000 categories and output each object’s name via serial, like a smart labeler for everything in view. It’s like giving your camera flashcards so it can instantly tell you what it sees.
1. Object Classification Project Example
Before You Start:
1.1 Object Classification and Output Related Data
When object classification is enabled, HuskyLens 2 can classify 1000 fixed categories of objects and identify learned objects, allowing you to access key data: total detected objects,classified object ID, object name). The system uses pre-trained models to recognize common objects without requiring extensive training.
Example program:
Connect to micro:bit and click Download to transfer the program. After successful download, click Show Data to activate data output mode. Point the HuskyLens 2 camera at various objects to observe the classification results.
As shown, when HuskyLens 2 successfully classifies an object such as "mouse", the following data will display:
How to use object classification, please refer to the Object Classification tutorial.
Result: The serial port will output: classified object name.
1.2 Object Classification Blocks Description
| block | Description |
|---|---|
|
Used to obtain one set of Object Classification data under the Object Classification function of HUSKYLENS 2. |
|
Determine if a recognizable object is present and classified in the current frame. |
|
Get the total number of object detected on the screen. |
|
Retrieves data of the classified object, including object ID and object name based on the pre-trained classification model. |
Was this article helpful?