Function Introduction-Object Classification

This function can learn multiple photos of different objects, and then use the built-in machine learning algorithm for training. After the training is completed, when the learned objects appear again in the HuskyLens' camera, HuskyLens can recognize them and display their ID numbers. The more HuskyLens learns the photos of the same object, the more accurate the recognition can be.

The default setting is to learn multiple objects. This chapter uses recognizing whether a worker wears a helmet as an example to demonstrate.

Operation and Setting

1. Dial the function button to the right or left until the words "Object Classification" is displayed at the top of the screen.

2. Long press the function button to enter the parameter setting of the object classification function.

3. Dial the function button until "Learn Multiple" is displayed, then short press the function button, and dial to the right to turn on the "Learn Multiple" switch, that is, progress bar turns blue and the square icon on the progress bar moves to the right. Then short press the function button to confirm this parameter.

   

4. Dial the function button to the left until "Save & Return" shows. And the screen prompts "Do you want to save the parameters?" Select "Yes" in default, now short-press the function button to save the parameters and return automatically.

Learning and Detection

You can use the following picture to test.

1. Object Learning:

   Point the large frame at the first target object(the worker with a helmet on the left in the picture above), and long press the “learning button”, a yellow frame with words "Learning XX/30 ID:1" will be displayed on the screen, indicating that HuskyLens is learning the object now. Adjust the distance and angle, let HuskyLens learn the object in various distances and angles. Then, release the "learning button" to complete learning the first object, meanwhile, a message "Click again to continue! Click other button to finish" will be displayed. Please short press the "learning button" before the countdown ends if you want to learn other objects. If not, short press the "function button" before the countdown ends, or do not press any button to let the countdown ends.
   

   In this chapter, you need to continue to learn the next object (the worker without a helmet on the right in the above picture), so press the "learning button" before the countdown ends, and then point the large frame at the second target object, long press the "learning button" to complete the learning of the second object. And so on.

   The order of the object ID and the learned object is the same, that is: the learned objects will be marked as "object: ID1", "Object: ID2", "Object: ID3", and so on, and the color of the frame corresponding to the object is also different.

2. Object Recognition:

   When HuskyLens encounters the learned object again, its ID number will be displayed on the screen. As shown in the figure below, when HuskyLens recognizes that the worker is wearing a helmet, the screen displays ID1, and if there is no helmet, it displays ID2.

   

More interesting ideas based on object classification: Click here to view

• Can the object classification function give the relative position of the object?
  Answer: No. In the object classification function, the position of the frame is fixed, and its x and y center coordinates on the screen remain unchanged, so it cannot give the relative position of the object on the screen. But you can learn different positions of objects as different IDs, and judge the position by ID. For example, in automatic vehicles, learn the ID 1, 2, and 3 as on the left, middle, and right sides of the road. By judging the ID, you can know the position of the automatic vehicles relative to the road.
• How to improve the accuracy of recognition under the object classification algorithm?
  Answer: Long press the "learning button" without releasing it, you can let HuskyLens learn the target photos from multiple angles and distances, to improve the recognition accuracy.