Coding with the AI Vision Sensor in VEXcode EXP Python

Make sure you have Color Signatures and Color Codes configured with your AI Vision Sensor so they can be used with your blocks. To learn more about how to configure them, you can read the articles below:

• Configuring Color Signatures with the AI Vision Signature in VEXcode EXP
• Configuring Color Codes with the AI Vision Signature in VEXcode EXP

The AI Vision Sensor can also detect AI Classifcations and AprilTags. To learn how to enable these detection modes, go here:

• AI Classifications with the AI Vision Sensor in VEXcode EXP
• AprilTags with the AI Vision Sensor in VEXcode EXP

To learn more detail about these individual commands and how to use them in VEXcode, go to the API site.

---

Obtain Visual Data with the AI Vision Sensor

Every AI Vision Sensor command will start with the name of the configured AI Vision Sensor. For all the examples in this article, the name of the AI Vision Sensor used will be ai_vision_1.

take_snapshot

The take_snapshot method takes a picture of what the AI Vision Sensor is currently seeing and pulls data from that snapshot that can then be used in a project. When a snapshot is taken, you need to specify what type of object the AI Vision Sensor should collect data of:

• A Color Signature or Color Code
  • These Visual Signatures start with the name of the AI Vision Sensor, double underscore, and then the name of the Visual Signature, for example: ai_vision_1__Blue.
• AI Classifications - AiVision.ALL_AIOBJS
• AprilTags - AiVision.ALL_TAGS

Taking a snapshot will create a tuple of all of the detected objects that you specified. For instance, if you wanted to detect a "Blue" Color Signature, and the AI Vision Sensor detected 3 different blue objects, data from all three would be put in the tuple.

In this example, the variable vision_objects stores a tuple containing the detected "Purple" Color Signatures from the AI Vision Sensor named ai_vision_1. It displays the number of objects detected and captures a new snapshot every 0.5 seconds.

while True: 
    # Get a snapshot of all Purple Color Signatures and store it in vision_objects.
    vision_objects = ai_vision_1.take_snapshot(ai_vision_1__Purple)
    
    # Check to make sure an object was detected in the snapshot before pulling data.
    if vision_objects[0].exists == True
    
        brain.screen.clear_screen()
        brain.screen.set_cursor(1, 1)
    
        brain.screen.print("Object count:", len(vision_objects))
    wait(0.5, SECONDS)

Object Properties

Every object from a snapshot has different properties that can be used to report information about that object. The available properties are as follows:

• id
• centerX and centerY
• originX and originY
• width
• height
• angle
• score
• exists

To access an object's property, use the variable name storing the tuple, followed by the object index.

The object index indicates which specific object's property you want to retrieve. After taking a snapshot, the AI Vision Sensor automatically sorts objects by size. The largest object is assigned index 0, with smaller objects receiving higher index numbers.

For example, calling the largest's object's width inside the vision_objects variable would be: vision_objects[0].width.

id

The id property is only available for AprilTags and AI Classifications.

Go to these articles for more information on AprilTags and AI Classifications and how to enable their detection in the AI Vision Utility.

centerX and centerY

This is the center coordinates of the detected object in pixels.

In this example, because the center of the AI Vision Sensor's view is (160, 120), the robot will turn right until a detected object's centerX coordinate is greater than 150 pixels, but less than 170 pixels.

while True:
    # Get a snapshot of all Blue Color Signatures and store it in vision_objects.
    vision_objects = ai_vision_1.take_snapshot(ai_vision_1__Blue)

    # Check to make sure an object was detected in the snapshot before pulling data.
    if vision_objects[0].exists == True

        # Check if the object isn't in the center of the AI Vision Sensor's view.
        if vision_objects[0].centerX > 150 and 170 > vision_objects[0].centerX:

            # Keep turning right until the object is in the center of the view.
            drivetrain.turn(RIGHT)
        else:
            drivetrain.stop()
    wait(5, MSEC)

originX and originY

OriginX and OriginY is the coordinate at the top-left corner of the detected object in pixels.

width and height

This is the width or height of the detected object in pixels.

In this example, the width of the object is used for navigation. The robot will approach the object until the width has reached a specific size before stopping.

while True:
    # Get a snapshot of all Blue Color Signatures and store it in vision_objects.
    vision_objects = ai_vision_1.take_snapshot(ai_vision_1__Blue)

    # Check to make sure an object was detected in the snapshot before pulling data.
    if vision_objects[0].exists == True

        # Check if the largest object is close to the AI Vision Sensor by measuring its width.
        if vision_objects[0].width < 250:

            # Drive closer to the object until it's wider than 250 pixels.
            drivetrain.drive(FORWARD)
        else:
            drivetrain.stop()

    wait(5, MSEC)

angle

score

The score property is used when detecting AI Classifications with the AI Vision Sensor.

exists

The exists property is used to detect if a specified Visual Signature has been detected in the last taken snapshot.

This lets you check if any detected objects were detected in the previous snapshot. This property will return a True when an object exists, and a False when the object does not exist.