Visión de IA#

Introducción#

El sensor de visión con IA permite a un robot detectar y rastrear información visual de su entorno. Al identificar objetos, colores y patrones, el sensor le permite analizar su entorno y reaccionar a lo que ve.

This page uses AIVision1 as the example AI Vision Sensor name. Color Signature objects (such as redBox) and Color Code objects (such as redBlue) are also used in examples. Replace these names with your own configured names as needed.

A continuación se muestra una lista de todos los métodos:

Conseguidores

  • takeSnapshot — Captures data for a specific Color Signature or Color Code.

  • objectCount — Returns the number of detected objects as an integer.

  • largestObject — Immediately select the largest object from the snapshot.

  • installed — Whether the AI Vision Sensor is connected to the V5 Brain.

Properties — Object data returned from takeSnapshot.

  • .exists — Whether the object exists in the current detection as a Boolean.

  • .width — Width of the detected object in pixels.

  • .height — Height of the detected object in pixels.

  • .centerX — X position of the object’s center in pixels.

  • .centerY — Y position of the object’s center in pixels.

  • .angle — Orientation of the Color Code in degrees.

  • .originX — X position of the object’s top-left corner in pixels.

  • .originY — Y position of the object’s top-left corner in pixels.

  • .id — Classification ID or AprilTag ID of the object.

  • .score — Confidence score for AI Classifications.

Constructores: inicializan y configuran manualmente los sensores.

Tomar instantánea#

takeSnapshot captures an image from the AI Vision Sensor, processes it based on the signature, and updates the objects array. This method can also limit the amount of objects captured in the snapshot.

Las Firmas de color y los Códigos de color deben configurarse primero en la Utilidad de visión antes de poder usarse con este método.

The objects array stores objects ordered from largest to smallest by width, starting at index 0. Each object’s properties can be accessed using its index. objects is an empty array if no matching objects are detected.

Default Usage:
AIVision1.takeSnapshot(signature)

Overloads:
AIVision1.takeSnapshot(signature, count)

Parámetros

Descripción

signature

The signature to retrieve data for.

  • Color Signatures or Color Codes — The name of the AI Vision Sensor, two underscores, and then the Color Signature’s or Color Code’s name.For example: AIVision1__redBox.
  • aivision::ALL_AIOBJS — Cubes, Rings, and Buckyballs.
  • aivision::ALL_TAGS — All AprilTag IDs.

count

Opcional. Establece el número máximo de objetos que se pueden devolver, de 1 a 24 (valor predeterminado: 8).

 
int main() {
  // Initializing Robot Configuration. DO NOT REMOVE!
  vexcodeInit();
  // Move forward if an object is detected
  while (true) {
    AIVision1.takeSnapshot(aivision::ALL_AIOBJS);
    if (AIVision1.objects[0].exists) {
      Drivetrain.driveFor(forward, 50, mm);
    }
    wait(50, msec);
  }
}

AI Classifications#

El sensor de visión de IA puede detectar diferentes objetos bajo ciertas clasificaciones de IA. Según el modelo de clasificación de IA seleccionado al configurar el sensor en la ventana Dispositivos, se pueden detectar diferentes objetos. Los modelos disponibles actualmente son:

Elementos del aula

Número de identificación

Clasificación de IA

0

blueBall

1

greenBall

2

redBall

3

blueRing

4

greenRing

5

redRing

6

blueCube

7

greenCube

8

redCube

V5RC de alto riesgo

Número de identificación

Clasificación de IA

0

mobileGoal

1

redRing

2

blueRing

V5RC Empuje hacia atrás

Número de identificación

Clasificación de IA

0

blueBlock

1

redBlock

Color Signatures#

A color signature is a unique color that the AI Vision Sensor can recognize. These signatures allow the AI Vision Sensor to detect and track objects based on their color. Once a color signature is configured, the sensor can identify objects with that specific color in its field of view. Color signatures are used with takeSnapshot to process and detect colored objects in real-time.

In order to use a configured color signature in a project, its name must be the name of the sensor, two underscores, and then the color signature’s name. For example: AIVision1__redBox.

int main() {
  // Initializing Robot Configuration. DO NOT REMOVE!
  vexcodeInit();

  while (true) {
    // Display when the color signature is detected
    Brain.Screen.setCursor(1, 1);
    Brain.Screen.clearLine(1);
    // Change to any configured Color Signature
    AIVision1.takeSnapshot(AIVision1__redBox);
    if (AIVision1.objects[0].exists) {
      Brain.Screen.print("Color detected!");
    }
    wait(50, msec);
  }
}

Color Codes#

Un código de color es un patrón estructurado compuesto por firmas de color dispuestas en un orden específico. Estos códigos permiten al sensor de visión de IA reconocer patrones de color predefinidos. Los códigos de color son útiles para identificar objetos complejos o crear marcadores únicos para la navegación autónoma.

To use a configured color code in a project, its name must be passed as a string in the format: the AI Vision Sensor’s name, followed by two underscores, and then the color code’s name. For example: AIVision1__redBlue.

int main() {
  // Initializing Robot Configuration. DO NOT REMOVE!
  vexcodeInit();

  while (true) {
    // Display when the color code is detected
    Brain.Screen.setCursor(1, 1);
    Brain.Screen.clearLine(1);
    // Change to any configured Color Code
    AIVision1.takeSnapshot(AIVision1__redBlue);
    if (AIVision1.objects[0].exists) {
      Brain.Screen.print("Code detected!");
    }
    wait(50, msec);
  }
}

objectCount#

objectCount returns the number of items inside the objects array as an integer.

Default Usage:
AIVision1.objectCount

Parámetros

Descripción

Este método no tiene parámetros.

 
int main() {
  // Initializing Robot Configuration. DO NOT REMOVE!
  vexcodeInit();
  // Display the number of detected objects
  while (true) {
    Brain.Screen.setCursor(1, 1);
    Brain.Screen.clearLine(1);
    AIVision1.takeSnapshot(aivision::ALL_AIOBJS);
    if (AIVision1.objects[0].exists) {
      Brain.Screen.print("%d", AIVision1.objectCount);
    }
    wait(50, msec);
  }
}

objeto más grande#

largestObject retrieves the largest detected object from the objects array.

This method can be used to always get the largest object from objects without specifying an index.

Default Usage:
AIVision1.largestObject

Parámetros

Descripción

Este método no tiene parámetros.

 
int main() {
  // Initializing Robot Configuration. DO NOT REMOVE!
  vexcodeInit();
  // Display the closest AprilTag's ID
  while (true) {
    Brain.Screen.setCursor(1, 1);
    Brain.Screen.clearLine(1);
    AIVision1.takeSnapshot(aivision::ALL_TAGS);
    if (AIVision1.objects[0].exists) {
      Brain.Screen.print("%d", AIVision1.largestObject.id);
    }
    wait(50, msec);
  }
}

instalado#

installed returns an integer indicating whether the AI Vision Sensor is currently connected to the V5 Brain.

  • 1 — The AI Vision Sensor is connected to the V5 Brain.

  • 0 — The AI Vision Sensor is not connected to the V5 Brain.

Parámetros

Descripción

Este método no tiene parámetros.

 
int main() {
  // Initializing Robot Configuration. DO NOT REMOVE!
  vexcodeInit();
  // Display a message if the AI Vision Sensor is detected
  if (AIVision1.installed()){
    Brain.Screen.print("Installed!");
  }
}

objetos#

objects returns an array of detected object properties. Use the array to access specific property values of individual objects.

Default Usage:
AIVision1.objects

Properties#

There are ten properties that are included with each object stored in the objects array after takeSnapshot is used.

Some property values are based off of the detected object’s position in the AI Vision Sensor’s view at the time that takeSnapshot was used. The AI Vision Sensor has a resolution of 320 by 240 pixels.

.existe#

.exists returns an integer indicating if the index exists in the objects array or not.

  • 1: The index exists.

  • 0: The index does not exist.

int main() {
  // Initializing Robot Configuration. DO NOT REMOVE!
  vexcodeInit();
  // Move forward if an object is detected
  while (true) {
    AIVision1.takeSnapshot(aivision::ALL_AIOBJS);
    if (AIVision1.objects[0].exists) {
      Drivetrain.driveFor(forward, 50, mm);
    }
    wait(50, msec);
  }
}

.ancho#

.width returns the width of the detected object in pixels, which is an integer between 1 and 320.

int main() {
  // Initializing Robot Configuration. DO NOT REMOVE!
  vexcodeInit();
  // Approach an object until it's at least 100 pixels wide
  while (true) {
    AIVision1.takeSnapshot(aivision::ALL_AIOBJS);

    if (AIVision1.objects[0].exists) {
      if (AIVision1.objects[0].width < 100) {
        Drivetrain.drive(forward);
      } else {
        Drivetrain.stop();
      }
    } else {
      Drivetrain.stop();
    }
    wait(50, msec);
  }
}

.altura#

.height returns the height of the detected object in pixels, which is an integer between 1 and 240.

int main() {
  // Initializing Robot Configuration. DO NOT REMOVE!
  vexcodeInit();
  // Approach an object until it's at least 90 pixels tall
  while (true) {
    AIVision1.takeSnapshot(aivision::ALL_AIOBJS);

    if (AIVision1.objects[0].exists) {
      if (AIVision1.objects[0].height < 90) {
        Drivetrain.drive(forward);
      } else {
        Drivetrain.stop();
      }
    } else {
      Drivetrain.stop();
    }
    wait(50, msec);
  }
}

.centroX#

.centerX returns the x-coordinate of the detected object’s center in pixels, which is an integer between 0 and 320.

int main() {
  // Initializing Robot Configuration. DO NOT REMOVE!
  vexcodeInit();
  // Turn until an object is directly in front of the sensor
  Drivetrain.setTurnVelocity(10, percent);
  Drivetrain.turn(right);
  while (true) {
    AIVision1.takeSnapshot(aivision::ALL_AIOBJS);

    if (AIVision1.objects[0].exists) {
      if (AIVision1.objects[0].centerX > 140 && AIVision1.objects[0].centerX < 180) {
        Drivetrain.stop();
      }
    }

    wait(10, msec);
  }
}

.centroY#

.centerY returns the y-coordinate of the detected object’s center in pixels, which is an integer between 0 and 240.

int main() {
  // Initializing Robot Configuration. DO NOT REMOVE!
  vexcodeInit();
  // Approach an object until it's close to the sensor
  while (true) {
    AIVision1.takeSnapshot(aivision::ALL_AIOBJS);

    if (AIVision1.objects[0].exists) {
      if (AIVision1.objects[0].centerY < 150) {
        Drivetrain.drive(forward);
      } else {
        Drivetrain.stop();
      }
    } else {
      Drivetrain.stop();
    }
    wait(50, msec);
  }
}

.ángulo#

.angle returns the orientation of the detected color code or AprilTag ID in degrees, which is a double between 0 and 360.

int main() {
  // Initializing Robot Configuration. DO NOT REMOVE!
  vexcodeInit();
  // Turn left or right depending on how a configured
  // Color Code is rotated
  while (true) {
    AIVision1.takeSnapshot(AIVision1__redBlue);
    if (AIVision1.objects[0].exists) {
      if (AIVision1.objects[0].angle > 50 && AIVision1.objects[0].angle < 100) {
        Drivetrain.turn(right);
      }
      else if (AIVision1.objects[0].angle > 270 && AIVision1.objects[0].angle < 330) {
        Drivetrain.turn(left);
      }
      else {
        Drivetrain.stop();
      }
    } else {
      Drivetrain.stop();
    }
    wait(50, msec);
  }
}

.origenX#

.originX returns the x-coordinate of the top-left corner of the detected object’s bounding box in pixels, which is an integer between 0 and 320.

int main() {
  // Initializing Robot Configuration. DO NOT REMOVE!
  vexcodeInit();
  // Display if an object is to the left or the right
  while (true) {
    Brain.Screen.clearScreen();
    Brain.Screen.setCursor(1, 1);
    AIVision1.takeSnapshot(aivision::ALL_AIOBJS);
    if (AIVision1.objects[0].exists) {
      if (AIVision1.objects[0].originX < 120) {
        Brain.Screen.print("To the left!");
      } else {
        Brain.Screen.print("To the right!");
      }
    } else {
      Brain.Screen.print("No objects");
    }
    wait(100, msec);
  }
}

.origenY#

.originY returns the y-coordinate of the top-left corner of the detected object’s bounding box in pixels, which is an integer between 0 and 240.

int main() {
  // Initializing Robot Configuration. DO NOT REMOVE!
  vexcodeInit();
  // Display if an object is close or far
  while (true) {
    Brain.Screen.clearScreen();
    Brain.Screen.setCursor(1, 1);
    AIVision1.takeSnapshot(aivision::ALL_AIOBJS);
    if (AIVision1.objects[0].exists) {
      if (AIVision1.objects[0].originY < 110) {
        Brain.Screen.print("Close");
      } else {
        Brain.Screen.print("Far");
      }
    }
    wait(100, msec);
  }
}

.identificación#

.id returns the ID of the detected AI Classification or AprilTag ID as an integer.

Para las clasificaciones de IA, consulte las tablas de clasificación de IA para obtener los ID correspondientes.

For an AprilTag ID, the .id property represents the detected AprilTag’s ID number in the range of 0 to 36. For an AI Classification, the ID corresponds to the predefined ID as shown below.

int main() {
  // Initializing Robot Configuration. DO NOT REMOVE!
  vexcodeInit();
  // Move forward when AprilTag ID 1 is detected
  while (true) {
    AIVision1.takeSnapshot(aivision::ALL_TAGS);
    if (AIVision1.objects[0].exists) {
      if (AIVision1.objects[0].id == 1) {
        Drivetrain.drive(forward);
      }
    } else {
      Drivetrain.stop();
    }
    wait(50, msec);
  }
}

.puntaje#

.score returns the confidence score of the detected AI Classification as an integer between 1 and 100.

int main() {
  // Initializing Robot Configuration. DO NOT REMOVE!
  vexcodeInit();
  // Display if a score is confident
  while (true) {
    AIVision1.takeSnapshot(aivision::ALL_AIOBJS);

    if (AIVision1.objects[0].exists) {
      Brain.screen.clearScreen();
      Brain.screen.setCursor(1, 1);

      if (AIVision1.objects[0].score > 95) {
        Brain.Screen.print("Confident");
      } else {
        Brain.Screen.print("Not confident");
      }
    }

    wait(50, msec);
  }
}

Constructores#

Constructors are used to manually create aivision, aivision::colordesc, and aivision::codedesc objects, which are necessary for configuring the AI Vision Sensor outside of VEXcode.

aivision#

aivision creates an AI Vision Sensor.

Default Usage:
aivision(port, sigs)

Parámetros

Descripción

port

A qué puerto inteligente está conectado el sensor de visión IA, del 1 al 21.

sigs

Optional. The name of one or more signatures: 

// Create the Color Signatures
aivision::colordesc AIVision1__greenBox(1, 85, 149, 46, 23, 0.23);
aivision::colordesc AIVision1__blueBox(2, 77, 135, 125, 27, 0.29);

// Create a Color Code
aivision::codedesc AIVision1__greenBlue(1, AIVision1__greenBox, AIVision1__blueBox);

/*
Create a Vision Sensor with the following values:
port: Port 1
sigs: greenBlue and AI Classifications
*/
aivision AIVision1(PORT11, AIVision1__greenBlue, aivision::ALL_AIOBJS);

aivision::colordesc#

aivision::colordesc creates a color signature. Up to seven different color signatures can be stored on an AI Vision Sensor at once.

Default Usage:
aivision::colordesc(index, red, green, blue, hangle, hdsat)

Parámetro

Descripción

index

The colordesc object’s index, from 1 - 7.
Note: Creating two colordesc objects with the same index number will cause the second created object to override the first.

red

El valor rojo del color de 0 a 255.

green

El valor del color verde de 0 a 255.

blue

El valor azul del color de 0 a 255.

hangle

Variación de tono admisible expresada en grados en el círculo cromático (1-40). Los valores más altos permiten una desviación rotacional más amplia respecto al tono base.

hdsat

La desviación de saturación permitida, de 0,10 a 1,00. Este valor representa la fracción del rango completo de saturación dentro del cual el color puede variar (p. ej., 0,10 = ±10 % de saturación).

 
/*
Create a Color Signature with the following values:
index: 1
red: 81
green: 149
blue: 44
hangle: 17
hsat: 0.23
*/

aivision::colordesc AIVision1__greenBox(1, 81, 149, 44, 17, 0.23);

aivision::codedesc#

aivision::codedesc creates a color code. It requires at least two already created aivision::colordesc in order to be used. Up to eight different color codes can be stored on an AI Vision Sensor at once.

Default Usage:
aivision::codedesc(sigs)

Parámetros

Descripción

sigs

Two or more previously created aivision::colordesc, named using the format AIVisionSensor__colorSignature (for example, AIVision1__blueBox), separated by commas. A color code can include up to five different color signatures.

 
// Create the Color Signatures
aivision::colordesc AIVision1__greenBox(1, 85, 149, 46, 23, 0.23);
aivision::colordesc AIVision1__blueBox(2, 77, 135, 125, 27, 0.29);

// Create a Color Code with the Color Signatures
aivision::codedesc AIVision1__greenBlue(1, AIVision1__greenBox, AIVision1__blueBox);
En esta página