Detección de equipos de protección individual en una imagen

Para detectar el equipo de protección personal (EPP) en las personas de una imagen, utilice la operación API DetectProtectiveEquipmentsin almacenamiento.

Puede proporcionar la imagen de entrada como matriz de bytes de imagen (bytes de imagen con codificación base64) o como un objeto de Amazon S3, utilizando el AWS SDK o la AWS Command Line Interface (AWS CLI). En estos ejemplos, se utiliza una imagen almacenada en un bucket de Amazon S3. Para obtener más información, consulte Trabajar con imágenes.

Para detectar el EPI en las personas de una imagen

Si aún no lo ha hecho:
1. Cree o actualice un usuario con los permisos AmazonRekognitionFullAccess y AmazonS3ReadOnlyAccess. Para obtener más información, consulte Paso 1: Configurar una cuenta de AWS y crear un usuario.
2. Instale y configure los AWS SDK AWS CLI y los mismos. Para obtener más información, consulte Paso 2: Configurar los SDK AWS CLI y AWS.
Suba una imagen que contenga una o varias personas llevando EPI en su bucket de S3.

Para ver las instrucciones, consulte Carga de objetos en Amazon S3 en la Guía del usuario de Amazon Simple Storage Service.

Consulte los siguientes ejemplos para llamar a la operación DetectProtectiveEquipment. Para obtener información sobre cómo mostrar los cuadros delimitadores en una imagen, consulte Visualización de cuadros delimitadores.

Java

En este ejemplo, se muestra información sobre los elementos de EPI detectados en las personas detectadas en una imagen.

Cambie el valor de bucket por el nombre del bucket de Amazon S3 que contiene su imagen. Cambie el valor de photo por el nombre de su archivo de imagen.


//Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
//PDX-License-Identifier: MIT-0 (For details, see https://github.com/awsdocs/amazon-rekognition-developer-guide/blob/master/LICENSE-SAMPLECODE.)

package com.amazonaws.samples;
import com.amazonaws.client.builder.AwsClientBuilder;
import com.amazonaws.services.rekognition.AmazonRekognition;
import com.amazonaws.services.rekognition.AmazonRekognitionClientBuilder;
import com.amazonaws.services.rekognition.model.AmazonRekognitionException;
import com.amazonaws.services.rekognition.model.Image;
import com.amazonaws.services.rekognition.model.ProtectiveEquipmentBodyPart;
import com.amazonaws.services.rekognition.model.S3Object;
import com.amazonaws.services.rekognition.model.ProtectiveEquipmentPerson;
import com.amazonaws.services.rekognition.model.ProtectiveEquipmentSummarizationAttributes;

import java.util.List;
import com.amazonaws.services.rekognition.model.BoundingBox;
import com.amazonaws.services.rekognition.model.DetectProtectiveEquipmentRequest;
import com.amazonaws.services.rekognition.model.DetectProtectiveEquipmentResult;
import com.amazonaws.services.rekognition.model.EquipmentDetection;


public class DetectPPE {

    public static void main(String[] args) throws Exception {

        String photo = "photo";
        String bucket = "bucket";


        AmazonRekognition rekognitionClient = AmazonRekognitionClientBuilder.defaultClient();
        
        ProtectiveEquipmentSummarizationAttributes summaryAttributes = new ProtectiveEquipmentSummarizationAttributes()
                .withMinConfidence(80F)
                .withRequiredEquipmentTypes("FACE_COVER", "HAND_COVER", "HEAD_COVER");
                
        DetectProtectiveEquipmentRequest request = new DetectProtectiveEquipmentRequest()
                .withImage(new Image()
                        .withS3Object(new S3Object()
                                .withName(photo).withBucket(bucket)))
                .withSummarizationAttributes(summaryAttributes);

        try {
            System.out.println("Detected PPE for people in image " + photo);
            System.out.println("Detected people\n---------------");
            DetectProtectiveEquipmentResult result = rekognitionClient.detectProtectiveEquipment(request);


            List <ProtectiveEquipmentPerson> persons = result.getPersons();


            for (ProtectiveEquipmentPerson person: persons) {
                System.out.println("ID: " + person.getId());
                List<ProtectiveEquipmentBodyPart> bodyParts=person.getBodyParts();
                if (bodyParts.isEmpty()){
                    System.out.println("\tNo body parts detected");
                } else
                    for (ProtectiveEquipmentBodyPart bodyPart: bodyParts) {
                        System.out.println("\t" + bodyPart.getName() + ". Confidence: " + bodyPart.getConfidence().toString());



                        List<EquipmentDetection> equipmentDetections=bodyPart.getEquipmentDetections();

                        if (equipmentDetections.isEmpty()){
                            System.out.println("\t\tNo PPE Detected on " + bodyPart.getName());

                        } 
                        else {
                            for (EquipmentDetection item: equipmentDetections) {
                                System.out.println("\t\tItem: " + item.getType() + ". Confidence: " + item.getConfidence().toString());
                                System.out.println("\t\tCovers body part: " 
                                        + item.getCoversBodyPart().getValue().toString() + ". Confidence: " + item.getCoversBodyPart().getConfidence().toString());

                                System.out.println("\t\tBounding Box");
                                BoundingBox box =item.getBoundingBox();

                                System.out.println("\t\tLeft: " +box.getLeft().toString());
                                System.out.println("\t\tTop: " + box.getTop().toString());
                                System.out.println("\t\tWidth: " + box.getWidth().toString());
                                System.out.println("\t\tHeight: " + box.getHeight().toString());
                                System.out.println("\t\tConfidence: " + item.getConfidence().toString());
                                System.out.println();
                            }
                        }

                    }
            }
            System.out.println("Person ID Summary\n-----------------");
            
            //List<Integer> list=;
            DisplaySummary("With required equipment", result.getSummary().getPersonsWithRequiredEquipment());
            DisplaySummary("Without required equipment", result.getSummary().getPersonsWithoutRequiredEquipment());
            DisplaySummary("Indeterminate", result.getSummary().getPersonsIndeterminate());         
       
            
        } catch(AmazonRekognitionException e) {
            e.printStackTrace();
        }
    }
    static void DisplaySummary(String summaryType,List<Integer> idList)
    {
        System.out.print(summaryType + "\n\tIDs  ");
        if (idList.size()==0) {
            System.out.println("None");
        }
        else {
            int count=0;
            for (Integer id: idList ) { 
                if (count++ == idList.size()-1) {
                    System.out.println(id.toString());
                }
                else {
                    System.out.print(id.toString() + ", ");
                }
            }
        }
                    
        System.out.println();
        
    
    }
}

Java V2

Este código se ha tomado del GitHub repositorio de ejemplos del SDK de AWS documentación. Consulte el ejemplo completo aquí.


//snippet-start:[rekognition.java2.detect_ppe.import]
import software.amazon.awssdk.auth.credentials.ProfileCredentialsProvider;
import software.amazon.awssdk.core.ResponseBytes;
import software.amazon.awssdk.core.SdkBytes;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.rekognition.RekognitionClient;
import software.amazon.awssdk.services.rekognition.model.BoundingBox;
import software.amazon.awssdk.services.rekognition.model.DetectProtectiveEquipmentRequest;
import software.amazon.awssdk.services.rekognition.model.DetectProtectiveEquipmentResponse;
import software.amazon.awssdk.services.rekognition.model.EquipmentDetection;
import software.amazon.awssdk.services.rekognition.model.ProtectiveEquipmentBodyPart;
import software.amazon.awssdk.services.rekognition.model.ProtectiveEquipmentSummarizationAttributes;
import software.amazon.awssdk.services.rekognition.model.Image;
import software.amazon.awssdk.services.rekognition.model.RekognitionException;
import software.amazon.awssdk.services.s3.S3Client;
import software.amazon.awssdk.services.s3.model.GetObjectRequest;
import software.amazon.awssdk.services.s3.model.GetObjectResponse;
import software.amazon.awssdk.services.s3.model.S3Exception;
import software.amazon.awssdk.services.rekognition.model.ProtectiveEquipmentPerson;
import java.io.ByteArrayInputStream;
import java.io.InputStream;
import java.util.List;
//snippet-end:[rekognition.java2.detect_ppe.import]

/**
* Before running this Java V2 code example, set up your development environment, including your credentials.
*
* For more information, see the following documentation topic:
*
* https://docs.aws.amazon.com/sdk-for-java/latest/developer-guide/get-started.html
*/
public class DetectPPE {

 public static void main(String[] args) {

     final String usage = "\n" +
         "Usage: " +
         "   <sourceImage> <bucketName>\n\n" +
         "Where:\n" +
         "   sourceImage - The name of the image in an Amazon S3 bucket (for example, people.png). \n\n" +
         "   bucketName - The name of the Amazon S3 bucket (for example, myBucket). \n\n";

     if (args.length != 2) {
          System.out.println(usage);
          System.exit(1);
     }

     String sourceImage = args[0];
     String bucketName = args[1];
     Region region = Region.US_WEST_2;
     S3Client s3 = S3Client.builder()
         .region(region)
         .credentialsProvider(ProfileCredentialsProvider.create("profile-name"))
         .build();

     RekognitionClient rekClient = RekognitionClient.builder()
         .region(region)
         .credentialsProvider(ProfileCredentialsProvider.create("profile-name"))
         .build();

     displayGear(s3, rekClient, sourceImage, bucketName) ;
     s3.close();
     rekClient.close();
     System.out.println("This example is done!");
 }

 // snippet-start:[rekognition.java2.detect_ppe.main]
 public static void displayGear(S3Client s3,
                                RekognitionClient rekClient,
                                String sourceImage,
                                String bucketName) {

     byte[] data = getObjectBytes (s3, bucketName, sourceImage);
     InputStream is = new ByteArrayInputStream(data);

     try {
         ProtectiveEquipmentSummarizationAttributes summarizationAttributes = ProtectiveEquipmentSummarizationAttributes.builder()
             .minConfidence(80F)
             .requiredEquipmentTypesWithStrings("FACE_COVER", "HAND_COVER", "HEAD_COVER")
             .build();

         SdkBytes sourceBytes = SdkBytes.fromInputStream(is);
         software.amazon.awssdk.services.rekognition.model.Image souImage = Image.builder()
             .bytes(sourceBytes)
             .build();

         DetectProtectiveEquipmentRequest request = DetectProtectiveEquipmentRequest.builder()
             .image(souImage)
             .summarizationAttributes(summarizationAttributes)
             .build();

         DetectProtectiveEquipmentResponse result = rekClient.detectProtectiveEquipment(request);
         List<ProtectiveEquipmentPerson> persons = result.persons();
         for (ProtectiveEquipmentPerson person: persons) {
             System.out.println("ID: " + person.id());
             List<ProtectiveEquipmentBodyPart> bodyParts=person.bodyParts();
             if (bodyParts.isEmpty()){
                 System.out.println("\tNo body parts detected");
             } else
                 for (ProtectiveEquipmentBodyPart bodyPart: bodyParts) {
                     System.out.println("\t" + bodyPart.name() + ". Confidence: " + bodyPart.confidence().toString());
                     List<EquipmentDetection> equipmentDetections=bodyPart.equipmentDetections();

                     if (equipmentDetections.isEmpty()){
                         System.out.println("\t\tNo PPE Detected on " + bodyPart.name());
                     } else {
                         for (EquipmentDetection item: equipmentDetections) {
                             System.out.println("\t\tItem: " + item.type() + ". Confidence: " + item.confidence().toString());
                             System.out.println("\t\tCovers body part: "
                                     + item.coversBodyPart().value().toString() + ". Confidence: " + item.coversBodyPart().confidence().toString());

                             System.out.println("\t\tBounding Box");
                             BoundingBox box =item.boundingBox();
                             System.out.println("\t\tLeft: " +box.left().toString());
                             System.out.println("\t\tTop: " + box.top().toString());
                             System.out.println("\t\tWidth: " + box.width().toString());
                             System.out.println("\t\tHeight: " + box.height().toString());
                             System.out.println("\t\tConfidence: " + item.confidence().toString());
                             System.out.println();
                         }
                     }
                 }
         }
         System.out.println("Person ID Summary\n-----------------");

         displaySummary("With required equipment", result.summary().personsWithRequiredEquipment());
         displaySummary("Without required equipment", result.summary().personsWithoutRequiredEquipment());
         displaySummary("Indeterminate", result.summary().personsIndeterminate());

     } catch (RekognitionException e) {
         e.printStackTrace();
         System.exit(1);
     }
 }

 public static byte[] getObjectBytes (S3Client s3, String bucketName, String keyName) {

     try {
         GetObjectRequest objectRequest = GetObjectRequest
             .builder()
             .key(keyName)
             .bucket(bucketName)
             .build();

         ResponseBytes<GetObjectResponse> objectBytes = s3.getObjectAsBytes(objectRequest);
         return objectBytes.asByteArray();

     } catch (S3Exception e) {
         System.err.println(e.awsErrorDetails().errorMessage());
         System.exit(1);
     }
     return null;
 }

 static void displaySummary(String summaryType,List<Integer> idList) {
     System.out.print(summaryType + "\n\tIDs  ");
     if (idList.size()==0) {
         System.out.println("None");
     } else {
         int count=0;
         for (Integer id: idList ) {
             if (count++ == idList.size()-1) {
                 System.out.println(id.toString());
             } else {
                 System.out.print(id.toString() + ", ");
             }
         }
     }
     System.out.println();
 }
 // snippet-end:[rekognition.java2.detect_ppe.main]
}

AWS CLI

Este AWS CLI comando solicita un resumen del PPE y muestra el resultado JSON de la operación detect-protective-equipment CLI.

Cambie bucketname por el nombre del bucket de Amazon S3 que contiene una imagen. Cambie el valor de input.jpg por el nombre de la imagen que desee usar.


aws rekognition detect-protective-equipment \
  --image "S3Object={Bucket=bucketname,Name=input.jpg}" \
  --summarization-attributes "MinConfidence=80,RequiredEquipmentTypes=['FACE_COVER','HAND_COVER','HEAD_COVER']"

Este AWS CLI comando muestra el resultado JSON de la operación detect-protective-equipment CLI.

Cambie bucketname por el nombre del bucket de Amazon S3 que contiene una imagen. Cambie el valor de input.jpg por el nombre de la imagen que desee usar.


aws rekognition detect-protective-equipment \
  --image "S3Object={Bucket=bucketname,Name=input.jpg}"

Python

En este ejemplo, se muestra información sobre los elementos de EPI detectados en las personas detectadas en una imagen.

Cambie el valor de bucket por el nombre del bucket de Amazon S3 que contiene su imagen. Cambie el valor de photo por el nombre de su archivo de imagen. Sustituya el valor de profile_name en la línea que crea la sesión de Rekognition por el nombre de su perfil de desarrollador.


# Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
# PDX-License-Identifier: MIT-0 (For details, see https://github.com/awsdocs/amazon-rekognition-developer-guide/blob/master/LICENSE-SAMPLECODE.)

import boto3

def detect_ppe(photo, bucket):

    session = boto3.Session(profile_name='profile-name')
    client = session.client('rekognition')

    response = client.detect_protective_equipment(Image={'S3Object': {'Bucket': bucket, 'Name': photo}},
                                                  SummarizationAttributes={'MinConfidence': 80,
                                                                           'RequiredEquipmentTypes': ['FACE_COVER',
                                                                                                      'HAND_COVER',
                                                                                                      'HEAD_COVER']})

    print('Detected PPE for people in image ' + photo)
    print('\nDetected people\n---------------')
    for person in response['Persons']:

        print('Person ID: ' + str(person['Id']))
        print('Body Parts\n----------')
        body_parts = person['BodyParts']
        if len(body_parts) == 0:
            print('No body parts found')
        else:
            for body_part in body_parts:
                print('\t' + body_part['Name'] + '\n\t\tConfidence: ' + str(body_part['Confidence']))
                print('\n\t\tDetected PPE\n\t\t------------')
                ppe_items = body_part['EquipmentDetections']
                if len(ppe_items) == 0:
                    print('\t\tNo PPE detected on ' + body_part['Name'])
                else:
                    for ppe_item in ppe_items:
                        print('\t\t' + ppe_item['Type'] + '\n\t\t\tConfidence: ' + str(ppe_item['Confidence']))
                        print('\t\tCovers body part: ' + str(
                            ppe_item['CoversBodyPart']['Value']) + '\n\t\t\tConfidence: ' + str(
                            ppe_item['CoversBodyPart']['Confidence']))
                        print('\t\tBounding Box:')
                        print('\t\t\tTop: ' + str(ppe_item['BoundingBox']['Top']))
                        print('\t\t\tLeft: ' + str(ppe_item['BoundingBox']['Left']))
                        print('\t\t\tWidth: ' + str(ppe_item['BoundingBox']['Width']))
                        print('\t\t\tHeight: ' + str(ppe_item['BoundingBox']['Height']))
                        print('\t\t\tConfidence: ' + str(ppe_item['Confidence']))
            print()
        print()

    print('Person ID Summary\n----------------')
    display_summary('With required equipment', response['Summary']['PersonsWithRequiredEquipment'])
    display_summary('Without required equipment', response['Summary']['PersonsWithoutRequiredEquipment'])
    display_summary('Indeterminate', response['Summary']['PersonsIndeterminate'])

    print()
    return len(response['Persons'])

# Display summary information for supplied summary.
def display_summary(summary_type, summary):
    print(summary_type + '\n\tIDs: ', end='')
    if (len(summary) == 0):
        print('None')
    else:
        for num, id in enumerate(summary, start=0):
            if num == len(summary) - 1:
                print(id)
            else:
                print(str(id) + ', ', end='')

def main():
    photo = 'photo-name'
    bucket = 'bucket-name'
    person_count = detect_ppe(photo, bucket)
    print("Persons detected: " + str(person_count))

if __name__ == "__main__":
    main()

Aviso JavaScript está desactivado o no está disponible en su navegador.

Para utilizar la documentación de AWS, debe estar habilitado JavaScript. Para obtener más información, consulte las páginas de ayuda de su navegador.

Convenciones del documento

Comprensión de la API de detección de EPI

Ejemplo: recuadros delimitadores y mascarillas