Блог

Я пытаюсь перенести свой код для работы на удаленном сервере (AWS). прямо сейчас у меня есть приложение flask на локальном компьютере, которое запускает скрипт для получения изображения с камеры и анализа его с помощью распознавания лиц, а также для рисования рамки вокруг лица людей и возврата изображения обратно. это происходит непрерывно. итак, я пытаюсь привести пример из https://github.com/dxue2012/python-webcam-flask но он делает это по-другому, сначала запрашивая пользователя через веб-клиент и отправляя на сервер, то, что я хочу сделать, немного отличается, просто отправив изображение вместо этого, не запрашивая через веб-клиент

это мой код flask

 from flask import Flask, render_template, Response, request
from camera import VideoCamera
import time
import os

app = Flask(__name__)
#app = Flask(__name__, template_folder='/var/www/html/templates')

#background process happening without any refreshing


@app.route('/', methods=['GET', 'POST'])
def move():
    result = ""
    if request.method == 'POST':
        
        return render_template('index.html', res_str=result)
                        
    return render_template('index.html')


def gen(camera):
    while True:
        frame = camera.get_frame()
        yield (b'--framern'
               b'Content-Type: image/jpegrnrn'   frame   b'rnrn')

@app.route('/video_feed')
def video_feed():
    return Response(gen(VideoCamera()),
                    mimetype='multipart/x-mixed-replace; boundary=frame')

if __name__ == '__main__':
    app.run(host='192.168.1.15', debug=True, threaded=True)
 

и это camera.py где я получаю снимок с моей камеры и делаю некоторое распознавание лиц.

 #Date: 27.06.20
#Desc: This scrtipt is running a face recongition of a live webcam stream. This is a modifed
#code of the orginal Ageitgey (GitHub) face recognition demo to include multiple faces.
#Simply add the your desired 'passport-style' face to the 'profiles' folder.

import face_recognition
import cv2
import numpy as np
import os
face_cascade=cv2.CascadeClassifier("haarcascade_frontalface_alt2.xml")
ds_factor=0.6

#Store objects in array
known_person=[] #Name of person string
known_image=[] #Image object
known_face_encodings=[] #Encoding object

# Initialize some variables
face_locations = []
face_encodings = []
face_names = []
process_this_frame = True

#Loop to add images in friends folder
for file in os.listdir("profiles"):
    try:
        #Extracting person name from the image filename eg: david.jpg
        known_person.append(file.replace(".jpg", ""))
        file=os.path.join("profiles/", file)
        known_image = face_recognition.load_image_file(file)
        #print("test")
        #print(face_recognition.face_encodings(known_image)[0])
        known_face_encodings.append(face_recognition.face_encodings(known_image)[0])
        #print(known_face_encodings)

    except Exception as e:
        pass
    
#print(len(known_face_encodings))
#print(known_person)


class VideoCamera(object):

    def __init__(self):
        self.video = cv2.VideoCapture(0)
    
    def __del__(self):
        self.video.release()
    
    def get_frame(self):
        success, image = self.video.read()
        process_this_frame = True
        
            # Resize frame of video to 1/4 size for faster face recognition processing
        small_frame = cv2.resize(image, (0, 0), fx=0.25, fy=0.25)

        # Convert the image from BGR color (which OpenCV uses) to RGB color (which face_recognition uses)
        rgb_small_frame = small_frame[:, :, ::-1]
        
       # Only process every other frame of video to save time
        if process_this_frame:
            # Find all the faces and face encodings in the current frame of video
            face_locations = face_recognition.face_locations(rgb_small_frame)
            face_encodings = face_recognition.face_encodings(rgb_small_frame, face_locations)

            global name_gui;
            #face_names = []
            for face_encoding in face_encodings:
                # See if the face is a match for the known face(s)
                matches = face_recognition.compare_faces(known_face_encodings, face_encoding)
                name = "Unknown"
                
                #print(face_encoding)
                print(matches)

                face_distances = face_recognition.face_distance(known_face_encodings, face_encoding)
                best_match_index = np.argmin(face_distances)
                if matches[best_match_index]:
                    name = known_person[best_match_index]

                print(name)
                #print(face_locations)
                face_names.append(name)
        
                name_gui = name

        process_this_frame = not process_this_frame
            
# Display the results
        for (top, right, bottom, left), name in zip(face_locations, face_names):
            # Scale back up face locations since the frame we detected in was scaled to 1/4 size
            top *= 4
            right *= 4
            bottom *= 4
            left *= 4

            # Draw a box around the face
            cv2.rectangle(image, (left, top), (right, bottom), (255, 255, 255), 2)

            # Draw a label with a name below the face
            cv2.rectangle(image, (left, bottom - 35), (right, bottom), (255, 255, 255), cv2.FILLED)
            font = cv2.FONT_HERSHEY_DUPLEX
            cv2.putText(image, name_gui, (left   10, bottom - 10), font, 1.0, (0, 0, 0), 1)

        
        ret, jpeg = cv2.imencode('.jpg', image)
        return jpeg.tobytes()