pip install opencv-python tensorflow keras

import cv2

def capture_video():
    cap = cv2.VideoCapture(0)  # 0 означает камеру по умолчанию

    while True:
        ret, frame = cap.read()
        if not ret:
            break

        cv2.imshow('Pet Monitor', frame)

        if cv2.waitKey(1) & 0xFF == ord('q'):
            break

    cap.release()
    cv2.destroyAllWindows()

# Тестирование функции захвата видео
capture_video()

import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense

def build_model():
    model = Sequential([
        Conv2D(32, (3, 3), activation='relu', input_shape=(64, 64, 3)),
        MaxPooling2D(pool_size=(2, 2)),
        Conv2D(64, (3, 3), activation='relu'),
        MaxPooling2D(pool_size=(2, 2)),
        Flatten(),
        Dense(128, activation='relu'),
        Dense(3, activation='softmax')  # Предположим, есть три поведения.
    ])

    model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
    return model

model = build_model()
model.summary()

from tensorflow.keras.preprocessing.image import ImageDataGenerator

# увеличение данных
train_datagen = ImageDataGenerator(rescale=1./255, shear_range=0.2, zoom_range=0.2, horizontal_flip=True)
train_generator = train_datagen.flow_from_directory('data/train', target_size=(64, 64), batch_size=32, class_mode='categorical')

# Модель обучения
model.fit(train_generator, epochs=10, steps_per_epoch=8000//32)
model.save('pet_behavior_model.h5')

import numpy as np
from tensorflow.keras.models import load_model

# Загрузить модель
model = load_model('pet_behavior_model.h5')

# картирование поведения
behavior_map = {0: «Поесть», 1: 'спать', 2: 'играть'}

def recognize_behavior(frame):
    img = cv2.resize(frame, (64, 64))
    img = np.expand_dims(img, axis=0)
    prediction = model.predict(img)
    behavior = behavior_map[np.argmax(prediction)]
    return behavior

def monitor_pet():
    cap = cv2.VideoCapture(0)

    while True:
        ret, frame = cap.read()
        if not ret:
            break

        behavior = recognize_behavior(frame)
        cv2.putText(frame, f'Behavior: {behavior}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2, cv2.LINE_AA)
        cv2.imshow('Pet Monitor', frame)

        if cv2.waitKey(1) & 0xFF == ord('q'):
            break

    cap.release()
    cv2.destroyAllWindows()

# Начать мониторинг домашних животных
monitor_pet()

import requests

def upload_frame(frame):
    _, img_encoded = cv2.imencode('.jpg', frame)
    response = requests.post('http://your-cloud-server/upload', data=img_encoded.tostring(), headers={'Content-Type': 'application/octet-stream'})
    return response.status_code

def monitor_pet_with_upload():
    cap = cv2.VideoCapture(0)

    while True:
        ret, frame = cap.read()
        if not ret:
            break

        behavior = recognize_behavior(frame)
        cv2.putText(frame, f'Behavior: {behavior}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2, cv2.LINE_AA)
        cv2.imshow('Pet Monitor', frame)

        # Загрузить видеокадры
        upload_frame(frame)

        if cv2.waitKey(1) & 0xFF == ord('q'):
            break

    cap.release()
    cv2.destroyAllWindows()

# Начните мониторинг домашних животных с помощью удаленного мониторинга
monitor_pet_with_upload()