锦中人工智能助手

from flask import Flask, request, jsonify

import os

app = Flask(__name__)

UPLOAD_FOLDER = 'uploads'

app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER

if not os.path.exists(UPLOAD_FOLDER):

os.makedirs(UPLOAD_FOLDER)

@app.route('/upload', methods=['POST'])

def upload_video():

if 'file' not in request.files:

return jsonify({'error': 'No file part'}), 400

file = request.files['file']

if file.filename == '':

return jsonify({'error': 'No selected file'}), 400

file.save(os.path.join(app.config['UPLOAD_FOLDER'], file.filename))

return jsonify({'message': 'File uploaded successfully', 'filename': file.filename}), 200

if __name__ == '__main__':

app.run(debug=True)

import cv2

import numpy as np

import tensorflow as tf

# 加载预训练的人脸检测模型

face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')

# 加载图像分类模型（这里只是一个示例）

model = tf.keras.models.load_model('face_recognition_model.h5')

def analyze_video(video_path):

cap = cv2.VideoCapture(video_path)

frame_count = 0

face_count = 0

while True:

ret, frame = cap.read()

if not ret:

break

gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

faces = face_cascade.detectMultiScale(gray, 1.1, 4)

for (x, y, w, h) in faces:

face_img = frame[y:y+h, x:x+w]

face_img = cv2.resize(face_img, (128, 128)) / 255.0

face_img = np.expand_dims(face_img, axis=0)

prediction = model.predict(face_img)

if prediction[0][0] > 0.5: # 假设0.5为阈值

face_count += 1

frame_count += 1

cap.release()

return {'total_frames': frame_count, 'faces_detected': face_count}

# 示例调用

result = analyze_video('uploads/lecture.mp4')

print(result)