'''from flask import Flask, render_template, request
import cv2
import numpy as np
import base64
import re

app = Flask(__name__)

@app.route('/')
def index():
    return render_template('index.html')

@app.route('/upload_frame', methods=['POST'])
def upload_frame():
    data = request.get_json()
    if 'image' not in data:
        return 'No image', 400

    image_data = re.sub('^data:image/.+;base64,', '', data['image'])
    img_bytes = base64.b64decode(image_data)
    np_img = np.frombuffer(img_bytes, dtype=np.uint8)
    frame = cv2.imdecode(np_img, cv2.IMREAD_COLOR)

    # Process frame here (e.g., face detection)
    print("Received a frame of shape:", frame.shape)

    return 'OK', 200

if __name__ == '__main__':
    app.run(host='0.0.0.0', port=5001, debug=True)'''
'''
import cv2
import numpy as np
import base64
from flask import Flask, request, jsonify, render_template
from ultralytics import YOLO

app = Flask(__name__)
model = YOLO('yolov8n.pt')  # Load the YOLO model

@app.route('/')
def index():
    return render_template('index.html')  # Your HTML file

@app.route('/upload_frame', methods=['POST'])
def upload_frame():
    data = request.get_json()
    image_data = data['image'].split(',')[1]
    img_bytes = base64.b64decode(image_data)
    np_arr = np.frombuffer(img_bytes, np.uint8)
    frame = cv2.imdecode(np_arr, cv2.IMREAD_COLOR)

    # Run YOLO detection
    results = model(frame)
    for result in results:
        for box in result.boxes:
            x1, y1, x2, y2 = map(int, box.xyxy[0])
            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)

    # (Optional) Save or return detections if needed
    return jsonify({"status": "success"})

if __name__ == '__main__':
    app.run(debug=True)
'''
'''import cv2
import numpy as np
import base64
from flask import Flask, request, jsonify, render_template
from ultralytics import YOLO

app = Flask(__name__)
model = YOLO('yolov8n.pt')

@app.route('/')
def index():
    return render_template('index.html')

@app.route('/upload_frame', methods=['POST'])
def upload_frame():
    data = request.get_json()
    image_data = data['image'].split(',')[1]
    img_bytes = base64.b64decode(image_data)
    np_arr = np.frombuffer(img_bytes, np.uint8)
    frame = cv2.imdecode(np_arr, cv2.IMREAD_COLOR)

    # Run YOLO detection
    results = model(frame)
    for result in results:
        for box in result.boxes:
            x1, y1, x2, y2 = map(int, box.xyxy[0])
            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)

    # Encode the frame back to JPEG
    _, buffer = cv2.imencode('.jpg', frame)
    annotated_base64 = base64.b64encode(buffer).decode('utf-8')
    return jsonify({"status": "success", "image": f"data:image/jpeg;base64,{annotated_base64}"})

if __name__ == '__main__':
    app.run(host="0.0.0.0", port=5001, debug=True)'''
'''import cv2
import numpy as np
import base64
from flask import Flask, request, jsonify, render_template
from ultralytics import YOLO

app = Flask(__name__)

# Load YOLOv8 model (e.g., yolov8n.pt, yolov8s.pt, etc.)
model = YOLO('yolov8n.pt')

@app.route('/')
def index():
    return render_template('index.html')

@app.route('/upload_frame', methods=['POST'])
def upload_frame():
    data = request.get_json()
    if 'image' not in data:
        return jsonify({'error': 'No image provided'}), 400

    # Decode base64 image
    image_data = data['image'].split(',')[1]
    img_bytes = base64.b64decode(image_data)
    np_arr = np.frombuffer(img_bytes, np.uint8)
    frame = cv2.imdecode(np_arr, cv2.IMREAD_COLOR)

    # Run YOLO detection
    results = model(frame)

    for result in results:
        for box in result.boxes:
            x1, y1, x2, y2 = map(int, box.xyxy[0])         # Coordinates
            class_id = int(box.cls[0])                     # Class ID
            class_name = model.names[class_id]             # Class name

            # Draw bounding box
            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)

            # Put class name text
            cv2.putText(
                frame,
                class_name,
                (x1, y1 - 10),
                cv2.FONT_HERSHEY_SIMPLEX,
                0.6,
                (0, 255, 0),
                2
            )

    # Encode annotated image back to base64
    _, buffer = cv2.imencode('.jpg', frame)
    annotated_base64 = base64.b64encode(buffer).decode('utf-8')

    return jsonify({
        "status": "success",
        "image": f"data:image/jpeg;base64,{annotated_base64}"
    })

if __name__ == '__main__':
    app.run(host='0.0.0.0', port=5001, debug=True)'''

'''import cv2
import numpy as np
import base64
from flask import Flask, request, jsonify, render_template
from ultralytics import YOLO

app = Flask(__name__)
model = YOLO('yolov8n.pt')  # Load YOLOv8 model
CONFIDENCE_THRESHOLD = 0.8  # Set confidence threshold (0.0 to 1.0)

@app.route('/')
def index():
    return render_template('index.html')

@app.route('/upload_frame', methods=['POST'])
def upload_frame():
    data = request.get_json()
    if 'image' not in data:
        return jsonify({'error': 'No image provided'}), 400

    # Decode base64 image
    image_data = data['image'].split(',')[1]
    img_bytes = base64.b64decode(image_data)
    np_arr = np.frombuffer(img_bytes, np.uint8)
    frame = cv2.imdecode(np_arr, cv2.IMREAD_COLOR)

    # Run YOLO detection
    results = model(frame)

    for result in results:
        for box in result.boxes:
            if box.conf[0] < CONFIDENCE_THRESHOLD:
                continue

            x1, y1, x2, y2 = map(int, box.xyxy[0])
            class_id = int(box.cls[0])
            class_name = model.names[class_id]
            confidence = float(box.conf[0])

            # Draw bounding box
            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)

            # Draw class name + confidence
            label = f"{class_name} {confidence:.2f}"
            cv2.putText(frame, label, (x1, y1 - 10),
                        cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2)

    # Encode the frame back to base64
    _, buffer = cv2.imencode('.jpg', frame)
    annotated_base64 = base64.b64encode(buffer).decode('utf-8')

    return jsonify({
        "status": "success",
        "image": f"data:image/jpeg;base64,{annotated_base64}"
    })

if __name__ == '__main__':
    app.run(host='0.0.0.0', port=5001, debug=True)
'''
import cv2
import numpy as np
import base64
from flask import Flask, request, jsonify, render_template
from ultralytics import YOLO

app = Flask(__name__)
model = YOLO('yolov8n.pt')  # Replace with your desired YOLO model
CONFIDENCE_THRESHOLD = 0.5

@app.route('/')
def index():
    return render_template('index.html')

@app.route('/upload_frame', methods=['POST'])
def upload_frame():
    data = request.get_json()
    if 'image' not in data:
        return jsonify({'error': 'No image provided'}), 400

    # Decode base64 image
    image_data = data['image'].split(',')[1]
    img_bytes = base64.b64decode(image_data)
    np_arr = np.frombuffer(img_bytes, np.uint8)
    frame = cv2.imdecode(np_arr, cv2.IMREAD_COLOR)

    # Run YOLO detection
    results = model(frame)

    for result in results:
        for box in result.boxes:
            if box.conf[0] < CONFIDENCE_THRESHOLD:
                continue

            x1, y1, x2, y2 = map(int, box.xyxy[0])
            class_id = int(box.cls[0])
            class_name = model.names[class_id]
            confidence = float(box.conf[0])

            # Draw bounding box
            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)

            # Draw class name + confidence
            label = f"{class_name} {confidence:.2f}"
            cv2.putText(frame, label, (x1, y1 - 10),
                        cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2)

    # Encode the frame back to base64
    _, buffer = cv2.imencode('.jpg', frame)
    annotated_base64 = base64.b64encode(buffer).decode('utf-8')

    return jsonify({
        "status": "success",
        "image": f"data:image/jpeg;base64,{annotated_base64}"
    })

if __name__ == '__main__':
    app.run(host='0.0.0.0', port=5001, debug=True)