import warnings
import threading  #导入多线程模块
import cv2
import mediapipe as mp
import numpy as np
from tensorflow.keras.models import load_model

# 禁用特定警告
warnings.filterwarnings("ignore", category=UserWarning, message='SymbolDatabase.GetPrototype() is deprecated')

# 初始化 MediaPipe 和 OpenCV
hands = None
mp_draw = mp.solutions.drawing_utils
cap = None
keep_running = False

# 加载手势识别模型
model_path = 'D:/hand/hand_gesture_model.h5'
model = load_model(model_path)

# 定义手势类别
gesture_classes = ['00', '01', '02', '03', '04', '05', '06', '07', '08', '09']

def start_recognition(callback=None):
    global keep_running, cap, hands
    if cap is None or not cap.isOpened():
        cap = cv2.VideoCapture(0)
    if hands is None:
        hands = mp.solutions.hands.Hands(static_image_mode=False, max_num_hands=2,
                                         model_complexity=1, min_detection_confidence=0.5,
                                         min_tracking_confidence=0.5)
    keep_running = True
    threading.Thread(target=run_recognition, args=(callback,)).start()

def run_recognition(callback=None):
    global keep_running
    last_gesture = None

    while keep_running and cap.isOpened():
        ret, img = cap.read()
        if not ret:
            break

        img = cv2.flip(img, 1)
        img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
        results = hands.process(img_rgb)

        total_raised_fingers = 0

        if results.multi_hand_landmarks:
            for handLms in results.multi_hand_landmarks:
                mp_draw.draw_landmarks(img, handLms, mp.solutions.hands.HAND_CONNECTIONS)
                _, raised_fingers = detect_gesture_and_fingers(handLms)
                total_raised_fingers += raised_fingers

        cv2.putText(img, f'Total Raised Fingers: {total_raised_fingers}', (10, 30),
                    cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 0), 2, cv2.LINE_AA,)

        img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
        if callback:
            callback(img)

    stop_recognition()
#停止识别
def stop_recognition():
    global keep_running, cap
    keep_running = False
    if cap is not None and cap.isOpened():
        cap.release()
        cap = None
    cv2.destroyAllWindows()



#释放摄像头资源
def release_camera():
    global cap
    if cap is not None and cap.isOpened():
        cap.release()
        cap = None

def detect_gesture_and_fingers(hand_landmarks):
    # 手势识别
    gesture_image = get_hand_image(hand_landmarks)
    gesture = predict_gesture(gesture_image)

    # 手指竖起数量检测
    raised_fingers = count_raised_fingers(hand_landmarks)

    return gesture, raised_fingers

def get_hand_image(hand_landmarks):
    # 提取手部区域图像
    # 示例实现，请根据你的需要进行调整
    img = np.zeros((150, 150, 3), dtype=np.uint8)  # 示例图像
    return img

def predict_gesture(img):
    img = cv2.resize(img, (150, 150))
    img_array = np.expand_dims(img, axis=0) / 255.0
    predictions = model.predict(img_array)
    predicted_class = gesture_classes[np.argmax(predictions)]
    return predicted_class

def count_raised_fingers(hand_landmarks):
    fingers_status = [0, 0, 0, 0, 0]

    # 拇指
    thumb_tip = hand_landmarks.landmark[mp.solutions.hands.HandLandmark.THUMB_TIP]
    thumb_ip = hand_landmarks.landmark[mp.solutions.hands.HandLandmark.THUMB_IP]
    thumb_mcp = hand_landmarks.landmark[mp.solutions.hands.HandLandmark.THUMB_MCP]
    thumb_cmc = hand_landmarks.landmark[mp.solutions.hands.HandLandmark.THUMB_CMC]

    # 计算拇指的角度
    angle_thumb = calculate_angle(thumb_cmc, thumb_mcp, thumb_tip)
    if angle_thumb > 160:  # 如果拇指的角度大于160度，认为拇指竖起
        fingers_status[0] = 1

    # 其他手指
    for i, finger_tip_id in enumerate([mp.solutions.hands.HandLandmark.INDEX_FINGER_TIP,
                                       mp.solutions.hands.HandLandmark.MIDDLE_FINGER_TIP,
                                       mp.solutions.hands.HandLandmark.RING_FINGER_TIP,
                                       mp.solutions.hands.HandLandmark.PINKY_TIP]):
        finger_tip = hand_landmarks.landmark[finger_tip_id]
        finger_pip = hand_landmarks.landmark[finger_tip_id - 2]
        finger_mcp = hand_landmarks.landmark[finger_tip_id - 3]

        # 计算手指的角度
        angle_finger = calculate_angle(finger_mcp, finger_pip, finger_tip)
        if angle_finger > 160:  # 如果手指的角度大于160度，认为手指竖起
            fingers_status[i + 1] = 1

    return sum(fingers_status)

def calculate_angle(point1, point2, point3):
    # 计算三个点之间的角度
    angle = np.arctan2(point3.y - point2.y, point3.x - point2.x) - np.arctan2(point1.y - point2.y, point1.x - point2.x)
    angle = np.abs(angle)
    if angle > np.pi:
        angle = 2 * np.pi - angle
    return angle * 180 / np.pi