fix_bugs_in_screenshot_pro

.vscode/settings.json

@@ -0,0 +1,5 @@
+{
+    "python-envs.defaultEnvManager": "ms-python.python:conda",
+    "python-envs.defaultPackageManager": "ms-python.python:conda",
+    "python-envs.pythonProjects": []
+}

utils/GUI.py

@@ -9,33 +9,44 @@ current_mode = None
 current_cap = None
 # 用于追踪当前模式和摄像头资源
 
+# 初始化图形界面主要的逻辑
 def create_gui():
-    root = tk.Tk()
-    root.title("Gesture Recognition")
-    root.geometry("800x600")
-
-    canvas = tk.Canvas(root, width=640, height=480)
-    canvas.pack()
-    # 创建显示视频内容的画布
-
-    camera_button = tk.Button(
-        root,
-        text="Use Camera for Real-time Recognition",
-        command=lambda: switch_to_camera(canvas)
-    )
-    camera_button.pack(pady=10)
-    # 启动摄像头实时识别的按钮
-
-    video_button = tk.Button(
-        root,
-        text="Upload Video File for Processing",
-        command=lambda: select_and_process_video(canvas, root)
-    )
-    video_button.pack(pady=10)
-    # 上传并处理视频文件的按钮
-
-    root.mainloop()
-
+    try:
+        print("开始创建GUI界面")
+        root = tk.Tk()
+        root.title("Gesture Recognition")
+        root.geometry("800x600")
+        print("GUI窗口创建成功")
+
+        canvas = tk.Canvas(root, width=640, height=480)
+        canvas.pack()
+        print("画布创建成功")
+
+        camera_button = tk.Button(
+            root,
+            text="Use Camera for Real-time Recognition",
+            command=lambda: switch_to_camera(canvas)
+        )
+        camera_button.pack(pady=10)
+        print("摄像头按钮创建成功")
+
+        video_button = tk.Button(
+            root,
+            text="Upload Video File for Processing",
+            command=lambda: select_and_process_video(canvas, root)
+        )
+        video_button.pack(pady=10)
+        print("视频上传按钮创建成功")
+
+        print("GUI界面创建完成，进入主循环")
+        root.mainloop()
+        
+    except Exception as e:
+        print(f"[ERROR] 创建GUI时发生异常: {str(e)}")
+        import traceback
+        print(traceback.format_exc())
+
+# 切换到摄像头实时识别模式
 def switch_to_camera(canvas):
     global current_mode, current_cap
 
@@ -46,18 +57,18 @@ def switch_to_camera(canvas):
     canvas.delete("all")
     # 设置当前模式为摄像头并清空Canvas
 
-
-    current_cap = cv2.VideoCapture(0)
+    current_cap = cv2.VideoCapture(1)
+    current_cap.open(0)
     if not current_cap.isOpened():
         messagebox.showerror("Error", "Cannot open camera")
         current_mode = None
         return
     # 启动摄像头
 
-
     start_camera(canvas, current_cap)
     # 传入canvas和current_cap
 
+# 切换到视频流处理模式
 def select_and_process_video(canvas, root):
     global current_mode, current_cap
 
@@ -108,5 +119,9 @@ def start_camera(canvas, cap):
     show_frame(canvas, cap, gesture_processor)
     # 启动摄像头进行实时手势识别
 
+
+
+
+
 if __name__ == "__main__":
     create_gui()

utils/gesture_recognition.ipynb

@@ -2,14 +2,16 @@
  "cells": [
   {
    "cell_type": "code",
+   "execution_count": 1,
    "id": "initial_id",
    "metadata": {
-    "collapsed": true,
     "ExecuteTime": {
      "end_time": "2024-09-07T05:11:28.761076Z",
      "start_time": "2024-09-07T05:11:22.404354Z"
-    }
+    },
+    "collapsed": true
    },
+   "outputs": [],
    "source": [
     "import cv2\n",
     "import time\n",
@@ -17,18 +19,19 @@
     "import numpy as np\n",
     "from collections import deque\n",
     "from filterpy.kalman import KalmanFilter"
-   ],
-   "outputs": [],
-   "execution_count": 1
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "40aada17ccd31fe",
    "metadata": {
     "ExecuteTime": {
      "end_time": "2024-09-07T05:11:28.777139Z",
      "start_time": "2024-09-07T05:11:28.761076Z"
     }
    },
-   "cell_type": "code",
+   "outputs": [],
    "source": [
     "gesture_locked = {'Left':False,'Right':False}\n",
     "gesture_start_time = {'Left':0,'Right':0}\n",
@@ -48,19 +51,19 @@
     "rect_draw_time = {'Left':0,'Right':0}\n",
     "last_drawn_box = {'Left':None,'Right':None}\n",
     "elapsed_time = {'Left':0,'Right':0}"
-   ],
-   "id": "40aada17ccd31fe",
-   "outputs": [],
-   "execution_count": 2
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "2ee9323bb1c25cc0",
    "metadata": {
     "ExecuteTime": {
      "end_time": "2024-09-07T05:11:28.824573Z",
      "start_time": "2024-09-07T05:11:28.777139Z"
     }
    },
-   "cell_type": "code",
+   "outputs": [],
    "source": [
     "def clear_hand_states(detected_hand ='Both'):\n",
     "    global gesture_locked, gesture_start_time, buffer_start_time, dragging, drag_point, buffer_duration,is_index_finger_up, trajectory,wait_time,kalman_wait_time, start_drag_time, rect_draw_time, last_drawn_box, wait_box, elapsed_time\n",
@@ -86,19 +89,19 @@
     "        last_drawn_box[h] = None\n",
     "        elapsed_time[h] = 0\n",
     "        # 清空没被检测的手"
-   ],
-   "id": "2ee9323bb1c25cc0",
-   "outputs": [],
-   "execution_count": 3
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "96cf431d2562e7d",
    "metadata": {
     "ExecuteTime": {
      "end_time": "2024-09-07T05:11:28.855831Z",
      "start_time": "2024-09-07T05:11:28.824573Z"
     }
    },
-   "cell_type": "code",
+   "outputs": [],
    "source": [
     "kalman_filters = {\n",
     "    'Left': KalmanFilter(dim_x=4, dim_z=2),\n",
@@ -127,19 +130,19 @@
     "    kf.x = np.array([x, y, 0., 0.])\n",
     "    kf.P *= 1000.\n",
     "    # 重置"
-   ],
-   "id": "96cf431d2562e7d",
-   "outputs": [],
-   "execution_count": 4
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "edc274b7ed495122",
    "metadata": {
     "ExecuteTime": {
      "end_time": "2024-09-07T05:11:28.887346Z",
      "start_time": "2024-09-07T05:11:28.855831Z"
     }
    },
-   "cell_type": "code",
+   "outputs": [],
    "source": [
     "\n",
     "mp_hands = mediapipe.solutions.hands\n",
@@ -154,19 +157,19 @@
     "\n",
     "mp_drawing = mediapipe.solutions.drawing_utils\n",
     "clear_hand_states()"
-   ],
-   "id": "edc274b7ed495122",
-   "outputs": [],
-   "execution_count": 5
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "51ff809ecaf1f899",
    "metadata": {
     "ExecuteTime": {
      "end_time": "2024-09-07T05:11:28.934274Z",
      "start_time": "2024-09-07T05:11:28.887346Z"
     }
    },
-   "cell_type": "code",
+   "outputs": [],
    "source": [
     "def process_image(image):\n",
     "\n",
@@ -256,7 +259,7 @@
     "                    contour = np.array(trajectory[temp_handness], dtype=np.int32)\n",
     "                    rect = cv2.minAreaRect(contour)\n",
     "                    box = cv2.boxPoints(rect)\n",
-    "                    box = np.int0(box)\n",
+    "                    box = np.int64(box)\n",
     "                    rect_draw_time[temp_handness] = time.time()\n",
     "                    last_drawn_box[temp_handness] = box\n",
     "                    # 如果指向操作结束 轨迹列表有至少四个点的时候\n",
@@ -334,19 +337,53 @@
     "        # 如果没检测到手就清空全部信息\n",
     "    \n",
     "    return image"
-   ],
-   "id": "51ff809ecaf1f899",
-   "outputs": [],
-   "execution_count": 6
+   ]
   },
   {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b7ce23e80ed36041",
    "metadata": {
     "ExecuteTime": {
      "end_time": "2024-09-07T05:19:32.248575Z",
      "start_time": "2024-09-07T05:11:28.934663Z"
     }
    },
-   "cell_type": "code",
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\25055\\AppData\\Local\\Temp\\ipykernel_4200\\752492595.py:89: DeprecationWarning: `np.int0` is a deprecated alias for `np.intp`.  (Deprecated NumPy 1.24)\n",
+      "  box = np.int0(box)\n"
+     ]
+    },
+    {
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[7], line 10\u001b[0m\n\u001b[0;32m      7\u001b[0m     \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCamera Error\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m      8\u001b[0m     \u001b[38;5;28;01mbreak\u001b[39;00m\n\u001b[1;32m---> 10\u001b[0m frame \u001b[38;5;241m=\u001b[39m \u001b[43mprocess_image\u001b[49m\u001b[43m(\u001b[49m\u001b[43mframe\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     11\u001b[0m cv2\u001b[38;5;241m.\u001b[39mimshow(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mVideo\u001b[39m\u001b[38;5;124m'\u001b[39m, frame)\n\u001b[0;32m     13\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m cv2\u001b[38;5;241m.\u001b[39mwaitKey(\u001b[38;5;241m1\u001b[39m) \u001b[38;5;241m&\u001b[39m \u001b[38;5;241m0xFF\u001b[39m \u001b[38;5;241m==\u001b[39m \u001b[38;5;28mord\u001b[39m(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mq\u001b[39m\u001b[38;5;124m'\u001b[39m):\n",
+      "Cell \u001b[1;32mIn[6], line 9\u001b[0m, in \u001b[0;36mprocess_image\u001b[1;34m(image)\u001b[0m\n\u001b[0;32m      6\u001b[0m image \u001b[38;5;241m=\u001b[39m cv2\u001b[38;5;241m.\u001b[39mcvtColor(image, cv2\u001b[38;5;241m.\u001b[39mCOLOR_BGR2RGB)\n\u001b[0;32m      7\u001b[0m \u001b[38;5;66;03m# 预处理帧\u001b[39;00m\n\u001b[1;32m----> 9\u001b[0m results \u001b[38;5;241m=\u001b[39m \u001b[43mhands\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mprocess\u001b[49m\u001b[43m(\u001b[49m\u001b[43mimage\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     11\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m results\u001b[38;5;241m.\u001b[39mmulti_hand_landmarks:\n\u001b[0;32m     12\u001b[0m     \u001b[38;5;66;03m# 如果检测到手\u001b[39;00m\n\u001b[0;32m     14\u001b[0m     handness_str \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m'\u001b[39m\n",
+      "File \u001b[1;32md:\\app-install-dict\\Anaconda3\\envs\\software_engineering\\lib\\site-packages\\mediapipe\\python\\solutions\\hands.py:153\u001b[0m, in \u001b[0;36mHands.process\u001b[1;34m(self, image)\u001b[0m\n\u001b[0;32m    132\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21mprocess\u001b[39m(\u001b[38;5;28mself\u001b[39m, image: np\u001b[38;5;241m.\u001b[39mndarray) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m NamedTuple:\n\u001b[0;32m    133\u001b[0m \u001b[38;5;250m  \u001b[39m\u001b[38;5;124;03m\"\"\"Processes an RGB image and returns the hand landmarks and handedness of each detected hand.\u001b[39;00m\n\u001b[0;32m    134\u001b[0m \n\u001b[0;32m    135\u001b[0m \u001b[38;5;124;03m  Args:\u001b[39;00m\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    150\u001b[0m \u001b[38;5;124;03m         right hand) of the detected hand.\u001b[39;00m\n\u001b[0;32m    151\u001b[0m \u001b[38;5;124;03m  \"\"\"\u001b[39;00m\n\u001b[1;32m--> 153\u001b[0m   \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mprocess\u001b[49m\u001b[43m(\u001b[49m\u001b[43minput_data\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m{\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mimage\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mimage\u001b[49m\u001b[43m}\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32md:\\app-install-dict\\Anaconda3\\envs\\software_engineering\\lib\\site-packages\\mediapipe\\python\\solution_base.py:335\u001b[0m, in \u001b[0;36mSolutionBase.process\u001b[1;34m(self, input_data)\u001b[0m\n\u001b[0;32m    329\u001b[0m   \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m    330\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_graph\u001b[38;5;241m.\u001b[39madd_packet_to_input_stream(\n\u001b[0;32m    331\u001b[0m         stream\u001b[38;5;241m=\u001b[39mstream_name,\n\u001b[0;32m    332\u001b[0m         packet\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_make_packet(input_stream_type,\n\u001b[0;32m    333\u001b[0m                                  data)\u001b[38;5;241m.\u001b[39mat(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_simulated_timestamp))\n\u001b[1;32m--> 335\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_graph\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mwait_until_idle\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    336\u001b[0m \u001b[38;5;66;03m# Create a NamedTuple object where the field names are mapping to the graph\u001b[39;00m\n\u001b[0;32m    337\u001b[0m \u001b[38;5;66;03m# output stream names.\u001b[39;00m\n\u001b[0;32m    338\u001b[0m solution_outputs \u001b[38;5;241m=\u001b[39m collections\u001b[38;5;241m.\u001b[39mnamedtuple(\n\u001b[0;32m    339\u001b[0m     \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mSolutionOutputs\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_output_stream_type_info\u001b[38;5;241m.\u001b[39mkeys())\n",
+      "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
+     ]
+    },
+    {
+     "ename": "",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m在当前单元格或上一个单元格中执行代码时 Kernel 崩溃。\n",
+      "\u001b[1;31m请查看单元格中的代码，以确定故障的可能原因。\n",
+      "\u001b[1;31m单击<a href='https://aka.ms/vscodeJupyterKernelCrash'>此处</a>了解详细信息。\n",
+      "\u001b[1;31m有关更多详细信息，请查看 Jupyter <a href='command:jupyter.viewOutput'>log</a>。"
+     ]
+    }
+   ],
    "source": [
     "cap = cv2.VideoCapture(1)\n",
     "cap.open(0)\n",
@@ -365,37 +402,34 @@
     "        \n",
     "cap.release()\n",
     "cv2.destroyAllWindows()  "
-   ],
-   "id": "b7ce23e80ed36041",
-   "outputs": [],
-   "execution_count": 7
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
-   "outputs": [],
    "execution_count": null,
-   "source": "",
-   "id": "10fca4bc34a944ea"
+   "id": "10fca4bc34a944ea",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "software_engineering",
    "language": "python",
    "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
-    "version": 2
+    "version": 3
    },
    "file_extension": ".py",
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython2",
-   "version": "2.7.6"
+   "pygments_lexer": "ipython3",
+   "version": "3.8.20"
   }
  },
  "nbformat": 4,

utils/hand_gesture.py

@@ -3,7 +3,7 @@ from model import HandTracker
 from index_finger import IndexFingerHandler
 from gesture_data import HandState
 from kalman_filter import KalmanHandler
-from utils.finger_drawer import FingerDrawer
+from finger_drawer import FingerDrawer
 
 class HandGestureHandler:
     def __init__(self):

utils/index_finger.py

@@ -78,7 +78,7 @@ class IndexFingerHandler:
                 contour = np.array(self.hand_state.trajectory[temp_handness], dtype=np.int32)
                 rect = cv2.minAreaRect(contour)
                 box = cv2.boxPoints(rect)
-                box = np.int0(box)
+                box = np.int64(box)
                 # 当拖拽点数大于4时则计算最小外接矩形
                 self.hand_state.rect_draw_time[temp_handness] = time.time()
                 self.hand_state.last_drawn_box[temp_handness] = box

utils/main.py

@@ -1,278 +0,0 @@
-import cv2
-import time
-import mediapipe
-import numpy as np
-from collections import deque
-from filterpy.kalman import KalmanFilter
-
-gesture_locked = {'Left':False,'Right':False}
-gesture_start_time = {'Left':0,'Right':0}
-buffer_start_time = {'Left':0,'Right':0}
-start_drag_time = {'Left':0,'Right':0}
-dragging = {'Left':False,'Right':False}
-drag_point = {'Left':(0, 0),'Right':(0, 0)}
-buffer_duration = {'Left':0.25,'Right':0.25}
-is_index_finger_up = {'Left':False,'Right':False}
-index_finger_second = {'Left':0,'Right':0}
-index_finger_tip = {'Left':0,'Right':0}
-trajectory = {'Left':[],'Right':[]}
-square_queue = deque()
-wait_time = 1.5
-kalman_wait_time = 0.5
-wait_box = 2
-rect_draw_time = {'Left':0,'Right':0}
-last_drawn_box = {'Left':None,'Right':None}
-elapsed_time = {'Left':0,'Right':0}
-
-def clear_hand_states(detected_hand ='Both'):
-    global gesture_locked, gesture_start_time, buffer_start_time, dragging, drag_point, buffer_duration,is_index_finger_up, trajectory,wait_time,kalman_wait_time, start_drag_time, rect_draw_time, last_drawn_box, wait_box, elapsed_time
-    
-    hands_to_clear = {'Left', 'Right'}
-    if detected_hand == 'Both':
-        hands_to_clear = hands_to_clear
-    else:
-        hands_to_clear -= {detected_hand}
-        # 反向判断左右手
-
-    for h in hands_to_clear:
-        gesture_locked[h] = False
-        gesture_start_time[h] = 0
-        buffer_start_time[h] = 0
-        dragging[h] = False
-        drag_point[h] = (0, 0)
-        buffer_duration[h] = 0.25
-        is_index_finger_up[h] = False
-        trajectory[h].clear()
-        start_drag_time[h] = 0
-        rect_draw_time[h] = 0
-        last_drawn_box[h] = None
-        elapsed_time[h] = 0
-        # 清空没被检测的手
-
-kalman_filters = {
-    'Left': KalmanFilter(dim_x=4, dim_z=2),
-    'Right': KalmanFilter(dim_x=4, dim_z=2)
-}
-
-for key in kalman_filters:
-    kalman_filters[key].x = np.array([0., 0., 0., 0.])
-    kalman_filters[key].F = np.array([[1, 0, 1, 0], [0, 1, 0, 1], [0, 0, 1, 0], [0, 0, 0, 1]])
-    # 状态转移矩阵
-    kalman_filters[key].H = np.array([[1, 0, 0, 0], [0, 1, 0, 0]])
-    # 观测矩阵
-    kalman_filters[key].P *= 1000.
-    kalman_filters[key].R = 3
-    kalman_filters[key].Q = np.eye(4) * 0.01
-
-def kalman_filter_point(hand_label, x, y):
-    kf = kalman_filters[hand_label]
-    kf.predict()
-    kf.update([x, y])
-    # 更新状态
-    return (kf.x[0], kf.x[1])
-
-def reset_kalman_filter(hand_label, x, y):
-    kf = kalman_filters[hand_label]
-    kf.x = np.array([x, y, 0., 0.])
-    kf.P *= 1000.
-    # 重置
-
-mp_hands = mediapipe.solutions.hands
-
-hands = mp_hands.Hands(
-    static_image_mode=False,
-    max_num_hands=2,
-    # 一只更稳定
-    min_detection_confidence=0.5,
-    min_tracking_confidence=0.5
-)
-
-mp_drawing = mediapipe.solutions.drawing_utils
-clear_hand_states()    
-
-def process_image(image):
-
-    start_time = time.time()
-    height, width = image.shape[:2]
-    image = cv2.flip(image, 1)
-    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
-    # 预处理帧
-    
-    results = hands.process(image)
-    
-    if results.multi_hand_landmarks:
-        # 如果检测到手
-        
-        handness_str = ''
-        index_finger_tip_str = ''
-        
-        if len(results.multi_hand_landmarks) == 1:
-            clear_hand_states(detected_hand = results.multi_handedness[0].classification[0].label)
-            # 如果只有一只手 则清空另一只手的数据 避免后续冲突导致不稳定
-        
-        for hand_idx in range(len(results.multi_hand_landmarks)):
-            
-            hand_21 = results.multi_hand_landmarks[hand_idx]
-            mp_drawing.draw_landmarks(image, hand_21, mp_hands.HAND_CONNECTIONS)
-            
-            temp_handness = results.multi_handedness[hand_idx].classification[0].label
-            handness_str += '{}:{}, '.format(hand_idx, temp_handness)
-            is_index_finger_up[temp_handness] = False
-            # 先设置为false 防止放下被错误更新为竖起
-            
-            cz0 = hand_21.landmark[0].z
-            index_finger_second[temp_handness] = hand_21.landmark[7]
-            index_finger_tip[temp_handness] = hand_21.landmark[8]
-            # 食指指尖和第一个关节
-            
-            index_x, index_y = int(index_finger_tip[temp_handness].x * width), int(index_finger_tip[temp_handness].y * height)
-
-            if all(index_finger_second[temp_handness].y < hand_21.landmark[i].y for i in range(21) if i not in [7, 8]) and index_finger_tip[temp_handness].y < index_finger_second[temp_handness].y:
-                is_index_finger_up[temp_handness] = True
-                # 如果指尖和第二个关节高度大于整只手所有关节点 则视为执行“指向”操作 
-
-            if is_index_finger_up[temp_handness]:
-                if not gesture_locked[temp_handness]:
-                    if gesture_start_time[temp_handness] == 0:
-                        gesture_start_time[temp_handness] = time.time()
-                        # 记录食指抬起的时间
-                    elif time.time() - gesture_start_time[temp_handness] > wait_time:
-                        dragging[temp_handness] = True
-                        gesture_locked[temp_handness] = True
-                        drag_point[temp_handness] = (index_x, index_y)
-                        # 如果食指抬起的时间大于预设的等待时间则视为执行“指向”操作
-                    buffer_start_time[temp_handness] = 0
-                    # 检测到食指竖起就刷新缓冲时间
-            else:
-                if buffer_start_time[temp_handness] == 0:
-                    buffer_start_time[temp_handness] = time.time()
-                elif time.time() - buffer_start_time[temp_handness] > buffer_duration[temp_handness]:
-                    gesture_start_time[temp_handness] = 0
-                    gesture_locked[temp_handness] = False
-                    dragging[temp_handness] = False
-                    # 如果缓冲时间大于设定 就证明已经结束指向操作
-                    # 这样可以防止某一帧识别有误导致指向操作被错误清除
-                    
-            if dragging[temp_handness]:
-
-                if start_drag_time[temp_handness] == 0:
-                    start_drag_time[temp_handness] = time.time()
-                    reset_kalman_filter(temp_handness, index_x, index_y)
-                    # 每次画线的时候初始化滤波器
-                    
-                smooth_x, smooth_y = kalman_filter_point(temp_handness, index_x, index_y)
-                drag_point[temp_handness] = (index_x, index_y)
-                index_finger_radius = max(int(10 * (1 + (cz0 - index_finger_tip[temp_handness].z) * 5)), 0)
-                cv2.circle(image, drag_point[temp_handness], index_finger_radius, (0, 0, 255), -1)
-                # 根据离掌根的深度距离来构建一个圆
-                # 用来显示已经开始指向操作
-                # 和下方构建的深度点位对应 直接用倍数
-                drag_point_smooth = (smooth_x, smooth_y)
-                
-                if time.time() - start_drag_time[temp_handness] > kalman_wait_time:
-                    trajectory[temp_handness].append(drag_point_smooth)
-                    # 因为kalman滤波器初始化的时候会很不稳定 前几帧通常会有较为严重的噪声
-                    # 所以直接等待前几帧运行完成之后再将点位加到轨迹列表中
-            else:
-                if len(trajectory[temp_handness]) > 4:
-                    contour = np.array(trajectory[temp_handness], dtype=np.int32)
-                    rect = cv2.minAreaRect(contour)
-                    box = cv2.boxPoints(rect)
-                    box = np.int0(box)
-                    rect_draw_time[temp_handness] = time.time()
-                    last_drawn_box[temp_handness] = box
-                    # 如果指向操作结束 轨迹列表有至少四个点的时候
-                    # 使用最小包围图形将画的不规则图案调整为一个矩形
-
-                start_drag_time[temp_handness] = 0
-                trajectory[temp_handness].clear()
-
-            for i in range(1, len(trajectory[temp_handness])):
-
-                pt1 = (int(trajectory[temp_handness][i-1][0]), int(trajectory[temp_handness][i-1][1]))
-                pt2 = (int(trajectory[temp_handness][i][0]), int(trajectory[temp_handness][i][1]))
-                cv2.line(image, pt1, pt2, (0, 0, 255), 2)
-                # 绘制连接轨迹点的线
-
-            if last_drawn_box[temp_handness] is not None:
-                elapsed_time[temp_handness] = time.time() - rect_draw_time[temp_handness]
-                
-                if elapsed_time[temp_handness] < wait_box:
-                    cv2.drawContours(image, [last_drawn_box[temp_handness]], 0, (0, 255, 0), 2)
-                    # 将矩形框保留一段时间 否则一帧太快 无法看清效果
-                    
-                elif elapsed_time[temp_handness] >= wait_box - 0.1:
-                    
-                    box = last_drawn_box[temp_handness]
-                    x_min = max(0, min(box[:, 0]))
-                    y_min = max(0, min(box[:, 1]))
-                    x_max = min(image.shape[1], max(box[:, 0]))
-                    y_max = min(image.shape[0], max(box[:, 1]))
-                    cropped_image = image[y_min:y_max, x_min:x_max]
-                    filename = f"../image/cropped_{temp_handness}_{int(time.time())}.jpg"
-                    cv2.imwrite(filename, cropped_image)
-                    last_drawn_box[temp_handness] = None
-                # 不能直接剪裁画完的图像 可能会错误的将手剪裁进去
-                # 等待一段时间 有一个给手缓冲移动走的时间再将这一帧里的矩形提取出来
-                        
-            for i in range(21):
-                
-                cx = int(hand_21.landmark[i].x * width)
-                cy = int(hand_21.landmark[i].y * height)
-                cz = hand_21.landmark[i].z
-                depth_z = cz0 - cz
-                radius = max(int(6 * (1 + depth_z*5)), 0)
-                
-                if i == 0:
-                    image = cv2.circle(image, (cx, cy), radius, (255, 255, 0), thickness=-1)
-                if i == 8:
-                    image = cv2.circle(image, (cx, cy), radius, (255, 165, 0), thickness=-1)
-                    index_finger_tip_str += '{}:{:.2f}, '.format(hand_idx, depth_z)
-                if i in [1,5,9,13,17]: 
-                    image = cv2.circle(image, (cx, cy), radius,  (0, 0, 255), thickness=-1)
-                if i in [2,6,10,14,18]:
-                    image = cv2.circle(image, (cx, cy), radius,  (75, 0, 130), thickness=-1)
-                if i in [3,7,11,15,19]:
-                    image = cv2.circle(image, (cx, cy), radius, (238, 130, 238), thickness=-1)
-                if i in [4,12,16,20]:
-                    image = cv2.circle(image, (cx, cy), radius, (0, 255, 255), thickness=-1)
-                # 提取出每一个关节点 赋予对应的颜色和根据掌根的深度
-        
-        scaler= 1
-        image = cv2.putText(image,handness_str, (25*scaler, 100*scaler), cv2.FONT_HERSHEY_SIMPLEX, 1.25*scaler, (0,0,255), 2,)
-        image = cv2.putText(image,index_finger_tip_str, (25*scaler, 150*scaler), cv2.FONT_HERSHEY_SIMPLEX, 1.25*scaler, (0,0,255), 2,)
-
-        spend_time = time.time() - start_time
-        if spend_time > 0:
-            FPS = 1.0 / spend_time
-        else:
-            FPS = 0
-            
-        image = cv2.putText(image,'FPS '+str(int(FPS)),(25*scaler,50*scaler),cv2.FONT_HERSHEY_SIMPLEX,1.25*scaler,(0,0,255),2,)
-        # 显示FPS 检测到的手和食指指尖对于掌根的深度值
-    
-    else:
-        clear_hand_states()
-        # 如果没检测到手就清空全部信息
-    
-    return image
-
-########################################
-
-cap = cv2.VideoCapture(1)
-cap.open(0)
-
-while cap.isOpened():
-    success, frame = cap.read()
-    if not success:
-        print("Camera Error")
-        break
-      
-    frame = process_image(frame)
-    cv2.imshow('Video', frame)
-    
-    if cv2.waitKey(1) & 0xFF == ord('q'):
-        break
-        
-cap.release()
-cv2.destroyAllWindows()