divide into classes

final_project/hand_detection.py

+
+
+def normalise_landmarks(landmark_list):
+    if len(landmark_list) == 0:
+        return landmark_list
+    
+    x = [lm[0] for lm in landmark_list]
+    y = [lm[1] for lm in landmark_list]
+
+    min_x = min(x)
+    max_x = max(x)
+    min_y = min(y)
+    max_y = max(y)
+    
+    normalised_landmarks = []
+    for lm in landmark_list:
+        x_norm = (lm[0] - min_x) / (max_x - min_x)
+        y_norm = (lm[1] - min_y) / (max_y - min_y)
+        lm_norm = (x_norm, y_norm)
+        
+        normalised_landmarks.append(lm_norm)
+    
+    return normalised_landmarks  
\ No newline at end of file

final_project/control_mouse.py → final_project/main.py

@@ -4,130 +4,12 @@ import mediapipe as mp
 import pickle
 import numpy as np
 from sklearn.ensemble import RandomForestClassifier
-import pyautogui
 import time
-from collections import Counter
-from screeninfo import get_monitors
+import os
 
-MONITOR = get_monitors()[0]
-WIDTH, HEIGHT = MONITOR.width, MONITOR.height
-
-class Mouse:
-    def __init__(self) -> None:
-        
-        self.predictions = []
-        self.previous_action = None
-        self.freeze_action = False
-
-        # parameters to fine-tune
-        self.action_length = 5
-        #self.move_distance = 10
-        self.scroll_distance = 50   
-        #self.time_checking = 0.5
-        self.stop_pos = None
-
-    def get_hand_pos(self, hand_pos):
-        self.hand_pos_x = hand_pos[0]
-        self.hand_pos_y = hand_pos[1]
-
-    def add_prediction(self, prediction):
-        self.predictions.append(prediction)
-        if len(self.predictions) == self.action_length:
-            self.make_action()
-
-    def make_action(self):
-        action = self.get_major_element(self.predictions)
-        if self.freeze_action and action == self.previous_action:
-            self.update_init(action)
-        else:
-            self.mouse_control(action)
-            self.update_init(action)
-
-    def update_init(self, action):
-        self.predictions = []
-        self.previous_action = action
-
-        self.freeze_action = action in {"left click", "right click", "double click"} # maybe change to keyboard and drops
-
-    def mouse_hand_parameters(self):
-        pass
-
-    def mouse_control(self, prediction):
-        if prediction == "stop execution" or None:
-            pass  # Stop movement
-        elif prediction == "move cursor":
-            
-            #hand_point = ([int(self.hand_pos_x*WIDTH), int(self.hand_pos_y*HEIGHT)])
-            hand_x = np.clip(int(self.hand_pos_x*WIDTH), 0, WIDTH-1)
-            hand_y = np.clip(int(self.hand_pos_y*HEIGHT), 0, HEIGHT-1)
-            pyautogui.moveTo(hand_x, hand_y)
-
-        elif prediction == "stop moving":
-            pyautogui.move(0, 0)  # Stop cursor
-            self.stop_pos = pyautogui.position()
-        elif prediction == "left click":
-            pyautogui.click()  # Left click 
-        elif prediction == "right click":
-            pyautogui.click(button='right')  # Right click
-        elif prediction == "double click":
-            pyautogui.click(clicks=2)    # Double click
-        elif prediction == "scrolling up":
-            pyautogui.scroll(self.scroll_distance)  # Scroll up
-        elif prediction == "scrolling down":
-            pyautogui.scroll(-self.scroll_distance)  # Scroll down
-        elif prediction == "scrolling right":
-            pyautogui.hscroll(self.scroll_distance)    # Scroll right
-            # THIS FUNCTION NOT WORKS ON WINDOWS
-        elif prediction == "scrolling left":
-            pyautogui.hscroll(self.scroll_distance)    # Scroll left
-            # THIS FUNCTION NOT WORKS ON WINDOWS
-        elif prediction == "drag":
-            if self.previous_action == "stop moving":
-                pyautogui.moveTo(*self.stop_pos)
-            pyautogui.mouseDown()  
-            hand_x = np.clip(int(self.hand_pos_x*WIDTH), 0, WIDTH-1)
-            hand_y = np.clip(int(self.hand_pos_y*HEIGHT), 0, HEIGHT-1)
-            pyautogui.moveTo(hand_x, hand_y)
-        elif prediction == "drop":
-            pyautogui.mouseUp()
-        elif prediction == "multiple item selection grab":
-            pyautogui.mouseDown()
-        elif prediction == "multiple item selection drop":
-            pyautogui.mouseUp()
-        elif prediction == "change to keyboard":
-            pass
-        
-        #time.sleep(self.time_checking)  # Adjust speed of movement
-    
-    def get_major_element(self, string_list):
-        counts = Counter(string_list)
-        # Find the element with the maximum count
-        major_element, _ = counts.most_common(1)[0]
-        
-        return major_element
-
-
-def normalise_landmarks(landmark_list):
-    if len(landmark_list) == 0:
-        return landmark_list
-    
-    x = [lm[0] for lm in landmark_list]
-    y = [lm[1] for lm in landmark_list]
-
-    min_x = min(x)
-    max_x = max(x)
-    min_y = min(y)
-    max_y = max(y)
-    
-    normalised_landmarks = []
-    for lm in landmark_list:
-        x_norm = (lm[0] - min_x) / (max_x - min_x)
-        y_norm = (lm[1] - min_y) / (max_y - min_y)
-        lm_norm = (x_norm, y_norm)
-        
-        normalised_landmarks.append(lm_norm)
-    
-    return normalised_landmarks    
+from mouse_class import Mouse
+from hand_detection import normalise_landmarks
+  
 
 ## main: open video and do hand detection
 def main():
@@ -135,7 +17,9 @@ def main():
     mouse = Mouse()
 
     # load model
-    model_dict = pickle.load(open('./trained_Moni_data.p', 'rb'))
+    current_dir = os.path.dirname(__file__)
+    model_path = os.path.abspath(os.path.join(current_dir, os.pardir, 'trained_models', 'trained_Moni_data.p'))
+    model_dict = pickle.load(open(model_path, 'rb'))
     model = model_dict['model']
     
     # create hand detection object

final_project/mouse_class.py

+import numpy as np
+import pyautogui
+from collections import Counter
+from screeninfo import get_monitors
+
+MONITOR = get_monitors()[0]
+WIDTH, HEIGHT = MONITOR.width, MONITOR.height
+
+class Mouse:
+    def __init__(self) -> None:
+        
+        self.predictions = []
+        self.previous_action = None
+        self.freeze_action = False
+
+        # parameters to fine-tune
+        self.action_length = 5
+        #self.move_distance = 10
+        self.scroll_distance = 50   
+        #self.time_checking = 0.5
+        self.stop_pos = None
+
+    def get_hand_pos(self, hand_pos):
+        self.hand_pos_x = hand_pos[0]
+        self.hand_pos_y = hand_pos[1]
+
+    def add_prediction(self, prediction):
+        self.predictions.append(prediction)
+        if len(self.predictions) == self.action_length:
+            self.make_action()
+
+    def make_action(self):
+        action = self.get_major_element(self.predictions)
+        if self.freeze_action and action == self.previous_action:
+            self.update_init(action)
+        else:
+            self.mouse_control(action)
+            self.update_init(action)
+
+    def update_init(self, action):
+        self.predictions = []
+        self.previous_action = action
+
+        self.freeze_action = action in {"left click", "right click", "double click"} # maybe change to keyboard and drops
+
+    def mouse_hand_parameters(self):
+        pass
+
+    def mouse_control(self, prediction):
+        if prediction == "stop execution" or None:
+            pass  # Stop movement
+        elif prediction == "move cursor":
+            
+            #hand_point = ([int(self.hand_pos_x*WIDTH), int(self.hand_pos_y*HEIGHT)])
+            hand_x = np.clip(int(self.hand_pos_x*WIDTH), 0, WIDTH-1)
+            hand_y = np.clip(int(self.hand_pos_y*HEIGHT), 0, HEIGHT-1)
+            pyautogui.moveTo(hand_x, hand_y)
+
+        elif prediction == "stop moving":
+            pyautogui.move(0, 0)  # Stop cursor
+            self.stop_pos = pyautogui.position()
+        elif prediction == "left click":
+            pyautogui.click()  # Left click 
+        elif prediction == "right click":
+            pyautogui.click(button='right')  # Right click
+        elif prediction == "double click":
+            pyautogui.click(clicks=2)    # Double click
+        elif prediction == "scrolling up":
+            pyautogui.scroll(self.scroll_distance)  # Scroll up
+        elif prediction == "scrolling down":
+            pyautogui.scroll(-self.scroll_distance)  # Scroll down
+        elif prediction == "scrolling right":
+            pyautogui.hscroll(self.scroll_distance)    # Scroll right
+            # THIS FUNCTION NOT WORKS ON WINDOWS
+        elif prediction == "scrolling left":
+            pyautogui.hscroll(self.scroll_distance)    # Scroll left
+            # THIS FUNCTION NOT WORKS ON WINDOWS
+        elif prediction == "drag":
+            if self.previous_action == "stop moving":
+                pyautogui.moveTo(*self.stop_pos)
+            pyautogui.mouseDown()  
+            hand_x = np.clip(int(self.hand_pos_x*WIDTH), 0, WIDTH-1)
+            hand_y = np.clip(int(self.hand_pos_y*HEIGHT), 0, HEIGHT-1)
+            pyautogui.moveTo(hand_x, hand_y)
+        elif prediction == "drop":
+            pyautogui.mouseUp()
+        elif prediction == "multiple item selection grab":
+            pyautogui.mouseDown()
+        elif prediction == "multiple item selection drop":
+            pyautogui.mouseUp()
+        elif prediction == "change to keyboard":
+            pass
+        
+        #time.sleep(self.time_checking)  # Adjust speed of movement
+    
+    def get_major_element(self, string_list):
+        counts = Counter(string_list)
+        # Find the element with the maximum count
+        major_element, _ = counts.most_common(1)[0]
+        
+        return major_element