mediapipe library hand detection exploration

hand detection discovery.py

+import cv2
+import random
+import mediapipe as mp
+
+def write_landmark_positions_on_frame(frame, landmark_list):
+    if len(landmark_list) == 0:
+        return frame
+    
+    height, width = frame.shape[:2]
+    color = (250, 0, 0)
+    for lm in landmark_list:
+        # landmark position in pixels
+        pos_px = ((int(width * lm[0])), int(height * lm[1]))
+        text = f'{pos_px[0]} : {pos_px[1]}'
+        org = (pos_px[0]-20, pos_px[1]-10)
+        cv2.putText(img = frame, text = text, org = org, 
+                    fontFace = cv2.FONT_HERSHEY_DUPLEX, fontScale = .5, color = color, thickness = 1)
+
+    return frame
+
+def transform_to_relative(landmark_list):
+    if len(landmark_list) == 0:
+        return landmark_list
+    
+    origon = landmark_list[0]
+    relative_landmark_list = []
+    for lm in landmark_list:
+        rel_lm = (lm[0] - origon[0], lm[1] - origon[1])
+        print(rel_lm)
+        relative_landmark_list.append(rel_lm)
+    
+
+## main: open video and do hand detection
+def main():
+    # create hand detection object
+    mp_hands = mp.solutions.hands
+    mp_drawing = mp.solutions.drawing_utils
+    
+    # open video
+    cap = cv2.VideoCapture(0)
+    
+    # if cannot open video give warning
+    if not cap.isOpened():
+        print("Warning: cannot reach camera")
+    else:
+        print("Program is running, push 'q' to quit.")
+    
+    # mediapipe hand object
+    with mp_hands.Hands( max_num_hands=1, model_complexity=1,
+                        min_detection_confidence=0.9, min_tracking_confidence=0.9) as hands:
+        
+        # read frames from webcamera
+        while cap.isOpened():
+            ret, frame = cap.read()
+            
+            if not ret:
+                print("Warning: cannot read camera input")
+                break
+            
+            # flip frame to appear as a mirror
+            frame = cv2.flip(frame, 1)
+            frameRGB = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+            
+            ## hand detection
+            results = hands.process(frameRGB)
+            
+            landmark_list = []
+            if results.multi_hand_landmarks:
+                # multi_hand_landmarks can store two hands, if max_num_hands=2, in which case we have to iterate through the hands with
+                # for num, hand in enumerate(results.multi_hand_landmarks): 
+                
+                # one hand is detected, because max_num_hands=1
+                hand_landmarks = results.multi_hand_landmarks[0]  
+
+                # draw landmarks on frame
+                mp_drawing.draw_landmarks(frameRGB, hand_landmarks, mp_hands.HAND_CONNECTIONS, 
+                                            mp_drawing.DrawingSpec(color=(250, 0, 0), thickness=2, circle_radius=4),
+                                            mp_drawing.DrawingSpec(color=(0, 250, 0), thickness=2, circle_radius=2),
+                                            )
+                
+                # get landmark list with indices described in https://github.com/google-ai-edge/mediapipe/blob/master/mediapipe/python/solutions/hands.py
+                for lm in hand_landmarks.landmark:
+                    landmark_list.append((lm.x, lm.y))
+                    
+            # relate landmarks to the first (wrist) position
+            relative_landmark_list = transform_to_relative(landmark_list)
+            
+            # write positions on frame
+            frameRGB = write_landmark_positions_on_frame(frameRGB, landmark_list)
+            
+            # transform back RGB and show frame with annotation
+            frame_annotated = cv2.cvtColor(frameRGB, cv2.COLOR_RGB2BGR)
+            cv2.imshow('Hand tracking', frame_annotated)
+            
+            # or show original frame without annotation
+            # cv2.imshow('Hand tracking', frame)
+            
+            if cv2.waitKey(1) & 0xFF == ord('q'):
+                print("Quit camera")
+                break
+
+    cap.release()
+    cv2.destroyAllWindows()
+    print("Program closed")
+
+if __name__ == '__main__':
+    main()
\ No newline at end of file