Update app.py

app.py

@@ -232,7 +232,7 @@ class Detection(NamedTuple):
     score: float
     box: np.ndarray
 
-result_queue: "queue.Queue[List[Detection]]" = queue.Queue()
+# result_queue: "queue.Queue[List[Detection]]" = queue.Queue()
 
 listImg = os.listdir('model/street') if os.path.exists('model/street') else []
 if not listImg:
@@ -249,7 +249,6 @@ if "output_text" not in st.session_state:
     st.session_state["output_text"] = ""
 
 
-result_queue=queue.Queue()
 # def video_frame_callback(frame: av.VideoFrame) -> av.VideoFrame:
 #     img = frame.to_ndarray(format="bgr24")
 #     hands, img = detector.findHands(img, flipType=False)
@@ -269,13 +268,34 @@ result_queue=queue.Queue()
         
 #     return av.VideoFrame.from_ndarray(img, format="bgr24")
 
+
+# Initialize result queue
+result_queue = queue.Queue()
+
 def video_frame_callback(frame: av.VideoFrame) -> av.VideoFrame:
     img = frame.to_ndarray(format="bgr24")
+    
+    # Detect hands
+    hands, img = detector.findHands(img, flipType=False)
+    
+    # Collect detections
+    detections = []
+    
     if hands:
-        hand = hands[0]
-        bbox = hand["bbox"]
-        cv2.rectangle(img, (bbox[0], bbox[1]), (255, 0, 0), 2)
-        result_queue.put(hands)
+        for hand in hands:
+            bbox = hand["bbox"]
+            label = hand["type"]
+            score = hand["score"]
+            
+            # Draw bounding box
+            cv2.rectangle(img, (bbox[0], bbox[1]), 
+                          (bbox[0]+bbox[2], bbox[1]+bbox[3]), (255, 0, 0), 2)
+            
+            # Append detection details
+            detections.append({"label": label, "score": score, "bbox": bbox})
+        
+        # Put detections into result queue
+        result_queue.put(detections)
 
     return av.VideoFrame.from_ndarray(img, format="bgr24")