added handshake code

Client/yolo_client.py

@@ -20,10 +20,20 @@ classNames = ["person", "bicycle", "car", "motorbike", "aeroplane", "bus", "trai
 
 def main(websocket_addr):
     # Connect to websocket server
-    # ws = create_connection(websocket_addr)
+    ws = create_connection(websocket_addr)
+
+    handshake = ws.recv()
+
+    if handshake == "Type?":
+        ws.send("Type: Automated")
+    else:
+        ws.close()
+        return
+
+    print("Handshake complete")
 
     # Load YOLO model
-    model = YOLO('yolov8s.pt')  # Load an official Detect model
+    model = YOLO('yolov8x.pt')  # Load an official Detect model
 
     # Open webcam
     cap = cv2.VideoCapture(0)
@@ -32,19 +42,20 @@ def main(websocket_addr):
 
     while cap.isOpened():
         ret, frame = cap.read()
+        frame = cv2.resize(frame, (640, 480))
         if not ret:
             break
 
         # Perform object detection
-        results = model.predict(frame)
-
-        max_x1, max_y1, max_x2, max_y2 = 0
+        results = model.track(frame, persist=True)
 
         for r in results:
+            lines = ""
             boxes = r.boxes
             for box in boxes:
-                if box.cls[0].item() == 0:
+                if box.cls[0].item() == 0 and not box.id is None:
                     # bounding box
+                    id = box.id.int().cpu().tolist()
                     x1, y1, x2, y2 = box.xyxy[0]
                     x1, y1, x2, y2 = int(x1), int(y1), int(x2), int(y2) # convert to int values
 
@@ -56,20 +67,19 @@ def main(websocket_addr):
 
                     # object details
                     org = [x1, y1]
+                    org2 = [x1, y1+50]
                     font = cv2.FONT_HERSHEY_SIMPLEX
                     fontScale = 1
                     color = (255, 0, 0)
+                    color_w = (255, 255, 255)
                     thickness = 2
 
                     cv2.putText(frame, classNames[cls], org, font, fontScale, color, thickness)
+                    cv2.putText(frame, str(id), org2, font, fontScale, color_w, thickness)
 
-                    if (x2-x1) * (y2 - y1):
-                        max_x1 = x1
-                        max_x2 = x2 
-                        max_y1 = y1 
-                        max_y2 = y2
+                    lines += f"{id} {x1}:{y1} {x2}:{y2}\n"
 
-        print(f"{max_x1}:{max_y1}, {max_x2}:{max_y2}")
+        ws.send(lines)
 
         cv2.imshow('Webcam', frame)
         if cv2.waitKey(1) == ord('q'):

YOLO python/generate-predictions.py

@@ -10,5 +10,5 @@ model = YOLO('yolov8s.pt')  # Load an official Detect model
 
 
 # Run inference on 'bus.jpg' with arguments
-for i in model.predict('D:\Projects\FaceTrackingCamerav3\YOLO python\kevin-center-camera-position.mp4', show=True, save=True, save_frames=True, save_txt=True, conf=0.5, stream=True):
+for i in model.predict("D:\Projects\FaceTrackingCamerav3\Raymond.mp4", save=True, save_frames=True, save_txt=True, conf=0.5, stream=True):
     continue

joystick-controller-client

@@ -1 +1 @@
-Subproject commit 2278b4cd79c9ec0267198eba9f92b4e4ad4aeb78
+Subproject commit ef96409082241db6ff012dc2d898894e6efde3a3