vcs-python-repository/Client/yolo_client.py
2024-04-16 17:26:17 -07:00

96 lines
No EOL
3.4 KiB
Python

import cv2
from websocket import create_connection
import argparse
import math
from ultralytics import YOLO
# object classes
classNames = ["person", "bicycle", "car", "motorbike", "aeroplane", "bus", "train", "truck", "boat",
"traffic light", "fire hydrant", "stop sign", "parking meter", "bench", "bird", "cat",
"dog", "horse", "sheep", "cow", "elephant", "bear", "zebra", "giraffe", "backpack", "umbrella",
"handbag", "tie", "suitcase", "frisbee", "skis", "snowboard", "sports ball", "kite", "baseball bat",
"baseball glove", "skateboard", "surfboard", "tennis racket", "bottle", "wine glass", "cup",
"fork", "knife", "spoon", "bowl", "banana", "apple", "sandwich", "orange", "broccoli",
"carrot", "hot dog", "pizza", "donut", "cake", "chair", "sofa", "pottedplant", "bed",
"diningtable", "toilet", "tvmonitor", "laptop", "mouse", "remote", "keyboard", "cell phone",
"microwave", "oven", "toaster", "sink", "refrigerator", "book", "clock", "vase", "scissors",
"teddy bear", "hair drier", "toothbrush"
]
def main(websocket_addr):
# Connect to websocket server
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('yolov8x.pt') # Load an official Detect model
# Open webcam
cap = cv2.VideoCapture(0)
cap.set(3, 640)
cap.set(4, 480)
while cap.isOpened():
ret, frame = cap.read()
frame = cv2.resize(frame, (640, 480))
if not ret:
break
# Perform object detection
results = model.track(frame, persist=True)
for r in results:
lines = ""
boxes = r.boxes
for box in boxes:
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
# put box in cam
cv2.rectangle(frame, (x1, y1), (x2, y2), (255, 0, 255), 3)
# class name
cls = int(box.cls[0])
# 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)
lines += f"{id} {x1}:{y1} {x2}:{y2}\n"
ws.send(lines)
cv2.imshow('Webcam', frame)
if cv2.waitKey(1) == ord('q'):
break
cap.release()
cv2.destroyAllWindows()
if __name__ == "__main__":
parser = argparse.ArgumentParser(description='Detect people from webcam feed and send data to websocket server')
parser.add_argument('websocket_addr', type=str, help='Websocket server address')
args = parser.parse_args()
main(args.websocket_addr)