I managed to make it work using some Docs and mainly ChatGPT(!).
However, I can't seem to integrate the ObjectTracker node into this program without running into some error; there have just been too many.
from pathlib import Path
import sys
import cv2
import depthai as dai
import numpy as np
import time
# Get yolo v8n model blob file path
nnPath = str("03022025.blob")
if not Path(nnPath).exists():
import sys
raise FileNotFoundError(f'Required file/s not found, please run "{sys.executable} install_requirements.py"')
# yolo v8 abel texts
labelMap = ["goat", "pig", "sheep"]
syncNN = True
# Create pipeline
pipeline = dai.Pipeline()
# Define sources and outputs
camRgb = pipeline.create(dai.node.ColorCamera)
detectionNetwork = pipeline.create(dai.node.YoloDetectionNetwork)
xoutRgb = pipeline.create(dai.node.XLinkOut)
nnOut = pipeline.create(dai.node.XLinkOut)
xoutRgb.setStreamName("rgb")
nnOut.setStreamName("nn")
# Properties
camRgb.setPreviewSize(640, 640)
camRgb.setResolution(dai.ColorCameraProperties.SensorResolution.THE_1080_P)
camRgb.setInterleaved(False)
camRgb.setColorOrder(dai.ColorCameraProperties.ColorOrder.BGR)
camRgb.setFps(40)
# Network specific settings
detectionNetwork.setConfidenceThreshold(0.5)
detectionNetwork.setNumClasses(3)
detectionNetwork.setCoordinateSize(4)
detectionNetwork.setIouThreshold(0.5)
detectionNetwork.setBlobPath(nnPath)
detectionNetwork.setNumInferenceThreads(2)
detectionNetwork.input.setBlocking(True) # From False
# Linking
camRgb.preview.link(detectionNetwork.input)
if syncNN:
detectionNetwork.passthrough.link(xoutRgb.input)
else:
camRgb.preview.link(xoutRgb.input)
detectionNetwork.out.link(nnOut.input)
# Connect to device and start pipeline
with dai.Device(pipeline) as device:
# Output queues will be used to get the rgb frames and nn data from the outputs defined above
qRgb = device.getOutputQueue(name="rgb", maxSize=4, blocking=False)
qDet = device.getOutputQueue(name="nn", maxSize=4, blocking=False)
frame = None
detections = []
startTime = time.monotonic()
counter = 0
color2 = (255, 255, 255)
# nn data, being the bounding box locations, are in <0..1> range - they need to be normalised with frame width/height
def frameNorm(frame, bbox):
normVals = np.full(len(bbox), frame.shape[0])
normVals[::2] = frame.shape[1]
return (np.clip(np.array(bbox), 0, 1) * normVals).astype(int)
def displayFrame(name, frame):
color = (255, 0, 0)
for detection in detections:
bbox = frameNorm(frame, (detection.xmin, detection.ymin, detection.xmax, detection.ymax))
cv2.putText(frame, labelMap[detection.label], (bbox[0] + 10, bbox[1] + 20), cv2.FONT_HERSHEY_TRIPLEX, 0.5, 255)
cv2.putText(frame, f"{detection.confidence}%", (bbox[0] + 10, bbox[1] + 40), cv2.FONT_HERSHEY_SIMPLEX, 0.5, 255)
cv2.rectangle(frame, (bbox[0], bbox[1]), (bbox[2], bbox[3]), color, 2)
# Show the frame
cv2.imshow(name, frame)
while True:
if syncNN:
inRgb = qRgb.get()
inDet = qDet.get()
else:
inRgb = qRgb.tryGet()
inDet = qDet.tryGet()
if inRgb is not None:
frame = inRgb.getCvFrame()
cv2.putText(frame, "NN fps: {:.2f}".format(counter / (time.monotonic() - startTime)),
(2, frame.shape[0] - 4), cv2.FONT_HERSHEY_TRIPLEX, 0.4, color2)
if inDet is not None:
detections = inDet.detections
counter += 1
if frame is not None:
displayFrame("rgb", frame)
if cv2.waitKey(1) == ord('q'):
break
This is my program, so far, any assistance into integrating ObjectTracking would be appreciated!
Thanks in advance.