Hey guys, how are you doing? I have this code, and how can I run it in standalone mode? I have both OAK-1 PoE and OAK-D PoE cameras, I want to run it in standalone mode to get the maximum performance as possible. Is there any step-by-step documentation or tutorial on how to convert into a standalone mode? I read the official website, But couldn't understand well exactly how to do it. I'll leave the code below, hope you will help me thanks 🙂
from pathlib import Path
import cv2
import depthai as dai
import time
from environs import Env
env = Env()
env.read_env()
MxID = env('MxID')
# Set custom ROI coordinates (x, y, width, height)
custom_roi = (350/640, 250/640, 640/640, 640/640)
# Coordinates of the counting line
line_start = (320, 0)
line_end = (320, 640)
# tiny yolo v4 label texts
labelMap = ["person",]
nnPath = str((Path(__file__).parent / Path('model/yolov6n_coco_640x640_openvino_2022.1_6shave.blob')).resolve().absolute())
# Creating pipeline
pipeline = dai.Pipeline()
# Sources and outputs
camRgb = pipeline.create(dai.node.ColorCamera)
detectionNetwork = pipeline.create(dai.node.YoloDetectionNetwork)
objectTracker = pipeline.create(dai.node.ObjectTracker)
xlinkOut = pipeline.create(dai.node.XLinkOut)
trackerOut = pipeline.create(dai.node.XLinkOut)
fullFrame = pipeline.create(dai.node.XLinkOut) # creating new pipline for full_frame
xlinkOut.setStreamName("preview")
trackerOut.setStreamName("tracklets")
fullFrame.setStreamName("full_frame") # To get Full Frame
# Creating Manip node
manip = pipeline.create(dai.node.ImageManip)
# Setting CropRect for the Region of Interest
# manip.initialConfig.setCropRect(*custom_roi)
# Setting Resize for the neural network input size
manip.initialConfig.setResize(640, 640)
# Setting maximum output frame size based on the desired output dimensions
max_output_width = 640
max_output_height = 640
max_output_frame_size = 3 * max_output_width * max_output_height # Assuming 3 channels for BGR image
manip.setMaxOutputFrameSize(max_output_frame_size)
# Properties
if MxID == "14442C10C1AD3FD700":
camRgb.setImageOrientation(dai.CameraImageOrientation.HORIZONTAL_MIRROR)
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(80)
detectionNetwork.setCoordinateSize(4)
# detectionNetwork.setAnchors([10, 14, 23, 27, 37, 58, 81, 82, 135, 169, 344, 319]) #for YOLOv4
# detectionNetwork.setAnchorMasks({"side26": [1, 2, 3], "side13": [3, 4, 5]})
detectionNetwork.setAnchors([10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326]) #for YOLOv5
detectionNetwork.setAnchorMasks({"side52": [0,1,2], "side26": [3,4,5], "side13": [6,7,8]})
detectionNetwork.setIouThreshold(0.5)
detectionNetwork.setBlobPath(nnPath)
detectionNetwork.setNumInferenceThreads(2)
detectionNetwork.input.setBlocking(False)
objectTracker.setDetectionLabelsToTrack([0]) # track only person
# possible tracking types: ZERO_TERM_COLOR_HISTOGRAM, ZERO_TERM_IMAGELESS, SHORT_TERM_IMAGELESS, SHORT_TERM_KCF
objectTracker.setTrackerType(dai.TrackerType.ZERO_TERM_COLOR_HISTOGRAM)
# take the smallest ID when new object is tracked, possible options: SMALLEST_ID, UNIQUE_ID
objectTracker.setTrackerIdAssignmentPolicy(dai.TrackerIdAssignmentPolicy.UNIQUE_ID)
#Linking
# Connecting Manip node to ColorCamera
camRgb.preview.link(manip.inputImage)
camRgb.preview.link(fullFrame.input)
# Connecting Manip node to YoloDetectionNetwork
manip.out.link(detectionNetwork.input)
# camRgb.preview.link(detectionNetwork.input)
objectTracker.passthroughTrackerFrame.link(xlinkOut.input)
detectionNetwork.passthrough.link(objectTracker.inputTrackerFrame)
detectionNetwork.passthrough.link(objectTracker.inputDetectionFrame)
detectionNetwork.out.link(objectTracker.inputDetections)
objectTracker.out.link(trackerOut.input)
device = dai.DeviceInfo(MxID)
# Connecting to device and starting pipeline
with dai.Device(pipeline, device) as device:
preview = device.getOutputQueue("preview", 4, False)
tracklets = device.getOutputQueue("tracklets", 4, False)
previewFull = device.getOutputQueue("full_frame", 4, False)
startTime = time.monotonic()
counter = 0
fps = 0
frame = None
h_line = 320
pos = {}
going_in = 0
going_out = 0
obj_counter = [0, 0, 0, 0] # left, right, up, down
while(True):
imgFrame = preview.get()
track = tracklets.get()
imgFull = previewFull.get()
counter+=1
current_time = time.monotonic()
if (current_time - startTime) > 1 :
fps = counter / (current_time - startTime)
counter = 0
startTime = current_time
color = (255, 0, 0)
text_color = (0, 0, 255)
rectangle = (111, 147, 26)
frame = imgFrame.getCvFrame()
trackletsData = track.tracklets
# Draw the counting line on the frame
cv2.line(frame, line_start, line_end, (0, 255, 0), 2)
for t in trackletsData:
if t.status.name == "TRACKED":
roi = t.roi.denormalize(frame.shape[1], frame.shape[0])
x1 = int(roi.topLeft().x)
y1 = int(roi.topLeft().y)
x2 = int(roi.bottomRight().x)
y2 = int(roi.bottomRight().y)
# Calculate centroid
centroid = (int((x2-x1)/2+x1), int((y2-y1)/2+y1))
# Calculate the buffer zone boundaries
right_boundary = h_line + 15
left_boundary = h_line - 15
try:
if not (left_boundary <= centroid[0] <= right_boundary):
pos[t.id] = {
'previous': pos[t.id]['current'],
'current': centroid[0] }
if pos[t.id]['current'] > right_boundary and pos[t.id]['previous'] < right_boundary:
obj_counter[1] += 1 #Right side
going_in += 1
if pos[t.id]['current'] < left_boundary and pos[t.id]['previous'] > left_boundary:
obj_counter[0] += 1 #Left side
going_out += 1
except:
pos[t.id] = {'current': centroid[0]}
try:
label = labelMap[t.label]
except:
label = t.label
cv2.putText(frame, str(label), (x1 + 10, y1 + 20), cv2.FONT_HERSHEY_TRIPLEX, 0.5, text_color)
cv2.putText(frame, f"ID: {[t.id]}", (x1 + 10, y1 + 45), cv2.FONT_HERSHEY_TRIPLEX, 0.5, text_color)
cv2.putText(frame, t.status.name, (x1 + 10, y1 + 70), cv2.FONT_HERSHEY_TRIPLEX, 0.5, text_color)
cv2.rectangle(frame, (x1, y1), (x2, y2), rectangle, cv2.FONT_HERSHEY_SIMPLEX)
cv2.circle(frame, (centroid[0], centroid[1]), 4, (255, 255, 255), -1)
cv2.putText(frame, f'Left: {obj_counter[0]}; Right: {obj_counter[1]}', (10, 35), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 0, 0xFF), 2, cv2.FONT_HERSHEY_SIMPLEX)
cv2.putText(frame, "FPS: {:.2f}".format(fps), (2, frame.shape[0] - 4), cv2.FONT_HERSHEY_TRIPLEX, 0.6, text_color)
# Displaying full frame
frameFull = imgFull.getCvFrame()
cv2.imshow("full_frame", frameFull)
# Displaying cropped frame with tracked objects
cv2.imshow("tracker", frame)
if cv2.waitKey(1) == ord('q'):
break`
