Skip to content

Instantly share code, notes, and snippets.


Erol444/ Secret

Created May 31, 2021
What would you like to do?
Mobilenet video DepthAI
#!/usr/bin/env python3
from pathlib import Path
import sys
import cv2
import depthai as dai
import numpy as np
# Get argument first
nnPath = str((Path(__file__).parent / Path('models/mobilenet-ssd_openvino_2021.2_5shave.blob')).resolve().absolute())
if len(sys.argv) > 1:
nnPath = sys.argv[1]
if not Path(nnPath).exists():
import sys
raise FileNotFoundError(f'Required file/s not found, please run "{sys.executable}"')
# MobilenetSSD label texts
labelMap = ["background", "aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow",
"diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
# Create pipeline
pipeline = dai.Pipeline()
# Define sources and outputs
camRgb = pipeline.createColorCamera()
nn = pipeline.createMobileNetDetectionNetwork()
xoutVideo = pipeline.createXLinkOut()
nnOut = pipeline.createXLinkOut()
# Properties
camRgb.setPreviewSize(300, 300) # NN input
# Define a neural network that will make predictions based on the source frames
# Has to be 1:1 aspect ratio to match the NN input aspect ratio (300x300)
camRgb.setVideoSize(1080, 1080)
# Linking
# Connect to device and start pipeline
with dai.Device(pipeline) as device:
# Output queues will be used to get the frames and nn data from the outputs defined above
qVideo = device.getOutputQueue(name="video", maxSize=4, blocking=False)
qDet = device.getOutputQueue(name="nn", maxSize=4, blocking=False)
videoFrame = None
detections = []
# nn data, being the bounding box locations, are in <0..1> range - they need to be normalized 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, color)
cv2.putText(frame, f"{int(detection.confidence * 100)}%", (bbox[0] + 10, bbox[1] + 40), cv2.FONT_HERSHEY_TRIPLEX, 0.5, color)
cv2.rectangle(frame, (bbox[0], bbox[1]), (bbox[2], bbox[3]), color, 2)
# Show the frame
cv2.imshow(name, frame)
while True:
# Instead of get (blocking), we use tryGet (nonblocking) which will return the available data or None otherwise
inVideo = qVideo.tryGet()
inDet = qDet.tryGet()
if inVideo is not None:
videoFrame = inVideo.getCvFrame()
if inDet is not None:
detections = inDet.detections
if videoFrame is not None:
displayFrame("video", videoFrame)
if cv2.waitKey(1) == ord('q'):
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment