代码拉取完成,页面将自动刷新
#!/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_2021.4_6shave.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} install_requirements.py"')
# 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
monoRight = pipeline.create(dai.node.MonoCamera)
manip = pipeline.create(dai.node.ImageManip)
nn = pipeline.create(dai.node.MobileNetDetectionNetwork)
manipOut = pipeline.create(dai.node.XLinkOut)
nnOut = pipeline.create(dai.node.XLinkOut)
manipOut.setStreamName("right")
nnOut.setStreamName("nn")
# Properties
monoRight.setCamera("right")
monoRight.setResolution(dai.MonoCameraProperties.SensorResolution.THE_720_P)
# Convert the grayscale frame into the nn-acceptable form
manip.initialConfig.setResize(300, 300)
# The NN model expects BGR input. By default ImageManip output type would be same as input (gray in this case)
manip.initialConfig.setFrameType(dai.ImgFrame.Type.BGR888p)
nn.setConfidenceThreshold(0.5)
nn.setBlobPath(nnPath)
nn.setNumInferenceThreads(2)
nn.input.setBlocking(False)
# Linking
monoRight.out.link(manip.inputImage)
manip.out.link(nn.input)
manip.out.link(manipOut.input)
nn.out.link(nnOut.input)
# Connect to device and start pipeline
with dai.Device(pipeline) as device:
# Output queues will be used to get the grayscale frames and nn data from the outputs defined above
qRight = device.getOutputQueue("right", maxSize=4, blocking=False)
qDet = device.getOutputQueue("nn", maxSize=4, blocking=False)
frame = 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 (non-blocking) which will return the available data or None otherwise
inRight = qRight.tryGet()
inDet = qDet.tryGet()
if inRight is not None:
frame = inRight.getCvFrame()
if inDet is not None:
detections = inDet.detections
if frame is not None:
displayFrame("right", frame)
if cv2.waitKey(1) == ord('q'):
break
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。