Here's the code;
#!/usr/bin/env python3
import cv2
import depthai as dai
import blobconverter
# Create pipeline
pipeline = dai.Pipeline()
# Define source and output
camRgb = pipeline.create(dai.node.ColorCamera)
xoutVideo = pipeline.create(dai.node.XLinkOut)
xoutVideo.setStreamName("video")
# Properties
camRgb.setBoardSocket(dai.CameraBoardSocket.RGB)
camRgb.setResolution(dai.ColorCameraProperties.SensorResolution.THE_1080_P)
camRgb.setVideoSize(1920, 1080)
xoutVideo.input.setBlocking(False)
xoutVideo.input.setQueueSize(1)
# Create MobileNet detection network
mobilenet = pipeline.create(dai.node.MobileNetDetectionNetwork)
mobilenet.setBlobPath(
blobconverter.from_zoo(name="face-detection-retail-0004", shaves=3)
)
mobilenet.setConfidenceThreshold(0.7)
# manipRgb = pipeline.createImageManip()
# rgbRr = dai.RotatedRect()
# rgbRr.center.x, rgbRr.center.y = camRgb.getPreviewWidth() // 2, camRgb.getPreviewHeight() // 2
# rgbRr.size.width, rgbRr.size.height = camRgb.getPreviewHeight(), camRgb.getPreviewWidth()
# rgbRr.angle = 0
# manipRgb.initialConfig.setCropRotatedRect(rgbRr, False)
#
#
# camRgb.isp.link(manipRgb.inputImage)
# manipRgb.out.link(mobilenet.input)
crop_manip2 = pipeline.create(dai.node.ImageManip)
crop_manip2.initialConfig.setResize(300, 300)
crop_manip2.initialConfig.setFrameType(dai.ImgFrame.Type.BGR888p)
camRgb.isp.link(crop_manip2.inputImage)
#crop_manip2.out.link(mobilenet.input)
crop_manip = pipeline.create(dai.node.ImageManip)
crop_manip.initialConfig.setResize(300, 300)
crop_manip.initialConfig.setFrameType(dai.ImgFrame.Type.BGR888p)
crop_manip.out.link(crop_manip2.inputImage)
# camRgb.isp.link(crop_manip.inputImage)
# crop_manip2.out.link(crop_manip.inputImage)
crop_manip.out.link(mobilenet.input)
# Script node
script = pipeline.create(dai.node.Script)
mobilenet.out.link(script.inputs["dets"])
script.outputs["cam_cfg"].link(camRgb.inputConfig)
script.outputs["cam_ctrl"].link(camRgb.inputControl)
script.setScript(
"""
ORIGINAL_SIZE = (5312, 6000) # 48MP with size constraints described on IMX582 luxonis page
SCENE_SIZE = (1920, 1080) # 1080P
x_arr = []
y_arr = []
AVG_MAX_NUM=7
limits = [0, 0] # xmin and ymin limits
limits.append((ORIGINAL_SIZE[0] - SCENE_SIZE[0]) / ORIGINAL_SIZE[0]) # xmax limit
limits.append((ORIGINAL_SIZE[1] - SCENE_SIZE[1]) / ORIGINAL_SIZE[1]) # ymax limit
cfg = ImageManipConfig()
ctrl = CameraControl()
def average_filter(x, y):
x_arr.append(x)
y_arr.append(y)
if AVG_MAX_NUM < len(x_arr): x_arr.pop(0)
if AVG_MAX_NUM < len(y_arr): y_arr.pop(0)
x_avg = 0
y_avg = 0
for i in range(len(x_arr)):
x_avg += x_arr[i]
y_avg += y_arr[i]
x_avg = x_avg / len(x_arr)
y_avg = y_avg / len(y_arr)
if x_avg < limits[0]: x_avg = limits[0]
if y_avg < limits[1]: y_avg = limits[1]
if limits[2] < x_avg: x_avg = limits[2]
if limits[3] < y_avg: y_avg = limits[3]
return x_avg, y_avg
while True:
dets = node.io['dets'].get().detections
if len(dets) == 0: continue
coords = dets[0] # take first
width = (coords.xmax - coords.xmin) * ORIGINAL_SIZE[0]
height = (coords.ymax - coords.ymin) * ORIGINAL_SIZE[1]
x_pixel = int(max(0, coords.xmin * ORIGINAL_SIZE[0]))
y_pixel = int(max(0, coords.ymin * ORIGINAL_SIZE[1]))
# ctrl.setAutoFocusRegion(x_pixel, y_pixel, int(width), int(height))
# ctrl.setAutoExposureRegion(x_pixel, y_pixel, int(width), int(height))
# Get detection center
x = (coords.xmin + coords.xmax) / 2
y = (coords.ymin + coords.ymax) / 2
x -= SCENE_SIZE[0] / ORIGINAL_SIZE[0] / 2
y -= SCENE_SIZE[1] / ORIGINAL_SIZE[1] / 2
# node.warn(f"{x=} {y=}")
x_avg, y_avg = average_filter(x,y)
# node.warn(f"{x_avg=} {y_avg=}")
cfg.setCropRect(x_avg, y_avg, 0, 0)
node.io['cam_cfg'].send(cfg)
node.io['cam_ctrl'].send(ctrl)
"""
)
# Linking
camRgb.video.link(xoutVideo.input)
# Connect to device and start pipeline
with dai.Device(pipeline) as device:
video = device.getOutputQueue(name="video", maxSize=1, blocking=False)
while True:
videoIn = video.get()
print("Done in seconds")
# Get BGR frame from NV12 encoded video frame to show with opencv
# Visualizing the frame on slower hosts might have overhead
cv2.imshow("video", videoIn.getCvFrame())
if cv2.waitKey(1) == ord('q'):
break
