skshareef
commented
1 year ago This is the code I am currently using: _import math import cv2 import depthai as dai import numpy as np stepSize = 0.05
newConfig = False
Create pipeline
pipeline = dai.Pipeline()
Define sources and outputs
monoLeft = pipeline.create(dai.node.MonoCamera) monoRight = pipeline.create(dai.node.MonoCamera) stereo = pipeline.create(dai.node.StereoDepth) spatialLocationCalculator = pipeline.create(dai.node.SpatialLocationCalculator)
xoutDepth = pipeline.create(dai.node.XLinkOut) xoutSpatialData = pipeline.create(dai.node.XLinkOut) xinSpatialCalcConfig = pipeline.create(dai.node.XLinkIn)
xoutDepth.setStreamName("depth") xoutSpatialData.setStreamName("spatialData") xinSpatialCalcConfig.setStreamName("spatialCalcConfig")
Properties
monoLeft.setResolution(dai.MonoCameraProperties.SensorResolution.THE_400_P) monoLeft.setCamera("left") monoRight.setResolution(dai.MonoCameraProperties.SensorResolution.THE_400_P) monoRight.setCamera("right")
stereo.setDefaultProfilePreset(dai.node.StereoDepth.PresetMode.HIGH_DENSITY) stereo.setLeftRightCheck(True) stereo.setSubpixel(True)
Config
topLeft = dai.Point2f(0.3, 0.3) bottomRight = dai.Point2f(0.35, 0.35)
config = dai.SpatialLocationCalculatorConfigData() config.depthThresholds.lowerThreshold = 100 config.depthThresholds.upperThreshold = 10000 calculationAlgorithm = dai.SpatialLocationCalculatorAlgorithm.MEDIAN config.roi = dai.Rect(topLeft, bottomRight)
spatialLocationCalculator.inputConfig.setWaitForMessage(False) spatialLocationCalculator.initialConfig.addROI(config)
Linking
monoLeft.out.link(stereo.left) monoRight.out.link(stereo.right)
spatialLocationCalculator.passthroughDepth.link(xoutDepth.input) stereo.depth.link(spatialLocationCalculator.inputDepth)
spatialLocationCalculator.out.link(xoutSpatialData.input) xinSpatialCalcConfig.out.link(spatialLocationCalculator.inputConfig) def calculate_distance(x,y,z): return math.sqrt(x 2 + y 2 + z ** 2)
Connect to device and start pipeline
with dai.Device(pipeline) as device:
# Output queue will be used to get the depth frames from the outputs defined above
depthQueue = device.getOutputQueue(name="depth", maxSize=4, blocking=False)
spatialCalcQueue = device.getOutputQueue(name="spatialData", maxSize=4, blocking=False)
spatialCalcConfigInQueue = device.getInputQueue("spatialCalcConfig")
color = (255, 255, 255)
print("Use WASD keys to move ROI!")
while True:
inDepth = depthQueue.get() # Blocking call, will wait until a new data has arrived
depthFrame = inDepth.getFrame() # depthFrame values are in millimeters
depth_downscaled = depthFrame[::4]
min_depth = np.percentile(depth_downscaled[depth_downscaled != 0], 1)
max_depth = np.percentile(depth_downscaled, 99)
depthFrameColor = np.interp(depthFrame, (min_depth, max_depth), (0, 255)).astype(np.uint8)
depthFrameColor = cv2.applyColorMap(depthFrameColor, cv2.COLORMAP_HOT)
spatialData = spatialCalcQueue.get().getSpatialLocations()
for depthData in spatialData:
roi = depthData.config.roi
roi = roi.denormalize(width=depthFrameColor.shape[1], height=depthFrameColor.shape[0])
xmin = int(roi.topLeft().x)
ymin = int(roi.topLeft().y)
xmax = int(roi.bottomRight().x)
ymax = int(roi.bottomRight().y)
depthMin = depthData.depthMin
depthMax = depthData.depthMax
depth_data=calculate_distance(depthData.spatialCoordinates.x,depthData.spatialCoordinates.y,depthData.spatialCoordinates.z)
print(depth_data)
fontType = cv2.FONT_HERSHEY_TRIPLEX
cv2.rectangle(depthFrameColor, (xmin, ymin), (xmax, ymax), color, 1)
cv2.putText(depthFrameColor, f"X: {int(depthData.spatialCoordinates.x)} mm", (xmin + 10, ymin + 20), fontType, 0.5, color)
cv2.putText(depthFrameColor, f"Y: {int(depthData.spatialCoordinates.y)} mm", (xmin + 10, ymin + 35), fontType, 0.5, color)
cv2.putText(depthFrameColor, f"Z: {int(depthData.spatialCoordinates.z)} mm", (xmin + 10, ymin + 50), fontType, 0.5, color)
cv2.putText(depthFrameColor, f"depth: {int(depth_data)} mm", (xmin + 10, ymin + 70), fontType, 0.5, color)
# Show the frame
cv2.imshow("depth", depthFrameColor)
key = cv2.waitKey(1)
if key == ord('q'):
break
elif key == ord('w'):
if topLeft.y - stepSize >= 0:
topLeft.y -= stepSize
bottomRight.y -= stepSize
newConfig = True
elif key == ord('a'):
if topLeft.x - stepSize >= 0:
topLeft.x -= stepSize
bottomRight.x -= stepSize
newConfig = True
elif key == ord('s'):
if bottomRight.y + stepSize <= 1:
topLeft.y += stepSize
bottomRight.y += stepSize
newConfig = True
elif key == ord('d'):
if bottomRight.x + stepSize <= 1:
topLeft.x += stepSize
bottomRight.x += stepSize
newConfig = True
elif key == ord('1'):
calculationAlgorithm = dai.SpatialLocationCalculatorAlgorithm.MEAN
print('Switching calculation algorithm to MEAN!')
newConfig = True
elif key == ord('2'):
calculationAlgorithm = dai.SpatialLocationCalculatorAlgorithm.MIN
print('Switching calculation algorithm to MIN!')
newConfig = True
elif key == ord('3'):
calculationAlgorithm = dai.SpatialLocationCalculatorAlgorithm.MAX
print('Switching calculation algorithm to MAX!')
newConfig = True
elif key == ord('4'):
calculationAlgorithm = dai.SpatialLocationCalculatorAlgorithm.MODE
print('Switching calculation algorithm to MODE!')
newConfig = True
elif key == ord('5'):
calculationAlgorithm = dai.SpatialLocationCalculatorAlgorithm.MEDIAN
print('Switching calculation algorithm to MEDIAN!')
newConfig = True
if newConfig:
config.roi = dai.Rect(topLeft, bottomRight)
config.calculationAlgorithm = calculationAlgorithm
cfg = dai.SpatialLocationCalculatorConfig()
cfg.addROI(config)
spatialCalcConfigInQueue.send(cfg)
newConfig = False_
Erol444
Hi, My inention is get the depth at every 10*10 pixel (or any legnth But we need the depth of the frame in all regions and we can filter the regions we dont want) in the frame and save them to a CSV with the pixel cordinates.
After setting the pipelines I have found this command: spatialData = spatialCalcQueue.get().getSpatialLocations()
The spaitial data have the spatial cordinates, so I can calculate the depth . But the when I print the spatial data
It gives the following output:
<depthai.SpatialLocations object at 0x000002023FC012F0> <depthai.SpatialLocations object at 0x000002023FC23EF0> <depthai.SpatialLocations object at 0x000002023FC012F0>
Well I can see that it is calculating the depth at differnt points in the frame,but I am not avle to undertand at whoch point the depth is calculated. I can use ROI , But I am able to get pnly depth at a region.
Is there a way where I can map the objects using the spaital data from spatialData = spatialCalcQueue.get().getSpatialLocations(). So I can convert them into pixel locations and save them into a csv,
Thank you