Rotate camera by 90 DEGREES

Hi chandrian ,
I assume you are using something similar to Lossless Zooming. So first you would want to rotate the frame 90deg (so people are upright), do the face detection, crop the original (rotated) 4k image into 1080x1920 (as in the lossless zooming example), then rotate that to 1080P, which you can feed into the UVC node. Thougths?
Thanks ,Erik

Hi chandrian , by default you will want to rotate the images by 90deg. So you will likely want 4k, then rotate it by 90deg, then do inference, then crop, then rotate back by -90deg to get to 1920x1080.

And how does the script node work in terms of code path. I see a "while true" in the script with no breaks and a while true after the script. do they run in parallel?

I tried keeping the same dimensions as my working code and just flipping twice and I didnt not get an output stream and then I tried a zero degree turn twice and still no stream. Am I messing something up here:

        manipRgb = pipeline.createImageManip()
        rgbRr = dai.RotatedRect()
        rgbRr.center.x, rgbRr.center.y = cam.getPreviewWidth() // 2, cam.getPreviewHeight() // 2
        rgbRr.size.width, rgbRr.size.height = cam.getPreviewHeight(), cam.getPreviewWidth()
        rgbRr.angle = 0
        manipRgb.initialConfig.setCropRotatedRect(rgbRr, False)
        cam.preview.link(manipRgb.inputImage)

        manipRgb2 = pipeline.createImageManip()
        manipRgb2.initialConfig.setCropRotatedRect(rgbRr, False)
        manipRgb.out.link(manipRgb2.inputImage)

        # Create an UVC (USB Video Class) output node. It needs 1920x1080, NV12 input
        uvc = pipeline.createUVC()
        manipRgb2.out.link(uvc.input)

I actually cant get the cam.video to go through any manipulation node and into the UVC

I tried passing the cam.video into the manip node and into the uvc. Then I tried setting the preview to 1920x1080 (is that a possible size?) and feeding that into the manip node and into uvc and I still could not get that working either.

Hi chandrian ,
With the new depthai you can also use cam.video with ImageManip. I believe we plan to update the depthai uvc branch to latest, so you will be able to achieve this. Regarding the issue, please submit the full MRE.
Thanks, Erik

Hi chandrian , yes it should be possible.

Thanks for the reply Eric,

I have been trying to get this to work with no luck. It seems when I add multiple nodes, it does not function well. I am just feeding isp output into a mobilenet.

I tried just duplicating the resize image ImageManip above to prove functionality since I got the single resize working and I cannot get it to pass to the mobilnet and function.

This is using the UVC demo.

Thanks!

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

Hi chandrian ,
Please prepare the full MRE.
Thanks, Erik

erik
Hi Erik,

What do you mean when you say that? Do I post those things here in the forum post? Or do I submit something like a git issue?

Ah ok thanks. I tried to keep it minimal with the images above but maybe that was too much? Basically I fed the camera.isp output through two image crops to see if it would work and I got an error. Both image crops worked independently but it feeding through both nodes gave me an error.

what should the general approach be? This is the camera source flow through two nodes. The crop node works fine but I am not seeing the face recognition working when I add the rotation:

# 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)
camRgb.setPreviewSize(300, 300)

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)


crop_manip = 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 = 90
crop_manip.initialConfig.setCropRotatedRect(rgbRr, False)
camRgb.isp.link(crop_manip.inputImage)

crop_manip2 = pipeline.create(dai.node.ImageManip)
crop_manip2.initialConfig.setResize(300, 300)
crop_manip2.initialConfig.setFrameType(dai.ImgFrame.Type.BGR888p)
crop_manip.out.link(crop_manip2.inputImage)

crop_manip2.out.link(mobilenet.input)

Hi chandrian , I believe NNs should be run after rotating (90deg) the camera, as otherwise you will try to run inference on rotated frames (-90deg) which will have much worse performance?