I am using Luxonis OAK-1 lite camera for my detection so I want to fully access it's encoding capabilities as well it's resolution capabilites so that I can clearer view of my frames in which I am doing my detection because my image is getting blurred out as it is detecting smaller objects .
Luxonis Camera feature extraction
Hi @AnamikaGupta
Have you checked the examples for encoding a 4K NN?
which example should I refer can you please tell in detail
Hi @AnamikaGupta
https://docs.luxonis.com/projects/api/en/latest/samples/MobileNet/rgb_mobilenet_4k/ this example shows how to show detections on a larger frame.
Thanks,
Jaka
I wanted to ask if set the senor resolution at THE_13_MP and sensor resolution at THE_4_K or at THE_1080_P what is the difference between them and is it possible that setting the sensor resolution at THE_13_MP is causing my images to look little blurred out.
Hi @AnamikaGupta
13MP is the highest resolution possible by IMX378. It also takes to longest time for this resolution to perform image acquisition. Process of creating other two is described here: https://docs.luxonis.com/projects/hardware/en/latest/pages/articles/sensors/imx378/#id1. If you pass the higher resolution through ISP the image will look better than to just select the lower resolution in the first place.
AnamikaGupta is it possible that setting the sensor resolution at THE_13_MP is causing my images to look little blurred out.
Technically no. Does this only happen at 12MP?
Thanks,
Jaka
- Edited
Will using 32MP camera be able to fix my issue for capturing high resolution images
jakaskerl Does this only happen at 12MP? No I am using 13MP camera which is Luxonis OAK-1 LITE
Hi @AnamikaGupta
My bad, read it as 12MP so I assumed you were using IMX378.
Still no, you shouldn't get blurry images on 13MP. Could you add a screenshot of the "blurriness"?
Thanks,
Jaka
- Edited
Below is the video for your reference. This is the kind of blurriness I am getting . I want the video frames to be high quality. So that each and every word should be clearly visible. And this video is also running fast forward in 30fps speed so how can I save the video in 25 fps .
Can I get reply on my above post I really need help
Hi @AnamikaGupta
Sorry for the late response.
I tested locally with this code:
#!/usr/bin/env python3
import cv2
import depthai as dai
# 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.CAM_A)
camRgb.setResolution(dai.ColorCameraProperties.SensorResolution.THE_13_MP)
xoutVideo.input.setBlocking(False)
xoutVideo.input.setQueueSize(1)
# Linking
camRgb.isp.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()
# 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
And had no trouble with blurriness. So perhaps your AF is off (placing the camera to close for the algo to work), or the sensor is bad. Could you check that please?
Thanks,
Jaka
Have you checked the video file which I have attached above that is the kind of blurriness I am getting.
Hi @AnamikaGupta
I have and it's hard to say what is causing it. Have you tried the AF issue?
Actually Can u tell what AF is
AnamikaGupta Autofocus. The IMX214 has two variants, AF and FF (fixed focus). If you have AF, this could mean the algorithm for focusing is not able to adjust lens position at the distance you are viewing from.
If it's FF, then this would mean the lens is off/badly placed. In this case we would replace the device.
You can check if the device is FF or AF if you run device.getConnectedCameraFeatures()
, then look for hasAutoFocus.
Thanks,
Jaka
Ok thank u