• DepthAI

  • ImageManip node rescale - moire

Hi, I've got a setup that involves a ColorCamera and an ImageManip node in a pipeline. The ColorCamera has a 12MP ISP output, which is then sent to the ImageManip node. I've noticed that when I resize the image to approximately FullHD (2:3 aspect ratio) using the .setResize method in the ImageManip node, the resulting image exhibits a pronounced moire effect. I'm curious to know what type of resizing method is being employed. Additionally, is there a filter or technique available in OAK-FFC-3P that can help mitigate this moire effect?

    Hi oto313
    The ImageManip node in the DepthAI platform uses bilinear/bicubic interpolation for downscaling images. This method is known to sometimes produce moiré patterns when resizing images with fine, high-frequency details.

    Currently, there is no built-in filter or technique in the OAK-FFC-3P platform specifically designed to mitigate the moiré effect. However, you can experiment with different image formats and configurations to potentially reduce the effect. For instance, using planar formats instead of interleaved images can be faster to process and might help in reducing the moiré effect.

    You can also try adjusting the ISP values such as sharpness, luma denoise, and chroma denoise in the ColorCamera node. These adjustments can sometimes improve image quality and potentially reduce the moiré effect. Here is an example of how to adjust these values:

    camRgb = pipeline.create(dai.node.ColorCamera)
camRgb.initialControl.setSharpness(0)     # range: 0..4, default: 1
camRgb.initialControl.setLumaDenoise(0)   # range: 0..4, default: 1
camRgb.initialControl.setChromaDenoise(4) # range: 0..4, default: 1

    Hope this helps.

    Thanks,
    Jaka