ARKit ARSCNView: use of ultra-wide camera or zoom? - ios

I have an ARKit ARSCNView providing an AR experience with the default rear-facing camera. I would like to use other cameras like the ultra-wide camera for that. If possible, it would be great to provide fluent zoom. Is it possible?
I did some research and found out one needs to loop over supported video formats of the AR configuration (e.g. ARWorldTrackingConfiguration.supportedVideoFormats). This gives an array of a few video formats with different fps values, ratios, ... But, there is always the AVCaptureDeviceTypeBuiltInWideAngleCamera. Ultra-wide or Tele does not seem to be included. How do we get the AR experience with an other camera than the default (wide) one?
Thanks in advance.

Related

Can we use vuforia for embedding markers into pre-recorded videos instead of a live camera feed?

I am currently working on a service to update the content of the video bases on the markers present in the video. I was curious if we can use Vuforia to achieve the same by providing the pre-recorded video as an input to Vuforia instead of the live camera feed from the mobile phone.
TLDR; This is not possible because replacing the camera is not a function that neither Vuforia or ARKit expose.
Aside from not exposing the camera both frameworks use a combination of camera input and sensor data (gyro, accelerometer, compass, altitude, etc) to calculate the camera/phone's position (translation/rotation) relative to the marker image.
The effect you are looking for is image tracking and rendering within a video feed. You should consider OpenCV for the feature point tracking, or some computer vision library. With regard to rendering there's three options SceneKit, Metal, or OpenGL. Following Apple's lead you could use SceneKit for the rendering, similar to how ARKit handles the sensor inputs and uses SceneKit for rendering. If you are ambitious and want to control the rendering as well you could use Metal or OpenGL.

Finding the horizon using ARKit?

I have an app using OpenCV to produce panoramas of outdoor scenes from multiple images (gebus I wish Apple would expose their pano feature!).
I need to extract the horizon. OCV does this, but is easily fooled in the samples I tried - it thought the roof was the horizon in one case.
So maybe there is a way to do this with ARKit instead? Essentially, I want to know where the "floor" is as the user moves the camera around to take images.
In ARKit there is the ARHitTestResult with various types that recognise planes (such as estimatedHorizontalPlane, existingPlane and existingPlaneUsingExtent. The upper edge of the plane would be your horizon.
You could try these and examine if the result is acceptable.

Reproduce the new scanning feature in iOS 11 Notes

Does anyone know how to reproduce the new Notes new scanning feature in iOS 11??
Is AVFoundation used for the camera?
How is the camera detecting the shape of the paper/document/card?
How do they place the overlay over in real time?
How does the camera know when to take the photo?
What's that animated overlay and how can we achieve this?
Does anyone know how to reproduce this?
Not exactly :P
Is AVFoundation used for the camera? Yes
How is the camera detecting the shape of the paper/document/card?
They are using the Vision Framework to do rectangle detection.
It's stated in this WWDC session by one of the demonstrators
How do they place the overlay over in real time?
You Should check out the above video for this as he talks about doing something similar in one of the demos
How does the camera know when to take the photo?
I'm not familiar with this app but it's surely triggered in the capture session, no?
Whats that animated overlay and how can we achieve this?
Not sure about this but I'd imagine it's some kind of CALayer with animation
Is Tesseract framework used for the image afterwards?
Isn't Tesseract OCR for text?
If you're looking for handwriting recognition, you might want to look for a MNIST model
Use Appleā€™s rectangle detection SDK, which provides an easy-to-use API that can identify rectangles in still images or video sequences in near-realtime. The algorithm works very well in simple scenes with a single prominent rectangle in a clean background, but is less accurate in more complicated scenes, such as capturing small receipts or business cards in cluttered backgrounds, which are essential use-cases for our scanning feature.
An image processor that identifies notable features (such as faces and barcodes) in a still image or video.
https://developer.apple.com/documentation/coreimage/cidetector

Is there front facing camera support with ARKit?

How can we access Front Facing Camera Images with ARCamera or ARSCNView and is it possible to record ARSCNView just like Camera Recording?
Regarding the front-facing camera: in short, no.
ARKit offers two basic kinds of AR experience:
World Tracking (ARWorldTrackingConfiguration), using the back-facing camera, where a user looks "through" the device at an augmented view of the world around them. (There's also AROrientationTrackingConfiguration, which is a reduced quality version of world tracking, so it still uses only the back-facing camera.)
Face Tracking (ARFaceTrackingConfiguration), supported only with the front-facing TrueDepth camera on iPhone X, where the user sees an augmented view of theirself in the front-facing camera view. (As #TawaNicolas notes, Apple has sample code here... which, until iPhone X actually becomes available, you can read but not run.)
In addition to the hardware requirement, face tracking and world tracking are mostly orthogonal feature sets. So even though there's a way to use the front facing camera (on iPhone X only), it doesn't give you an experience equivalent to what you get with the back facing camera in ARKit.
Regarding video recording in the AR experience: you can use ReplayKit in an ARKit app same as in any other app.
If you want to record just the camera feed, there isn't a high level API for that, but in theory you might have some success feeding the pixel buffers you get in each ARFrame to AVAssetWriter.
As far as I know, ARKit with Front Facing Camera is only supported for iPhone X.
Here's Apple's sample code regarding this topic.
If you want to access the UIKit or AVFoundation cameras, you still can, but separately from ARSCNView. E.g., I'm loading UIKit's UIImagePickerController from an IBAction and it is a little awkward to do so, but it works for my purposes (loading/creating image and video assets).

How do I generate stereo images from mono camera?

I have a stationary mono camera which captures a single image frame at some fps.
Assume the camera is not allowed to move,how do I generate a stereo image pair from the obtained single image frame? Is there any algorithms exists for this? If so, are they available in Open-CV?
To get a stereo image, you need a stereo camera, i.e. a camera with two calibrated lenses. So you cannot get a stereo image from a single camera with traditional techniques.
However, with the magic of deep learning, you can obtain the depth image from single camera.
And no, there's no builtin OpenCV function to do that.
The most common use of this kind of techniques is in 3D TVs, which often offer 2D-to-3D conversion, and thus mono to stereo conversion.
Various algorithms are used for this, you can look at this state of the art report.
There is also optical way for this.
If you can add binocular prisms/mirrors to your camera objective ... then you could obtain real stereoscopic image from single camera. That of coarse need access to the camera and setting up the optics. This also introduce some problems like wrong auto-focusing , need for image calibration, etc.
You can also merge Red/Cyan filtered images together to maintain the camera full resolution.
Here is a publication which might be helpful Stereo Panorama with a single Camera.
You might also want to have a look at the opencv camera calibration module and a look at this page.

Resources