augmented-reality

I'm trying to make my OpenCV-based fiducial marker detection more robust when the user moves the camera (phone) violently. Markers are ArTag-style with a Hamming code embedded within a black border. Borders are detected by thresholding the image, then looking for quads based on the found contours, then checking the internals of the quads. In general, decoding of the marker is fairly robust if the black border is recognized. I've tried the most obvious thing, which is downsampling the image twice, and also performing quad-detection on those levels. This helps with camera defocus on extreme

Does anyone know a way to take an image captured on the iphone's camera, and do some image processing (e.g. edge detection, skeletization), and then overlay parts of the processed image on the original image (e.g. only the highlighted edges). More generically how do I create a UImage with transparency (do I just scale the image and overlay it with an alpha value, does UIImage support transparency like gifs do). I'm thinking that you could combine a UIImagePickerController with a background thread that takes "screenshots" of the UIImagePickerController view and does image processing on it to

What are the next Android smartphones to be compatible with ARCore? Is there a known list of future compatible devices yet? Maybe a general project schedule? We are about to purchase some units for AR development assessments, at first we thought about trying one of the Tango devices out there (we already had a good experience with Tango), but our current bet is that the ARCore platform will beat it in terms of market share. Currently, the compatible devices are only: Google Pixel Samsung Galaxy S8 (the non-plus version) But obviously, we would prefer to choose from a wider variety (e.g. S8+,

I am using Vuforia SDK to do AR stuff on Android. For a project I want to track a ball. But with Vuforia this is not possible. So I tried to use OpenCV color detection to track a ball. I adapt this solution for my project. For now I can track and calculate center point(in screen coordinates) of the ball with OpenCV. How can I use OpenCV screen coordinates to do OpenGL AR stuff on Android. Where to start? I combined opencv tracking (using the Camshift algorithm) with OpenGL here: http://www.youtube.com/watch?v=yEioXZT-lv0 My first recommendation is not to try and tackle opengl libraries

I'm implementing live video capture through DirectShow for live processing and display. (Augmented Reality app). I can access the pixels easily enough, but it seems I can't get the SampleGrabber to provide RGB data. The device (an iSight -- running VC++ Express in VMWare) only reports MEDIASUBTYPE_YUY2. After extensive Googling, I still can't figure out whether DirectShow is supposed to provide built-in color space conversion for this sort of thing. Some sites report that there is no YUV<->RGB conversion built in, others report that you just have to call SetMediaType on your ISampleGrabber

I am building an Android application based on Augmented Reality. The main idea is when user opens up my application, by default device's camera starts in preview mode. Based on user's current GPS location and the direction in which user/camera is facing I want to calculate which are the set of latitudes and longitudes in the range? Following image explains my scenario very well. I have full set of latitudes and longitudes as drawn all black spots in the figure. Now suppose user is at the center of the circle. Also considering that he is viewing in North direction. If we consider an angle of 45