Teej's profile - activity

I'm trying to port a rectangle detection project onto iOS, and I've noticed that the CvVideoCamera takes a very long time to focus, and is generally blurry (which negatively affects the detection). Is there any way around this? How can I, for example, obtain camera inputs that are as clear as the native iOS camera application?

If there are also ways to mitigate the loss of accuracy (through image sharpening maybe) that would not affect the real-time nature of the app, that would also be great advice. Any help is appreciated!

I'm trying to get an OpenCV project up and running on iOS, and have recreated the video capture example found here: https://github.com/Itseez/opencv_for_...

I've made sure all the frameworks were imported, and modified the building settings accordingly. However, no matter what I do, no video is ever displayed. How can I fix this?

iOS version: 10.3

Xcode version: 8.3

OpenCV version: 3.2.0

I'm trying to get an OpenCV project up and running on iOS, and have recreated the video capture example found here: https://github.com/Itseez/opencv_for_...

I've made sure all the frameworks were imported, and modified the building settings accordingly. However, no matter what I do, no video is ever displayed. How can I fix this?

iOS version: 10.3 Xcode version: 8.3

How do I best implement an AR tool that would allow me to display pictures onto a sized frame on the wall? I'm currently using Canny edge detection and finding a shape with 4 corners, then warping the perspective of an input image for each frame of a video.

Is there a better way to do this? I've experimented with Aruco markers but would prefer a way that does not require camera calibration, and there is no need for pose estimation as well.