ARScanner

iOS 11 Project using Vision and CoreML to recognize objects from the camera's video output

make VNCoreMLRequest every new videoframe (AVCaptureVideoDataOutputSampleBufferDelegate)
use VNSequenceRequestHandler
using MobileNet.mlmodel (https://arxiv.org/abs/1704.04861v1) for object classification

figure out the best way to recognize multiple objects ( a better model like https://pjreddie.com/darknet/yolo/ , or process frame as a grid of small images )
bounding boxes
object tracking

Name		Name	Last commit message	Last commit date
Latest commit History 10 Commits
ARScanner.xcodeproj		ARScanner.xcodeproj
ARScanner		ARScanner
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md