I made a AR camera application that can detect an object via camera and display its name and related words in augmented reality.
Many AR applications displays object or image in the space, like Google’s AR search.
Although there are a plenty of AR applications that shows visual effect via camera, I see a few that deals with natural language. I agree that these applications are brilliant, while I also believe in power of words, that people recognize the world with language and the AR is one representation of the world. …
Augmented Reality allows us to programmatically work with 3 dimensional world using camera-equipped device. ARCore is one of the libraries for augmented reality that provides simple and powerful API’s to make a new application for Android, iOS, Unity and Unreal Engine. You may find many sample applications in the ARCore website.
Common thing you do with augmented reality application is using camera as interface to change the scene you can see. You may easily think of it to use for games, but I am expecting more possibilities to AR to attract real world.
Augmented reality technology allows us to…
Finally I am ready to play with ARCore. ARCore is a powerful library to implement augmented reality with various platforms: Android, iOS, Unreal and Unity. It provides API’s to understand the real world with camera interface including motion tracking, light estimation and object placement.
While there are many examples, I would like to combine segmentation to place a duplication object…
Just detecting and classifying can be done by human beings, but segmenting realtime image for those you can see is pretty difficult. In this post, I am going through executing realtime segmentation with Android CameraX and Firebase ML kit.
I am going to use the starter model of deeplab version3, provided free by Google. Cool thing about the segmentation model is that it classifies objects in the image pixel by pixel, which sums up to be able to draw segments of object in the image.
In the previous post, I have gone through running custom image classification model on Firebase ML kit. It was just classifying the whole camera screen. In the real world, the camera takes a bunch of noises in one image. On the other hand, the object you want to focus on is only a portion of the whole image. In order to focus on the object, we use object detection.
While there are plenty of methods to utilize object detection, Firebase ML kit provides a pretrained one ready…
Today, I would like to introduce combination of Tensorflow Lite, Firebase ML kit, ARCore on Android with CameraX.
Using smartphone camera as a visual device to interact with the real world has becoming ever popular with utilization of deep learning and augmented reality as a tool. There is no doubt that Tensorflow Lite, the Tensorflow implementation for smartphone devices, including Android and iOS, is one of the most practical library to run inference in the devices. Running inference int the device, however, is not only thing you have to deal with for the device-side inference. You at least have to…
technical engineer of cloud, container, Kubernetes, ML, and AR.