Menu
I'm working on a project in which we have to launch several AR animations after detection of a toy's face. There are 36 toy's models and each toy must have a specific animation.
In other similar projects we have worked with common AR libraries but we never had to face the image recognition issue.
Do you know any library that could fit into that case?
After googling a lot I've found qualcomm Vuforia and it seems interesting. Have you used it or heard comments about it?
Thank you in advance.
928
Marker-based AR This type of AR, also known as recognition-based AR or image recognition, relies on identification of markers/user-defined images to function.
Image recognition is a marker-based AR technology. Think of a marker as an anchor that connects virtual content with the real-world. The marker can be an image, shape, or surface. Once the marker is detected by the application, the AR experience begins by placing preloaded digital content on top of it.
What Is AR Object Recognition? AR object recognition, also known as object detection, attaches a digital 3D model to a real-world object that learners can pick up and manipulate. Learners scan the real-world 3D object, then a simulated 3D model is attached to it.
The user must orientate the camera towards a precise marker to make the 3D image appear on the screen. The connection is created between the digital world and the real world by using a code hidden in an image, in a text or an object for example. These tools must be very distinctive and recognizable by the camera.
Qualcomm is a really good library, completely up-to-date. We have worked with it and results are difficult to improve with other libraries. The problem is that it is not free.
If you want a free library where you can build your own SDK then OpenCV is the choice. You have all the functions you need. You will need to spend some time in understanding it and coding, but for your application it is quite easy.
105
I would recommend OpenCV. Great open source library that is perfect for applications like this.
33
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With
