A Real use case of practical AR-AI couple - Size my luggage
summary
Android native app overlays a fixed-dimension 3D luggage model onto camera view and lets users drag and rotate it to check airline allowance; it uses ARCore for motion tracking/planes, Sceneform for renderables and nodes, and Firebase ML Kit object-detection to find a bag via bounding box + coarse classification. Detection runs on-device but the finer label lookup is remote; demo recognizes a backpack and places the model correctly. Limitations: no true 3D scan, Gradle conflicts in ARCore 1.9/1.10.
AI-written summary · about
chapters (6)
- 0:00Introduction to AR
- 6:32ARCore framework overview
- 14:36Building AR app with Sceneform
- 21:39Adding AI with Firebase ML Kit
- 32:31Live demo of luggage measurement
- 35:01Future improvements and Q&A
related talks
39mA Real use case of practical AR-AI couple: Size my luggage
37mExploring Augmented Reality with ARCore
41mFusing AI with AR: Custom Markers
44mAdd some reality to your app with ArCore
39mNow smile (also in 3D)! Exploring AR, ML and Camera related APIs on Android
31mRecreating That AR App with 2019 Technology
52mAugmented Reality: The Lion, The Witch and The Robot
44mNow smile (also in 3D)! Exploring AR, ML and Camera related APIs on Android