Augmented Reality System for Accelerometer Equipped Mobile Devices

摘要: In this paper, we present a novel approach for mobile augmented reality system. We estimate the 3D camera pose by detecting local invariant image features and combining them with camera’s accelerometer data. applied NELFD - Neuroevolved Local Feature Descriptor that encodes data around points of interest in using neural network evolved topology weights. For every frame, correspondence between 2D feature is calculated established based on additional sensor information. Generally systems are low performance equipped low-grade camera. Thus, due to estimation accuracy computational complexity our has been considered as new alternative augmenting process. Experimental evaluation proved method capable real-time tracking augmentation an unconstrained environment.