Invariant-Based Augmented Reality on Mobile Phones

Abstract

<div><div>A calibration-free augmented reality based on affine invariant is firstly formulated by tensor method. This </div><div>approach does not use the calibration parameters of the camera and the 3D locations of the environment’s object, and can realize the augmentation of virtual objects. Meanwhile, a new approach to resolving occlusion problem in augmented reality is presented. Based on an arm-optimized implementation of the Scale Invariant Feature Transform (SIFT) algorithm developed by David Lowe and Random Sample Consensus (RANSAC) algorithm, the point correspondences in any two views are determined. According to the invariant for two views and these point correspondences, the occluding contours can be transferred to any views, so the occlusion is resolved. Some typical experiments show that the approach of invariant-based augmented reality is feasible on mobile phones. </div></div

Correspondência eficiente de descritores SIFT para construção de mapas densos de pontos homólogos em imagens de sensoriamento remoto

“…Por tais virtudes proliferaram as aplicações do SIFT na área de Visão Computacional, tais como localização e mapeamento por robôs (SLAM) (LEE e SONG, 2010), reconhecimento de gestos (MINHAS et al, 2010), reconhecimento facial (TAN et al, 2010), realidade aumentada (SHEN et al, 2010) e análise de imagens médicas (TOEWS et al, 2009).…”

Improved Vision-Based Algorithm for Unmanned Aerial Vehicles Autonomous Landing

“…The vision aided autonomous landing system will be achieved finally. In [6] they consider the problems of finding suitable but previously unmapped landing sites given general coordinates of the goal and planning collision free trajectories in real time to land After the appearance of SIFT researches have done extensive improvements and it is also used widely [12,13,14]. The SIFT descriptors encode the salient aspects of the image gradient in the feature point's neighborhood.…”