Optical flow based tracking and retexturing of garments

Abstract

In this paper, we present a method for tracking and retexturing of garments that exploits the entire image information using the optical flow constraint instead of working with distinct features. In a hierarchical framework we refine the motion model with every level. The motion model is used to regularize the optical flow field such that finding the best transformation amounts in minimizing an error function that can be solved in a least squares sense. Knowledge about the position and deformation of the garment in 2D allows us to erase the old texture and replace it by a new one with correct deformation and shading properties without 3D reconstruction. Additionally, it provides an estimation of the irradiance such that the new texture can be illuminated realistically.

Personalized augmented reality for anatomy education

“…Previous systems have augmented virtual shoes (Eisert et al, ; Luh et al, ), shirts (Ehara et al ) and knight's armor (Fiala, ) on to the user. To track the position of the user, these previous systems used tracking markers (Fiala, ; Eisert et al ., ; Luh et al ., ) or a tracking shirt with a rectangular highly‐textured region (Hilsmann et al ). For shoes, a vision‐based approach has been presented (Eisert et al ., ).…”

Reviews on detection technology of low-small-slow UAV

“…Optical Flow (OF) refers to the instantaneous velocity information of pixel movement corresponding to the observation imaging plane when the object is moving in space. It reflects the relationship between the gray level of the image in the time and the structure and movement of objects in the scene, which has a wide range of applications in image segmentation and target tracking [25,26] . Based on the analysis of OF model constrains, Yuan H W et al from Huazhong Institute of Electro-Optics proposes an algorithm based on hierarchical processing of optical flow estimation, in which by two frames difference selected candidate interested points and performed prediction and detection algorithm in each frames sequence to eliminate false targets.…”