This paper presents a pose estimation method based on a 3D camera⎯the SwissRanger SR4000. The proposed method estimates the camera’s ego-motion by using intensity and range data produced by the camera. It detects the SIFT (ScaleInvariant Feature Transform) features in one intensity image and match them to that in the next intensity image. The resulting 3D data point pairs are used to compute th...

Robust local image features have been used successfully in robot localization and camera pose estimation; region tracking using affine warps is considered state of the art also for many years. Although such correspondences provide a warp of the local image region and are quite powerful, in direct pose estimation they are so far only considered as points and therefore three of them are required ...

We propose three novel solvers for estimating the relative pose of a multi-camera system from affine correspondences (ACs). A new constraint is derived interpreting relationship ACs and generalized camera model. Using constraint, we demonstrate efficient two types motions. Considering that cameras undergo planar motion, minimal solution using single AC solver with to overcome degenerate case. A...

Egocentric vision has gained increasing popularity recently, opening new avenues for human-centric applications. However, the use of egocentric fisheye cameras allows wide angle coverage but image distortion is introduced along with strong human body self-occlusion imposing significant challenges in data processing and model reconstruction. Unlike previous work only leveraging synthetic trainin...

In this paper, we propose a framework for 3D human pose estimation using single 360° camera mounted on the user’s wrist. Perceiving with such simple setup has remarkable potential various applications (e.g., daily-living activity monitoring, motion analysis sports training). However, no existing method tackled task due to difficulty of estimating from image in which only part body...