ii intelligent than conventional approaches as it is designed to select frames representing content of videos. We finally apply our methods to build a video logging system, which automatically records actions of gymnastic videos according to the actions displayed. Both systems perform well for a small set of motion categories. However they are object-dependent systems that need users to manuall...

We propose a new general approach to the problem of head pose estimation, based on semi-supervised low-dimensional topographic feature mapping. We show how several recently proposed nonlinear manifold learning methods can be applied in this general framework, and additionally, we present a new algorithm, IsoScale, which combines the best aspects of some of the other methods. The efficacy of the...

Head pose is a rich visual cue that finds great interest in the field of human robot interaction (HRI) and for video surveillance applications. Previous attempts at solving this problem have often proposed solutions formulated in a classification setting. Furthermore, strong assumptions on illumination and scale in an occlusion-free environment have usually been made. We propose a regression so...

We present a new system for the automatic determination of the position, size and pose of the head of a human gure in a camera image. The system is an extension of the well{known face recognition system 15] to pose estimation. The pose estimation system is characterized by a certain reliability and speed. We improve this performance and speed with the help of statistical estimation methods. In ...

We introduce a vision based, markerless upper body pose tracking approach that first tracks the 3D movements of extremities, including head and hands. Then based on the knowledge of upper body model, these extremity movements are used to predict the whole upper body motion as an inverse kinematics problem. The experimental validation showed the promise of applying this approach in several smart...

We introduce a vision based, markerless upper body pose tracking approach that first tracks the 3D movements of extremities, including head and hands. Then based on the knowledge of upper body model, these extremity movements are used to predict the whole upper body motion as an inverse kinematics problem. The experimental validation showed the promise of applying this approach in several smart...

Object Localization, Segmentation, Classification, and Pose Estimation in 3D Images Using Deep Learning

あらまし 本論文は,環境の全周囲情報を取得できるカメラシステム(全方位センサ)で得られた画像を用い てセンサの位置と姿勢をロバストに推定する新しい手法を提案する.本手法は,まず環境中のいくつかの参照点 において,全方位センサで得られた画像から全周囲エッジヒストグラムをあらかじめ計算しておく.センサの位 置・姿勢を推定する際,動的計画法 (DP)を 2 パス DPに拡張して現位置と参照点の全周囲エッジヒストグラム をマッチングし,各方位角におけるエッジのシフト量を求める.これらのシフト量は sin 曲線と同じ周期性をも ち,センサの回転はエッジの全体的なシフト量に,その移動方向は sin 曲線の 0 位相に対応する.本研究では, これらのエッジシフト量から全体のシフト量とその周期の 0 位相を独立に当てはめることによって,センサの移 動方向と回転角度を効率的に推定する.最後に,最も近い...

In this paper, we present a systematic method for pose estimation of such a generalized imaging device. We formulate it as a non-perspective n point (NPnP) problem. The case with exact solutions, n=3, is investigated comprehensively. Approximate solutions can also be found for n>3 with our approach in a least-squared-error manner. The proposed method can be used not only to perspective imaging ...