Geometric object models have been widely used for visual object tracking. In this contribution we present particle filter based object tracking with pose estimation using an appearance based lightfield object model. A light-field is an image-based object representation which can be used to render a photo realistic view of an arbitrarily shaped object from arbitrary viewpoints. It is shown how l...

Ming-Ching Chang1,2 [email protected] Honggang Qi1,3 [email protected] Xin Wang1 [email protected] Hong Cheng4 [email protected] Siwei Lyu1 [email protected] 1 Computer Science Department University at Albany, State University of New York Albany, USA 2 Computer Vision Lab GE Global Research Center Niskayuna, USA 3 University of Chinese Academy of Sciences Beijing, China 4 Center for Robotics Univers...

Estimation of 3D hand pose is useful in many gesture recognition applications, ranging from human-computer interaction to automated recognition of sign languages. In this paper, 3D hand pose estimation is treated as a database indexing problem. Given an input image of a hand, the most similar images in a large database of hand images are retrieved. The hand pose parameters of the retrieved imag...

Predicting accurately and in real-time 3D body joint positions from a depth image is the cornerstone for many safety, biomedical, and entertainment applications. Despite the high quality of the depth images, the accuracy of existing human pose estimation methods from single depth images remains insufficient for some applications. In order to enhance the accuracy, we suggest to leverage a rough ...

In this paper we approach the problem of head pose estimation by combining Multi-scale Gaussian Derivatives with Support Vector Machines. We evaluate the approach on the Pointing04 and CMU-PIE data sets and to estimate the pan and tilt of the head from facial images. We achieved a mean absolute error of 6.9 degrees for pan and 8.0 degrees for tilt on the Pointing04 data set.

This paper explores a method, first proposed by Wei and Chai [1], for estimating 3D human pose from several frames of uncalibrated 2D point correspondences containing projected body joint locations. In their work Wei and Chai boldly claimed that, through the introduction of rigid constraints to the torso and hip, camera scales, bone lengths and absolute depths could be estimated from a finite n...

In recent years, 6 Degrees Of Freedom (DOF) Pose Estimation and 3D Mapping is becoming more important not only in the robotics community for applications such as robot navigation but also in computer vision for the registration of large surfaces such as buildings and statues. In both situations, the robot/camera position and orientation must be estimated in order to be used for further alignmen...

We present a novel multi-person pose estimation framework, which extends pictorial structures (PS) to explicitly model interactions between people and to estimate their poses jointly. Interactions are modeled as occlusions between people. First, we propose an occlusion probability predictor, based on the location of persons automatically detected in the image, and incorporate the predictions as...

In this paper, we exploit the advantages of tensor representations and propose a Supervised Multilinear Learning Model for regression. The model is based on the Canonical (CANDECOMP)/Parallel Factors (PARAFAC) decomposition of tensors of multiple modes and allows the simultaneous projection of an input tensor to more than one discriminative directions along each mode. These projection weights a...

As software-intensive systems become more pervasive, more and more safety-critical systems are being developed. In this column, I will use the concept of a quality model to define safety as a quality factor. Thus, safety (like security and survivability) is a kind of defensibility, which is a kind of dependability, which is a kind of quality. Next, I discuss the structure of quality requirement...