In this paper we present a method for 3D shape classification and pose estimation. Our approach is related to the recently popular adaptations of Implicit Shape Models to 3D data, but differs in some key aspects. We propose to omit the quantization of feature descriptors in favor of a better descriptiveness of training data. Additionally, a continuous voting space, in contrast to discrete Hough...

In markerless model-based tracking approaches image features as points or straight lines are used to estimate the pose. We introduce an analysis of parametrizations of the pose data as well as of error measurements between 2D image features and 3D model data. Further, we give a review of critical geometrical configurations as they can appear on the input data. From these results the best parame...

Tree-structured models have been widely used for human pose estimation, in either 2D or 3D. While such models allow efficient learning and inference, they fail to capture additional dependencies between body parts, other than kinematic constraints between connected parts. In this paper, we consider the use of multiple tree models, rather than a single tree model for human pose estimation. Our m...

We present a new on-line scheme for the recognition and pose estimation of a large isolated 3-D object, which may not entirely fit in a camera’s field of view. We do not assume any knowledge of the internal parameters of the camera, or their constancy. We use a probabilistic reasoning framework for recognition and next view planning. We show results of successful recognition and pose estimation...

In this paper, we propose an embedding method to seek an optimal low-dimensional manifold describing the intrinsical pose variations and to provide an identity-independent head pose estimator. In order to handle the appearance variations caused by identity, we use a learned Mahalanobis distance to seek optimal subjects with similar manifold to construct the embedding. Then, we propose a new smo...

Model-based approaches to 3D hand tracking have been shown to perform well in a wide range of scenarios. However, they require initialisation and cannot recover easily from tracking failures that occur due to fast hand motions. Data-driven approaches, on the other hand, can quickly deliver a solution, but the results often suffer from lower accuracy or missing anatomical validity compared to th...

In this paper we propose a new local learning algorithm for appearance-based object pose estimation, called Locally Linearly Embedded Regression (LLER). LLER uses a constrained version of Locally Linear Embedding (LLE) to simultaneously embed into an intermediate low-dimensional space the training images, the query image and a grid of pose parameters. A linear map is learned between the points ...

This paper proposes a pipeline for lying pose recognition from single images, which is designed for health-care robots to find fallen people. We firstly detect object bounding boxes by a mixture of viewpoint-specific part based model detectors and later estimate a detailed configuration of body parts on the detected regions by a finer tree-structured model. Moreover, we exploit the information ...

Vision transformer architectures have been demonstrated to work very effectively for image classification tasks. Efforts solve more challenging vision tasks with transformers rely on convolutional backbones feature extraction. In this paper we investigate the use of a pure architecture (i.e., one no CNN backbone) problem 2D body pose estimation. We evaluate two ViT COCO dataset. demonstrate tha...