vision based Human Robot Interaction (HRI) in a crowded scene is a challenging research problem. The aim of this paper is to provide a reliable framework for simple gesture recognition for robotic navigation under par...
详细信息
This paper describes a method of building a medical ontology prototype in Chinese. During the procedure, we explored the following questions, which are crucial for the task of ontology engineering: (1) Are there some ...
详细信息
We show how to outsource data annotation to Amazon Mechanical Turk. Doing so has produced annotations in quite large numbers relatively cheaply. The quality is good, and can be checked and controlled. Annotations are ...
详细信息
We show how to outsource data annotation to Amazon Mechanical Turk. Doing so has produced annotations in quite large numbers relatively cheaply. The quality is good, and can be checked and controlled. Annotations are produced quickly. We describe results for several different annotation problems. We describe some strategies for determining when the task is well specified and properly priced.
This paper describes how the calculation of depth from stereo images was accelerated using a GPU. The Compute Unified Device Architecture (CUDA) from NVIDIA was employed in novel ways to compute depth using BT cost ma...
详细信息
This paper describes how the calculation of depth from stereo images was accelerated using a GPU. The Compute Unified Device Architecture (CUDA) from NVIDIA was employed in novel ways to compute depth using BT cost matching and the semi-global matching algorithm. The challenges of mapping a sequential algorithm to a massively parallel thread environment and performance optimization techniques are considered.
Nowadays, it is paramount to study and develop robust algorithms to detect the very existence of hidden messages in digital images. In this paper, we provide two data sets for the unseen challenge of the First ieee wo...
详细信息
Nowadays, it is paramount to study and develop robust algorithms to detect the very existence of hidden messages in digital images. In this paper, we provide two data sets for the unseen challenge of the First ieee workitorial on vision of the unseen (WVU). Example usage of the data sets is demonstrated with the steg detect analysis tool, with surprising results reported. Our objective is to challenge researchers to assess their Digital Image steg analysis state-of-the-art algorithms.
We present a system to capture high accuracy 3D models of faces by taking just one photo without the need of specialized hardware, just a consumer grade digital camera and beamer. The proposed 3D face scanner utilizes...
详细信息
We present a system to capture high accuracy 3D models of faces by taking just one photo without the need of specialized hardware, just a consumer grade digital camera and beamer. The proposed 3D face scanner utilizes structured light techniques: A colored pattern is projected into the face of interest while a photo is taken. Then, the 3D geometry is calculated based on the distortions of the pattern detected in the face. This is performed by triangulating the pattern found in the captured image with the projected one.
In this paper we deal with general camera models that allow to describe any kind of camera as a mapping between each pixel and the corresponding projection rays. This work is inspired by [19] and proposes a study of t...
详细信息
In this paper we deal with general camera models that allow to describe any kind of camera as a mapping between each pixel and the corresponding projection rays. This work is inspired by [19] and proposes a study of the multi-view geometry of such cameras and a new formulation of multi-view matching tensors working for projection rays crossing the same 3D line. We also delineate a method to estimate such tensors and recover the motion between the views.
We develop a topology-based method which can be used as a measure of the dissimilarity between shapes. For us, a shape is a point cloud dataset in Euclidean space. In the experiments described in this paper a shape co...
详细信息
We develop a topology-based method which can be used as a measure of the dissimilarity between shapes. For us, a shape is a point cloud dataset in Euclidean space. In the experiments described in this paper a shape comes with a particular choice of triangulation (mesh). However, the method can be applied to a more general situation when no particular triangulation is given. We test our method on a database of models achieving only a minor misclassification error.
In this work, we define two new and important qualities of features which expand upon the usual local feature information. Spatio-temporal consistency is a quality of a feature that quantifies how consistently a featu...
详细信息
In this work, we define two new and important qualities of features which expand upon the usual local feature information. Spatio-temporal consistency is a quality of a feature that quantifies how consistently a feature has been tracked in prior frames and how smooth its motion was over prior frames. Distributivity is a quality of a feature that quantifies physical distance (in number of pixels) from other features in the same frame.
Inferring the 3D spatial layout from a single 2D image is a fundamental visual task. We formulate it as a grouping problem where edges are grouped into lines, quadrilaterals, and finally depth-ordered planes. We demon...
详细信息
Inferring the 3D spatial layout from a single 2D image is a fundamental visual task. We formulate it as a grouping problem where edges are grouped into lines, quadrilaterals, and finally depth-ordered planes. We demonstrate that the 3D structure of planar objects in indoor scenes can be fast and accurately inferred without any learning or indexing.
暂无评论