A Model-Based System for Real-Time Articulated Hand Tracking Using a Simple Data Glove and a Depth Camera

Tracking detailed hand motion is a fundamental research topic in the area of human-computer interaction (HCI) and has been widely studied for decades. Existing solutions with single-model inputs either require tedious calibration, are expensive or lack sufficient robustness and accuracy due to occlusions. In this study, we present a real-time system to reconstruct the exact hand motion by iteratively fitting a triangular mesh model to the absolute measurement of hand from a depth camera under the robust restriction of a simple data glove. We redefine and simplify the function of the data glove to lighten its limitations, i.e., tedious calibration, cumbersome equipment, and hampering movement and keep our system lightweight. For accurate hand tracking, we introduce a new set of degrees of freedom (DoFs), a shape adjustment term for personalizing the triangular mesh model, and an adaptive collision term to prevent self-intersection. For efficiency, we extract a strong pose-space prior to the data glove to narrow the pose searching space. We also present a simplified approach for computing tracking correspondences without the loss of accuracy to reduce computation cost. Quantitative experiments show the comparable or increased accuracy of our system over the state-of-the-art with about 40% improvement in robustness. Besides, our system runs independent of Graphic Processing Unit (GPU) and reaches 40 frames per second (FPS) at about 25% Central Processing Unit (CPU) usage.

Tool Path Generation for Local Interference Region Machining of Triangular Mesh Model

In this paper, a novel method is proposed for identifying local interference region and generation iso-scallop tool paths based on triangular mesh model for 3-axis ball-end milling. With our method, the principal curvatures and directions at vertices have been computed first and a recursive merging algorithm for segmenting local interference regions is developed. In addition, a method of generation tool path with constant scallop height for local interference region is also presented. Some illustrative examples are tested that indicate the feasibility and availability.

A Feature-Preserving Hole Filling Algorithm in Reverse Engineering

To get complete and accurate triangular mesh model in reverse engineering, the hole-filling operation is indispensable. This paper presents a new feature preserving hole-filling algorithm based on the feature line extraction. Firstly, the hole and its neighborhood were obtained. Then, the feature lines in the hole region were extracted which were used to divided the hole to several single surface holes. To each hole, triangulation and subdivision were performed. Finally, the new added vertices in the hole were moved to the underlying surface which was approximated by the hole neighborhood. The experimental results demonstrate that our mesh hole-filling algorithm can effectively recover the original shape of the hole.

Determination of Geometric Shape of the Molecular Surface

A new type of compound can be got by docking the active site of acceptor and the active site of ligand. In general, active sites of the molecule are often located in the concave-convex regions. In this paper, we propose a new method which combines discrete Gaussian curvature with normal to determine geometric shape of the molecular surface of protein. Firstly, we compute the normal and Gaussian curvature of all vertices of the triangular mesh model that present a molecular surface. Then we choose a certain number of vertices ac-cording to Gaussian curvature of each vertex on the mesh. By doing so, the shape of the region consisting of those vertices is determined, that is the region is concave or convex.