This paper aims to tackle the practically very challenging problem of efficient and accurate hand pose estimation from single depth images. A dedicated two-step regression forest pipeline is proposed: given an input hand depth image, step one involves mainly estimation of 3D location and in-plane rotation of the hand using a pixelwise regression forest. This is utilized in step two which delivers final hand estimation by a similar regression forest model based on the entire hand image patch. Moreover, our estimation is guided by internally executing a 3D hand kinematic chain model. For an unseen test image, the kinematic model parameters are estimated by a proposed dynamically weighted scheme. As a combined effect of these proposed building blocks, our approach is able to deliver more precise estimation of hand poses. In practice, our approach works at 15.6 frame-per-second (FPS) on an average laptop when implemented in CPU, which is further sped-up to 67.2 FPS when running on GPU. In addition, we introduce and make publicly available a data-glove annotated depth image dataset covering various hand shapes and gestures, which enables us conducting quantitative analyses on real-world hand images. The effectiveness of our approach is verified empirically on both synthetic and the annotated real-world datasets for hand pose estimation, as well as related applications including part-based labeling and gesture classification. In addition to empirical studies, the consistency property of our approach is also theoretically analyzed.

We propose the first algorithm to compute the 3D Delaunay triangulation (DT) on the GPU. Our algorithm uses massively parallel point insertion followed by bilateral flipping, a powerful local operation in computational geometry. Although a flipping algorithm is very amenable to parallel processing and has been employed to construct the 2D DT and the 3D convex hull on the GPU, to our knowledge there is no such successful attempt for constructing the 3D DT. This is because in 3D when many points are inserted in parallel, flipping gets stuck long before reaching the DT, and thus any further correction to obtain the DT is costly. In contrast, we show that by alternating between parallel point insertion and flipping, together with picking an appropriate point insertion order, one can still obtain a triangulation very close to Delaunay. We further propose an adaptive star splaying approach to subsequently transform this result into the 3D DT efficiently. In addition, we introduce several GPU speedup techniques for our implementation, which are also useful for general computational geometry algorithms. On the whole, our hybrid approach, with the GPU accelerating the main work of constructing a near-Delaunay structure and the CPU transforming that into the 3D DT, outperforms all existing sequential CPU algorithms by up to an order of magnitude, in both synthetic and real-world inputs. We also adapt our approach to the 2D DT problem and obtain similar speedup over the best sequential CPU algorithms, and up to 2 times over previous GPU algorithms.

No abstract

A novel algorithm is presented to compute the convex hull of a point set in ℝ 3 using the graphics processing unit (GPU). By exploiting the relationship between the Voronoi diagram and the convex hull, the algorithm derives the approximation of the convex hull from the former. The other extreme vertices of the convex hull are then found by using a two-round checking in the digital and the continuous space successively. The algorithm does not need explicit locking or any other concurrency control mechanism, thus it can maximize the parallelism available on the modern GPU. The implementation using the CUDA programming model on NVIDIA GPUs is exact and efficient. The experiments show that it is up to an order of magnitude faster than other sequential convex hull implementations running on the CPU for inputs of millions of points. The works demonstrate that the GPU can be used to solve nontrivial computational geometry problems with significant performance benefit.