安卓平台上的医用图像信息采集系统的开发设计

为了探讨在安卓平台上构建医用图像采集系统的开发个案,分析通过以智能手机、平板电脑为核心安卓设备通过拍照获得化验单数据后进行文本识别并提交智慧医疗系统的解决方案。本文首先通过二值化算法形成低阈值图像数据,使用卷积神经元网络算法对文本进行逐一识别,使用K-means算法对识别后的单字文本进行字段记录值的整合并形成元数据库服务于其他智慧医疗系统模块。在使用9000组数据对神经元网络进行前期训练的前提下,该系统的识别准确率达到了99.5%以上。本系统具有一定的可行性,对未来智慧医疗的系统开发有实践意义。     

Experimental study on free and submerged multi-jets

The flow characteristics of the hydraulic jump due to parallel jets are different from the classical jump emerging from a single gate. Due to the highly complex flow field at the downstream pool, deciding about the tailwater measuring location is a challenging issue affecting the flow measuring accuracy. Experiments are conducted herein, on different parallel jets’ configurations for both free and submerged flow conditions. To quantify the flow uniformity, for any downstream cross section, the associated momentum correction factors, β₂, were estimated for the free-flow condition. It is found that β₂-values depend significantly on the measuring location, and consequently the available conjugated depths relationship results in poor estimation when measuring location moves downstream. Employing Buckingham analysis, a general formula is proposed to calculate the momentum correction factors associated with the free hydraulic jump at different downstream measuring locations. The experimental results of this study indicated that such a formula enhances distinguishing between free and submerged flow conditions of the gates installed in parallel. Finally, a dimensionless stage-discharge formula is presented to predict the submerged flow rate through parallel gates of different gate openings and widths.     

A Practical Method for Animating Anisotropic Elastoplastic Materials

This paper introduces a simple method for simulating highly anisotropic elastoplastic material behaviors like the dissolution of fibrous phenomena (splintering wood, shredding bales of hay) and materials composed of large numbers of irregularly-shaped bodies (piles of twigs, pencils, or cards). We introduce a simple transformation of the anisotropic problem into an equivalent isotropic one, and we solve this new “fictitious” isotropic problem using an existing simulator based on the material point method. Our approach results in minimal changes to existing simulators, and it allows us to re-use popular isotropic plasticity models like the Drucker-Prager yield criterion instead of inventing new anisotropic plasticity models for every phenomenon we wish to simulate.     

增强现实场景下移动边缘计算资源分配优化方法

针对高速数据传输及计算所带来时延和终端设备能耗问题，提出了一种在上行链路采用等功率分配的传输方案。首先，依据增强现实（AR）业务的协作属性建立了针对AR特性的系统模型；其次，详细分析了系统帧结构，建立以最小化系统消耗总能量为优化目标的约束条件；最后，在保障延迟和功耗满足约束的条件下，建立了基于凸优化的移动边缘计算（MEC）资源优化求解数学模型，从而获得最优的通信和计算资源分配方案。与独立传输相比，该方案在最大延迟时间分别为0.1 s和0.15 s时的总能耗降幅均为14.6%。仿真结果表明，在相同条件下，与基于用户独立传输的优化方案相比，考虑用户间协作传输的等功率MEC优化方案能显著减少系统消耗的总能量。     

ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills

Humans are highly adept at walking in environments with foot placement constraints, including stepping-stone scenarios where footstep locations are fully constrained. Finding good solutions to stepping-stone locomotion is a longstanding and fundamental challenge for animation and robotics. We present fully learned solutions to this difficult problem using reinforcement learning. We demonstrate the importance of a curriculum for efficient learning and evaluate four possible curriculum choices compared to a non-curriculum baseline. Results are presented for a simulated humanoid, a realistic bipedal robot simulation and a monster character, in each case producing robust, plausible motions for challenging stepping stone sequences and terrains.     

Persistence Analysis of Multi-scale Planar Structure Graph in Point Clouds

Modern acquisition techniques generate detailed point clouds that sample complex geometries. For instance, we are able to produce millimeter-scale acquisition of whole buildings. Processing and exploring geometrical information within such point clouds requires scalability, robustness to acquisition defects and the ability to model shapes at different scales. In this work, we propose a new representation that enriches point clouds with a multi-scale planar structure graph. We define the graph nodes as regions computed with planar segmentations at increasing scales and the graph edges connect regions that are similar across scales. Connected components of the graph define the planar structures present in the point cloud within a scale interval. For instance, with this information, any point is associated to one or several planar structures existing at different scales. We then use topological data analysis to filter the graph and provide the most prominent planar structures. Our representation naturally encodes a large range of information. We show how to efficiently extract geometrical details (e.g. tiles of a roof), arrangements of simple shapes (e.g. steps and mean ramp of a staircase), and large-scale planar proxies (e.g. walls of a building) and present several interactive tools to visualize, select and reconstruct planar primitives directly from raw point clouds. The effectiveness of our approach is demonstrated by an extensive evaluation on a variety of input data, as well as by comparing against state-of-the-art techniques and by showing applications to polygonal mesh reconstruction.     

Particle-based Liquid Control using Animation Templates

It is notoriously difficult for artists to control liquids while generating plausible animations. We introduce a new liquid control tool that allows users to load, transform, and apply precomputed liquid simulation templates in a scene in order to control a particle-based simulation. Each template instance generates control forces that drive the global simulated liquid to locally reproduce the templated liquid behavior. Our system is augmented with a variable proportion of temporary particles to help efficiently reproduce the templated liquid density, with fewer requirements on the surrounding environment. The resulting control strategy adds only a small computational overhead, leading to quick visual feedback for resolutions allowing interactive simulation. We demonstrate the robustness and ease of use of our method on various examples in 2D and 3D.     

Parallel spatial-temporal convolutional neural networks for anomaly detection and location in crowded scenes

Anomaly detection and location in crowded scenes have attracted a lot of attention in computer vision research community recently due to the increased applications of intelligent surveillance improve security in public. We propose a novel parallel spatial-temporal convolution neural networks model to detect and localize the abnormal behavior in video surveillance. Our approach contains two main steps. Firstly, considering the typical position of camera and the large number of background information, we introduce a novel spatial-temporal cuboid of interest detection method with varied-size cell structure and optical flow algorithm. Then, we use the parallel 3D convolution neural networks to describe the same behavior in different temporal-lengths. That step ensures that the most of behavior information in cuboids could be captured, also insures the reduction of information unrelated to the major behavior. The evaluation results on benchmark datasets show the superiority of our method compared to the state-of-the-art methods.     

On Demand Solid Texture Synthesis Using Deep 3D Networks

This paper describes a novel approach for on demand volumetric texture synthesis based on a deep learning framework that allows for the generation of high-quality three-dimensional (3D) data at interactive rates. Based on a few example images of textures, a generative network is trained to synthesize coherent portions of solid textures of arbitrary sizes that reproduce the visual characteristics of the examples along some directions. To cope with memory limitations and computation complexity that are inherent to both high resolution and 3D processing on the GPU, only 2D textures referred to as ‘slices’ are generated during the training stage. These synthetic textures are compared to exemplar images via a perceptual loss function based on a pre-trained deep network. The proposed network is very light (less than 100k parameters), therefore it only requires sustainable training (i.e. few hours) and is capable of very fast generation (around a second for 256³ voxels) on a single GPU. Integrated with a spatially seeded pseudo-random number generator (PRNG) the proposed generator network directly returns a color value given a set of 3D coordinates. The synthesized volumes have good visual results that are at least equivalent to the state-of-the-art patch-based approaches. They are naturally seamlessly tileable and can be fully generated in parallel.     

Comments on “Study and application of discharge calibration for submerged radial gates” by Guo X., Guo Y., Wang T., Fu H., Li J. Flow Meas. Instrum. 78 (2021) 101912, https://doi.org/10.1016/j.flowmeasinst.2021.101912

This paper discusses the capability of Guo et al.'s (2021) equations to determine the discharge of radial gates under submerged flow conditions. It was concluded that Guo et al.'s (2021) equations are associated with error reduction compared to the Incomplete Self-Similarity (ISS) theory and the calibration method. However, it does not have a significant advantage over Energy-Momentum (E-M) approach. Employing E-M principles, new equations were proposed to determine the discharge of radial gates, which has some advantages compared to Guo et al. (2021), such as (1) error reduction under partially and fully submerged flow conditions, (2) least dependence on the empirical constants, (3) uniformity of form over the entire submerged condition, and (4) no need to classify the submerged flow. Field calibration showed that the proposed equations in the present study for a single gate predict the discharge of parallel radial gates with a mean absolute error of less than 4.5% subject to the submerged operation of all open gates.