Robust optical flow estimation via edge preserving filtering

It is known that optical flow estimation techniques suffer from the issues of ill-defined edges and boundaries of the moving objects. Traditional variational methods for optical flow estimation are not robust to handle these issues since the local filters in these methods do not hold the robustness near the edges. In this paper, we propose a non-local total variation NLTV-$L^1$ optical flow estimation method based on robust weighted guided filtering. Specifically, first, the robust weighted guided filtering objective function is proposed to preserve motion edges. The proposed objective function is based on the linear model which is computationally efficient and edge-preserving in complex natural scenarios. Second, the proposed weighted guided filtering objective function is incorporated into the non-local total variation NLTV-$L^1$ energy function. Finally, the novel NLTV-$L^1$ optical flow method is performed using the coarse-to-fine process. Additionally, we modify some state-of-the-art variational optical flow estimation methods by the robust weighted guided filtering objective function to verify the performance on Middlebury, MPI-Sintel, and Foggy Zurich sequences. Experimental results show that the proposed method can preserve edges and improve the accuracy of optical flow estimation compared with several state-of-the-art methods.     

基于线状特性的大数据地铁用户识别与定位方法

从MR原始数据特性出发研究数据结构与字段,采用基于线状特性分析MR大数据的地铁用户识别过滤方法和位置定位方法,该方法经过验证能够有效输出地铁用户数据并定位在地图上,解决人工地铁测试效率低且测试片面的问题,实现基于大数据的自动化地铁网络评估,提供海量的有效定位数据用于地铁评估与分析。     

A two-layered cross coupling control scheme for a three-dimensional motion control system

A two-layered modeling and compensation scheme is proposed to reduce the contouring error of a three-dimensional motion control system. In the proposed scheme, the contouring error model of the three-dimensional motion control system is divided into two layers: the top layer and the bottom layer. The proposed multi-layered structure of the contouring error model presents more flexibility in the control system design because the cross coupling controllers in different layers can be designed separately. In this paper, a nonlinear PI controller and a position error compensator are designed in the bottom layer in order to achieve high contouring accuracy in the XY plane, while a unilateral compensator is designed in the top layer to further reduce contouring error in the three dimensional space. Finally, experiments are performed to verify the performance of the proposed two-layered modeling and compensation scheme. Experiment results show that the designed two-layered cross coupling controller can obtain higher contouring accuracy than traditional cross coupling controller both in the XY plane and in the XYZ space.     

Content adaptive video denoising based on human visual perception

In this paper, we propose content adaptive denoising in highly corrupted videos based on human visual perception. We introduce the human visual perception in video denoising to achieve good performance. In general, smooth regions corrupted by noise are much more annoying to human observers than complex regions. Moreover, human eyes are more interested in complex regions with image details and more sensitive to luminance than chrominance. Based on the human visual perception, we perform perceptual video denoising to effectively preserve image details and remove annoying noise. To successfully remove noise and recover the image details, we extend nonlocal mean filtering to the spatiotemporal domain. With the guidance of content adaptive segmentation and motion detection, we conduct content adaptive filtering in the YUV color space to consider context in images and obtain perceptually pleasant results. Extensive experiments on various video sequences demonstrate that the proposed method reconstructs natural-looking results even in highly corrupted images and achieves good performance in terms of both visual quality and quantitative measures.     

Experimental optimization of power-function-shaped drive pulse for stick-slip piezo actuators

Motion of a stick-slip piezo actuator is generally controlled by the parameters related to its mechanical design and characteristics of the driving pulses applied to piezoceramic shear plates. The goal of the proposed optimization method is to find the driving pulse parameters leading to the fastest and the most reliable actuator operation. In the paper the method is tested on a rotary stick-slip piezo actuating system utilized in an atomic force microscope.The optimization is based on the measurement of the actuator response to driving pulses of different shapes and repetition frequencies at various load forces. To provide it, a computer controlled testing system generating the driving pulses, and detecting and recording the corresponding angular motion response of the actuator by a position sensitive photo detector (PSPD) in real time has been developed. To better understand and interpret the experimental results, supportive methods based on a simple analytical model and numerical simulations were used as well.In this way the shapes of the single driving pulses and values of the load force providing the biggest actuator steps were determined. Generally, the maximal steps were achieved for such a combination of the pulse shapes and load forces providing high velocities at the end of the sticking mode of the actuator motion and, at the same time, lower decelerations during the slipping mode.As for the multiple driving pulses, the pulse shapes and values of repetition frequency ensuring the sticking mode of the actuator motion during the pulse rise time together with the maximum average angular rotor velocity were specified. In this way the effective and stable operation conditions of the actuator were provided.In principle, the presented method can be applied for the testing and optimization of any linear or angular stick-slip actuator.     

Style-Controllable Speech-Driven Gesture Synthesis Using Normalising Flows

Automatic synthesis of realistic gestures promises to transform the fields of animation, avatars and communicative agents. In off-line applications, novel tools can alter the role of an animator to that of a director, who provides only high-level input for the desired animation; a learned network then translates these instructions into an appropriate sequence of body poses. In interactive scenarios, systems for generating natural animations on the fly are key to achieving believable and relatable characters. In this paper we address some of the core issues towards these ends. By adapting a deep learning-based motion synthesis method called MoGlow, we propose a new generative model for generating state-of-the-art realistic speech-driven gesticulation. Owing to the probabilistic nature of the approach, our model can produce a battery of different, yet plausible, gestures given the same input speech signal. Just like humans, this gives a rich natural variation of motion. We additionally demonstrate the ability to exert directorial control over the output style, such as gesture level, speed, symmetry and spacial extent. Such control can be leveraged to convey a desired character personality or mood. We achieve all this without any manual annotation of the data. User studies evaluating upper-body gesticulation confirm that the generated motions are natural and well match the input speech. Our method scores above all prior systems and baselines on these measures, and comes close to the ratings of the original recorded motions. We furthermore find that we can accurately control gesticulation styles without unnecessarily compromising perceived naturalness. Finally, we also demonstrate an application of the same method to full-body gesticulation, including the synthesis of stepping motion and stance.     

Intuitive Facial Animation Editing Based On A Generative RNN Framework

For the last decades, the concern of producing convincing facial animation has garnered great interest, that has only been accelerating with the recent explosion of 3D content in both entertainment and professional activities. The use of motion capture and retargeting has arguably become the dominant solution to address this demand. Yet, despite high level of quality and automation performance-based animation pipelines still require manual cleaning and editing to refine raw results, which is a time- and skill-demanding process. In this paper, we look to leverage machine learning to make facial animation editing faster and more accessible to non-experts. Inspired by recent image inpainting methods, we design a generative recurrent neural network that generates realistic motion into designated segments of an existing facial animation, optionally following user-provided guiding constraints. Our system handles different supervised or unsupervised editing scenarios such as motion filling during occlusions, expression corrections, semantic content modifications, and noise filtering. We demonstrate the usability of our system on several animation editing use cases.     

Ergonomic postural assessment using a new open-source human pose estimation technology (OpenPose)

Observational ergonomic postural assessment methods have been commonly used to evaluate the risks of musculoskeletal disorders. Researchers have proposed semi-automatic methods using Kinect, known for limitations with body occlusions and non-frontal tracking. Meanwhile, new human pose estimation methods have been actively developed, and a popular open-source technology is OpenPose. This study aims to propose the OpenPose-based system for computing joint angles and RULA/REBA scores and validate against the reference motion capture system, and compare its performance to the Kinect-based system. Recordings of 10 participants performing 12 experimental tasks under different conditions: with/without body occlusions and tracked from frontal/non-frontal views were analyzed. OpenPose showed good performance under all task conditions, whereas Kinect performed significantly worse than OpenPose especially at cases with body occlusions or non-frontal tracking. The findings suggested that OpenPose could be a promising technology to measure joint angles and conduct semi-automatic ergonomic postural assessments in the real workspace where the conditions are often non-ideal.     

Efficacy of utilizing a hybrid algorithmic method in enhancing the functionality of multi-instance multi-label radial basis function neural networks

The facts show that multi-instance multi-label (MIML) learning plays a pivotal role in Artificial Intelligence studies. Evidently, the MIML learning introduces a framework in which data is described by a bag of instances associated with a set of labels. In this framework, the modeling of the connection is the challenging problem for MIML. The RBF neural network can explain the complex relations between the instances and labels in the MIMLRBF. The parameters estimation of the RBF network is a difficult task. In this paper, the computational convergence and the modeling accuracy of the RBF network has been improved. The present study aimed to investigate the impact of a novel hybrid algorithm consisting of Gases Brownian Motion optimization (GBMO) algorithm and the gradient based fast converging parameter estimation method on multi-instance multi-label learning. In the current study, a hybrid algorithm was developed to estimate the RBF neural network parameters (the weights, widths and centers of the hidden units) simultaneously. The algorithm uses the robustness of the GBMO to search the parameter space and the efficiency of the gradient. For this purpose, two real-world MIML tasks and a Corel dataset were utilized within a two-step experimental design. In the first step, the GBMO algorithm was used to determine the widths and centers of the network nodes. In the second step, for each molecule with fixed inputs and number of hidden nodes, the parameters were optimized by a structured nonlinear parameter optimization method (SNPOM). The findings demonstrated the superior performance of the hybrid algorithmic method. Additionally, the results for training and testing the dataset revealed that the hybrid method enhances RBF network learning more efficiently in comparison with other conventional RBF approaches. The results obtain better modeling accuracy than some other algorithms.     

铸件多功能作业机器人多臂协调轨迹规划与仿真

以铸件多功能作业机器人的工作臂为研究对象,采用笛卡尔空间变量法对机器人铸件搬运过程进行轨迹规划。结合多臂协调的运动约束条件以及伪逆法,对机器人的4个工作臂关节运动进行优化,得到多机械臂协调运动的关节位置和速度变化曲线。由MATLAB软件仿真得到的运动参数曲线可知,算法优化后得到的运动轨迹均能保持连续、平滑,有利于实现对机器人的精准控制。利用机械臂正运动学方程得到了机械臂末端执行器的轨迹曲线,曲线满足铸件搬运的要求,验证了算法的正确性。