为减小新冠疫情感染风险,进一步实现医疗自动化,本文针对基于OpenMV模块的医疗收集机器人的机械臂运动控制进行了研究.结合已有的硬件条件,通过在运动空间中的识别、定位,采用增量法对传统机械臂控制算法进行了改进.实验结果表明,改进的机械臂算法在控制稳定性、抓取正确率方面均有较好的表现,能有效促进医疗物品收集装置的智能化、自动化.

为了减轻医护人员的工作压力,降低传染风险,并使痰盂收集自动化,本文提出了一种基于视觉导航技术控制收集小车的方法.首先通过OpenMV视觉传感器搜寻并识别空间中的Apriltag标识,读取相应位置信息后,视觉传感器通过串口与收集小车的主控制器进行通信,使收集小车按控制要求自动进行路径规划,从而对目标痰盂进行识别、抓取、转运等操作.经过在实验环境下的运行与测试,该收集小车运行稳定,较好地满足了自动收集痰盂的任务.

为了使羽毛球爱好者能快速了解自身身体素质与击球特点,基于机器学习方法,设计了一款可以识别挥拍动作并分析行为模式的智能羽毛球拍,给出了系统的硬件与软件整体框架.通过对智能羽毛球拍的动作识别准确度进行多方位测试与分析,验证了其具有较好的准确性与易用性.

Sensor management in multi-object stochastic systems is a theoretically and computationally challenging problem. This paper presents a novel approach to the multi-target multi-sensor control problem within the partially observed Markov decision process (POMDP) framework. We model the multi-object state as a labeled multi-Bernoulli random finite set (RFS), and use the labeled multi-Bernoulli filter in conjunction with minimizing a task-driven control objective function: posterior expected error of cardinality and state (PEECS). A major contribution is a guided search for multi-dimensional optimization in the multi-sensor control command space, using coordinate descent method. In conjunction with the Generalized Covariance Intersection method for multi-sensor fusion, a fast multi-sensor algorithm is achieved. Numerical studies are presented in several scenarios where numerous controllable (mobile) sensors track multiple moving targets with different levels of observability. The results show that our method works significantly faster than the approach taken by a state of art method, with similar tracking errors.

This paper presents a novel method for track-to-track fusion to integrate multiple-view sensor data in a centralized sensor network. The proposed method overcomes the drawbacks of the commonly used Generalized Covariance Intersection method, which considers constant weights allocated for sensors. We introduce an intuitive approach to automatically tune the weights in the Generalized Covariance Intersection method based on the amount of information carried by the posteriors that are locally computed from measurements acquired at each sensor node. To quantify information content, Cauchy-Schwarz divergence is used. Our solution is particularly formulated for sensor networks where the update step of a Labeled Multi-Bernoulli filter is running locally at each node. We will show that with that type of filter, the weight associated with each sensor node can be separately adapted for each Bernoulli component of the filter. The results of numerical experiments show that our proposed method can successfully integrate information provided by multiple sensors with different fields of view. In such scenarios, our method significantly outperforms the common approach of using Generalized Covariance Intersection method with constant weights, in terms of inclusion of all existing objects and tracking accuracy. (C) 2018 Elsevier B.V. All rights reserved.

A constrained sensor control method is presented for multiobject tracking using labeled multi-Bernoulli filters. The proposed framework is based on a novel approximation of theCauchySchwarz divergence between the labeled multi-Bernoulli prior and posterior densities, which does not need Monte Carlo sampling of random sets in the multiobject space. The void probability functional is also formulated for labeled multi-Bernoulli distributions and used within our proposed method to form a constrained sensor control solution. Numerical studies demonstrate that reasonably acceptablemovements are decided for the controlled sensor by our sensor control method, with the advantage that the void probability constraint is formally considered as part of the sensor control optimization algorithm.

This paper presents a novel statistical information fusion method to integrate multiple-view sensor data in multi-object tracking applications. The proposed method overcomes the drawbacks of the commonly used Generalized Covariance Intersection method, which considers constant weights allocated for sensors. Our method is based on enhancing the Generalized Covariance Intersection with adaptive weights that are automatically tuned based on the amount of information carried by the measurements from each sensor. To quantify information content, Cauchy-Schwarz divergence is used. Another distinguished characteristic of our method lies in the usage of the Labeled Multi-Bernoulli filter for multi-object tracking, in which the weight of each sensor can be separately adapted for each Bernoulli component of the filter. The results of numerical experiments show that our proposed method can successfully integrate information provided by multiple sensors with different fields of view. In such scenarios, our method significantly outperforms the state of art in terms of inclusion of all existing objects and tracking accuracy.

由于载体姿态的变化和海浪等因素的影响,海洋浮标成像系统所获得的图像不稳定或者模糊,如何改变现状是人们不断探讨和研究的课题.结合陀螺传感器MPU6050和磁力计HMC5883L设计一套基于ARM11的云台稳定控制系统,通过S3C6410的I2C接口读取MPU6050和HMC5883L的数据,采用卡尔曼滤波算法对其进行处理,然后解算出载体的航向角和俯仰角,实现云台摄像机姿态的反向调整.当云台摄像机与PC相连时,对UleadVideoStudio软件进行简单的配置,便可看到云台摄像机所拍摄的视频信息.实验结果表明:云台将以水平速度280°/s、垂直速度100°/s完成反向偏转,最长反馈调整时间为0.38s,满足工程上的应用需求;该系统电路结构简单、成本低、可视化且稳定,可以移植到无人机及船舶监控等场合,具有一定的实用性.

The probability hypothesis density (PHD) filter is a practical alternative to the optimal Bayesian multi-target filter based on finite set statistics. This paper presents two extensions implementation to nonlinear models in PHD filters, namely the extended Kalman filter (EKF) and the unscented Kalman filter (UKF), and discusses their advantage and disadvantage. The simulation scenarios with different target numbers are presented while OSPA distance, clutter parameters and execute time comparisons are also analyzed as a guide for further application research.

Badminton is a kind of mass sports for all ages, for it is easy to grasp. In order to enable the junior badminton enthusiasts to master the correct footwork quickly, this paper designed a kind of badminton footwork training device combined with voice and infrared remote control. The system's hardware and software framework and some key procedures are given. A multi-faceted test and analysis verify that the footwork training device has a good performance with stability and practicability.

For the swing problem of ocean buoy under billowy environment, which is hard to obtain clear and stable image, this paper designed a kind of PTZ stabilization system platform based on gyroscope and electronic compass module. During the angle data collection process, we adapt accelerometer trigonometric function method to overcome not only the low accuracy problem with a single sensor, but also accumulative error to a large extent. With the vertical direction gyroscope, the experiment results show that the angle errors of proposed accelerometer trigonometric function method are within ±1 degree which has a better practicality.

针对海洋浮标上成像系统受其载体姿态的变化和海浪等因素的影响导致获得的图像信息不稳定或模糊这一现状,设计一套基于ARM11的云台稳定控制系统,即利用陀螺传感器MPU6050和磁力计HMC5883l对海洋浮标的运动姿态进行感应,通过姿态解算单元计算出载体的航向角和俯仰角,实现云台摄像机姿态的反向调整,从而使得云台摄像机输出稳定的图像。在姿态解算过程中将四元数和卡尔曼滤波结合起来对陀螺仪进行补偿,并利用基于椭球拟合的方法对磁力计进行补偿。实验结果表明该算法在静止情况下,俯仰角精度±0.1o,航向角±0.2o。

介绍了一种从高压输电线上进行取电的电源方案,通过互感自取电直接从输电线上获得电能.凭借将锂电池与超级电容进行联合供电的充放电技术,电源设计部分成功解决了夜间母线小电流状态输出功率小、设备供不上电的问题,运用整流电路后级的能量泄放电路,降低了整流桥上的感应电压并限制了互感器的输出电流,解决了母线大电流状态对后级电路的影响.结果表明,混合能量存储系统比单一能量储能装置可以发挥更好的性能.

Quantitative analysis of cell dynamic processes through fluorescence microscopy imaging requires simultaneously tracking large and time-varying number of bright spots and its individual states in noisy image sequences. Such process is characterized as a challenging task due to several roadblocks including the severe image noise and clutter, the occlusion of one cell by others, and the weak image contrast. In this paper, we propose a novel ant stochastic searching behavior based tracking algorithm, which is called ANT estimator, to tracking multiple cells in fluorescence image sequences. In our ant system, each ant determines probabilistically potential state and then adjusts its mobility according to cell detection position heuristic information. Simulation results verify the effectiveness of our algorithm when applied to cell tracking cases, and its performance is also compared with the particle filter based cell tracking algorithm.

In this paper, we propose a novel ant system algorithm for balancing node energy distribution with maximum the number of complete data transmission in ocean buoy communication sensor network. In our algorithm, a complete transmission process is regarded as an ant tour, and each ant stochastically select corresponding node based on such information as energy function, heuristic function, and pheromone amount. An appropriate objective function is carefully designed with the expectation of maximizing the number of complete transmission and uniform minimum energy distribution. Simulation results are presented to support obtained favorable performance of our algorithm.

This paper put forward a kind of hybrid 3G-VHF wide range communication system over buoys and offered latest research progress. Buoy to buoy, buoy to monitoring center has a self-organizing wide-area topology structure and each node can select or switch 3G or VHF protocol to communicate according to their signal receiving area. System test shows that it is an effective means to expand maritime ecological monitoring coverage with very low cost.

This paper introduced DirectShow technology and its image acquisition application in Windows CE embedded system.The advantages of DirectShow technology in Windows CE system for image acquisition are also discussed.Based on them,image acquisition function is realized,which offered the first step to video monitoring system and OCR system application development.

In this article,we study and analyze several kinds of data transmission that are used in red tide monitoring: Short Message Service in GSM,GPRS network,Iridium satellite remote monitoring technology,ZigBee technology and Airborne laser radar technology on the sea.During the study,we find out the advantages and limitations of each technology.Afterwards,we put forward a data transmission system in red tide monitoring with the consideration of the advantages of the above data transmission.

This paper put forward a mine location algorithm based on multiple linear regression, which using only simple RSSI value to get a higher location accuracy under long narrow and sensitive mine environment. General RSSI measurement method and its drawbacks are discussed in the paper. In order to acquire smaller location error, we filtered some abnormal RSSI data through Gaussian filter method. And we deduced regression equation according to multiple linear regression principle. Combined with training sample, we got their regression parameter. We did relevant location experiment again in the same environment-40m long and narrow bomb shelter which may imitate mine tunnel to a great extent, which shows that the total errors are limited in 3m and 75% errors are less than 2m. What's more, it can be extended to infinite measuring range with the same set regression coefficient in similar environment.

In order to accurately measure level from object to image acquisition devices, this paper put forward a kind of new non-contact level measuring method based on image process and its prototype equipment. Through a series of image preprocessing for captured image such as difference, grayness, binarization and thinness, original image is preferable to measure than before. The relation between image pixel value and tilt angle is acquired via mathematical derivation, as well as the distance formula is gained through fitting function. A large amount of data is gathered in the experiment while error analysis of these results is also offered, in which testified that the measuring method for object distance achieved expected effect.