A Target Grabbing Strategy for Telerobot Based on Improved Stiffness Display Device

Most target grabbing problems have been dealt with by computer vision system, however, computer vision method is not always enough when it comes to the precision contact grabbing problems during the teleoperation process, and need to be combined with the stiffness display to provide more effective information to the operator on the remote side. Therefore, in this paper a more portable stiffness display device with a small volume and extended function is developed based on our previous work. A new static load calibration of the improved stiffness display device is performed to detect its accuracy, and the relationship between the stiffness and the position is given. An effective target grabbing strategy is presented to help operator on the remote side to judge and control and the target is classified by multi-class SVM(supporter vector machine). The teleoperation system is established to test and verify the feasibility. A special experiment is designed and the results demonstrate that the improved stiffness display device could greatly help operator on the remote side control the telerobot to grab target and the target grabbing strategy is effective.

A Contribution to a Better Understanding of Global Land Grabbing＇s Impact on Employment and Environmental Threats

In the last two decades, the global interest on farmland grew at a remarkable pace. As a consequence, million hectares of land exchanged hands. The ways the transfers happened combined with their geographic concentration in Sub-Saharian Africa, have earned the phenomenon the name of ＂land grab＂. The agricultural sector considered a ＂sunset industry＂ when commodities prices were declining, is now attractive to financial investors. These foreign investments may be good as they may improve agricultural productivity or instead bad as they may benefit only financial investors. Some results in terms of environmental and local communities＇ worsening conditions have already emerged. This paper aims to investigate what drives the big size transfers of land, to empirically estimate their effects in terms of local employment and to assess the environmental effects produced by the rapid transformation in the use of vast amount of land in terms of CO2 emissions. It is also proposed to use the estimation in terms of local employment impact as a way of distinguishing between foreign direct investment and land grabbing.

Grabbing the Opportunity to Create Elaborately

Approved by Ministry of Culture in 1999 as China Wuqiao International Acrobatic Art Training Center, Hebei Wuqiao Acrobatic Art School started to train 6 students from Tanzania.

Outward foreign direct investment in agriculture by Chinese companies:land grabbing or win–win?

Using the firsthand materials collected during on-site fieldworks and in-depth interviews,this paper examines the dimensions,especially the motives,for driving Chinese firms to invest in agriculture overseas from the macro(or government’s)-and micro(or firms’)-perspectives,as well as the impact of Chinese firms’agricultural outward foreign direct investment(OFDI)from the multistakeholder perspective.From the perspective of China’s central government,the goal of encouraging domestic enterprises’overseas investment in agriculture is not to ensure national grain security,but to stabilise the domestic supply of strategic agricultural products.From the micro-perspective,the impetuses for driving Chinese firms to invest in agriculture overseas are diverse and land exploitation is just one of them.They may wish to compete with local producers and some of the enterprises do not have a strong awareness of environmental protection and social responsibility.This is not the whole story.Chinese enterprises’agricultural OFDI increases agricultural investment and reduces poverty in the host countries,and expands the supply of agricultural products of the local markets.In the long run,the growing presence of Chinese firms with advanced technology will yield the benefits of competition:an expansion of local supplies while providing cheap technology that can be duplicated by local farmers.Only a very small proportion of the agricultural products grown abroad is sold back to China,while a large part is sold domestically or exported to a third market.Therefore,Chinese firms’agricultural OFDI has offered little direct,but some indirect,help in guaranteeing China’s food security.Perhaps,China’s diplomatic and political benefits obtained through agricultural OFDI outweigh the benefits of ensuring food security.Chinese enterprises’agricultural OFDI is a win-win situation for the host countries and for China.

Research on robot grabbing system based on hybrid cloud

Robot grabbing has been successfully applied to a range of challenging environments but met the resource bottleneck. To answer this question, a hybrid cloud-based robot grabbing system is proposed, which supports centralized bin-picking management and deployment, large-scale storage, and communication technologies. The hybrid cloud combines the powerful computational capabilities through massive parallel computation and higher data storage facilities in the public cloud with data privacy in the private data center. The benchmark tasks against a public cloud based on robot grabbing method are evaluated, whose results indicate that the whole system reduces the data collection time and increases elastic resource scheduling and is adapted in the real industry.

Multitarget Flexible Grasping Detection Method for Robots in Unstructured Environments

In present-day industrial settings,where robot arms performtasks in an unstructured environment,theremay exist numerousobjects of various shapes scattered in randompositions,making it challenging for a robot armtoprecisely attain the ideal pose to grasp the object.To solve this problem,a multistage robotic arm flexible grasp detection method based on deep learning is proposed.This method first improves the Faster RCNN target detection model,which significantly improves the detection ability of the model for multiscale grasped objects in unstructured scenes.Then,a Squeeze-and-Excitation module is introduced to design a multitarget grasping pose generation network based on a deep convolutional neural network to generate a variety of graspable poses for grasped objects.Finally,a multiobjective IOU mixed area attitude evaluation algorithm is constructed to screen out the optimal grasping area of the grasped object and obtain the optimal grasping posture of the robotic arm.The experimental results show that the accuracy of the target detection network improved by the method proposed in this paper reaches 96.6%,the grasping frame accuracy of the grasping pose generation network reaches 94%and the flexible grasping task of the robotic arm in an unstructured scene in a real environment can be efficiently and accurately implemented.

改进Grab Cut算法的复合绝缘子憎水性评估

为快速、准确地识别复合绝缘子伞裙的憎水性,提出了一种基于改进Grab Cut算法的复合绝缘子憎水性评估方法,在Grab Cut的基础上引入自适应对比度增强算法来解决图像光照不均匀问题和自适应平滑滤波算法解决图像噪声问题。在伞裙表面滴下20μL的液滴,使用改进后的Grab Cut算法对电晕老化样品、自然积污硅橡胶样品、不同憎水性硅橡胶样品和实际运行工况复合绝缘子进行液滴面积识别。结果表明:算法能降低由于复合绝缘子运行时伞裙表面积污产生的图像噪声,且能较为准确地分割液滴图像与复合绝缘子背景,验证了其有效性和可靠性;可对人工加速老化和自然老化样品液滴面积变化进行测算,并对照静态接触角法,实现复合绝缘子憎水性的评估。

基于热红外成像技术的油菜菌核病早期检测研究

将热红外成像技术和低空遥感技术相结合,基于冠层和叶片两个尺度对菌核病侵染油菜的过程进行检测研究。从冠层尺度分析,首先获取整株样本的温度值(平均温度与最大温差),并采集其生理指数(气孔导度、 CO_2浓度、蒸腾速率及光合速率)。然后,将染病样本与健康样本的温度值进行判别分析,并对其进行单因素方差分析。从结果可知,平均温度和最大温差值都可以对染病样本与健康样本进行区分,且最大温差相较平均温度结果较明显。同时单因素方差分析也显示,最大温差三次检测中均存在显著性差异。对获取的生理指数进行分析,发现染病样本与健康样本之间可以通过生理指数进行明显区分。另外,将生理指数与叶片温度进行相关性分析,结果表明二氧化碳浓度与叶片温度之间的三次检测均存在显著性差异。基于叶片尺度,首先从单一叶片来看健康区域和染病区域的温度差异,可以明显区分出染病区域和健康区域的温度差异。然后,提取健康区域与染病区域的的温度值(最大温度、最小温度、平均温度以及最大温差)对进行对比分析,并对其进行单因素方差分析。结果表明,以上四个温度指标均可以区分叶片的染病区域和健康区域。但根据单因素方差分析结果可知,与冠层尺度相同,最大温差三次检测中均存在显著性差异,可以实现对油菜菌核病的早期识别。

基于图割算法的木材表面缺陷图像分割

木材表面缺陷分割的研究能够有效提高木材的利用率,节约现有木材资源,缓解森林资源短缺的压力。为了更好地对板材表面的节子和虫眼进行快速有效地分割,论述了基于图割算法的图像分割方法(Graph Cuts)及其改进方法(Grab Cuts)的原理。针对传统Graph Cuts算法只能针对灰度图像进行分割、运行时参数的选择比较复杂,并且存在该算法效率和精度较低的缺陷,采用这两种方法分别对3种木材表面缺陷活节、虫眼和死节图像进行分割实验。为了验证Grab Cuts方法的适用性,用含有多个缺陷目标的木质板材图像做了图像分割验证。结果表明:缺陷图像的目标和背景的种子点选取直接影响Graph Cuts算法的分割结果,Graph Cuts算法的计算效率较低,分割时间较长,对相邻像素间的区分度较差,分割结果不理想。改进后的Grab Cut算法是迭代的Graph Cuts,该方法虽然在图像分割前也需要人工画定初始化矩形框,但操作相对简单,分割结果能够得到完整的闭合缺陷区域边界,且不受木材表面缺陷的类型、数量、尺寸和缺陷形状的影响,分割效果好,分割速度快,抗噪性强,对灰度图像和彩色图像都可使用。

二恶英分子生物学检测方法

二恶英类化合物的检测是现代化合物检测的重点和难点,现在二恶英化合物的标准检测方法为高分辨气相色谱-质谱法。但色谱-质谱法费用昂贵、耗时,对试验设备和人员要求高,因此发展了一些其他快速、低廉的检测方法。作者着重介绍了能快速、简便、低廉及高通量检测二恶英类化合物的分子生物学检测方法,并将报告基因法中的化学活性荧光素酶表达法(CALUX)和体外DNA结合法中的凝胶阻滞电泳生物检测法(GRAB)进行了比较。提出了各种方法的优缺点,为发展新的二恶英生物检测法提供了依据。

基于双目立体视觉的目标识别与定位

为从不同角度识别目标物体以及解决左右两幅图像中目标轮廓中心不匹配的问题,将SURF(Speeded Up Robust Features)算法与Grab Cut算法相结合,离线采集目标物体不同角度的图像,生成目标模板图片库。利用SURF算法完成目标物体的识别;利用SURF算法自动初始化Grab Cut算法,实现目标轮廓的提取;利用基于灰度相关的区域匹配算法完成目标轮廓中心点的匹配,结合三维重建原理实现目标定位。实验结果表明,该方法可以成功识别目标物体并对目标物体进行准确定位。

基于Grab Cut和八方向链码法的藻类细胞轮廓提取算法

为了解决藻类细胞轮廓提取的困难,提出了一种不同于传统方法的新的边缘提取算法。首先对图像进行Grab Cut处理,然后进行阈值法二值化,接着用八方向链码法轮廓跟踪,最后用傅立叶描述子进行边界平滑。实验结果表明,该算法不仅忽略了藻类细胞内部杂乱的纹理,还较好地保留了细胞边缘信息,精确地提取了外部轮廓。

基于LDOF光流算法的视频对象分割方法

针对目前视频对象分割算法中存在分割速度慢的问题,提出了一种基于LDOF光流算法的视频对象分割方法。首先,利用LDOF((Large Displace Optical Flow)计算视频帧中t与t+1时刻像素点的光流;然后,计算N个邻近像素的方向导数,获得视频对象粗略轮廓信息;再利用高斯混合模型建立前景与背景模型,并运用扫描线算法获得到视频对象精确的轮廓;最后,采用Grab Cut算法对视频对象进行分割。实验结果表明,该算法能有效的提高了视频对象分割的速度。

基于Grab Cut和二维熵的SAR图像目标分割方法

传统的Grab cut算法需要人工交互操作,无法实现SAR图像的自动分割;且SAR图像的斑点噪声干扰容易降低图像的分割质量。针对以上问题,文中以Grab Cut图像分割算法为基础,首先利用FCM算法对SAR图像进行预分割,根据预分割结果标记SAR图像中的前景与背景集合,得到两组较为准确的GMM初始化参数,迭代求得能量函数的最小化,实现SAR图像前景区域与背景区域的自动分割;并结合二维熵算法滤除SAR图像中的阴影,分割出目标区域。实验表明,利用该方法可自动分割出SAR图像中的目标,且分割质量良好。

Analysis of Stresses and Deflection of Sun Gear by Theoretical and ANSYS Method

Gearing is one of the most critical components in mechanical power transmission systems. This article examines the various stresses and deflection developed in sun gear tooth of planetary gearbox which is used in Grabbing Crane. Article includes checking sun gear wear stresses and bending stresses using IS 4460 equations. Also calculate various forces acting on gear tooth. In this study, perform the calculation for sun gear tooth to calculate bending, shear, wear & deflection using theoretical method. 3D model is created of circular root fillet & trochoidal root fillet of gear tooth for simulation using ProE Wildfire 3. In Pro-E, the geometry is saved as a file and then it is transferred from Pro-E to ANSYS 10 in IGES format. The results of the 3 D analyses from ANSYS are compared with the theoretical values. Comparison of ANSYS results in circular root fillet & trochoidal root fillet also carry out.

基于SLIC的GrabCut减小姿态搜索空间算法

针对人体的高自由度导致姿态估计过程中搜索空间过大的问题,提出一种基于简单线性迭代聚类(SLIC)超像素算法的Grab Cut减小姿态空间算法。运用SLIC算法对图像进行超像素分割,以超像素作为s-t图中的节点构建图模型,利用超像素区域的颜色特征平均值作为该区域内每个像素的特征值,分别为前景和背景超像素建立混合高斯模型,迭代更新高斯参数,运用最小割算法完成前景提取,并在得到的前景区域中进行后续的姿态估计。实验结果表明,基于SLIC的Grab Cut与基于Grab Cut的减小搜索空间算法在运行时间和姿态估计准确度上均有较大程度提升。

一种古建墙壁受污文字图像的多特征引导Grab Cut分割方法

古建墙壁题记毛笔文字受霉变污染影响,字迹不清,不利于辨识,而传统算法对文字图像进行分割时未充分考虑污染和文字的特征信息,结果中往往存在误分割或缺损现象。本研究提出一种结合图像偏振信息的多特征引导Grab Cut分割算法,该方法首先对采集的0°、45°、90°、135°四个角度偏振图像进行斯托克斯解算,得到偏振度特征图;然后利用SLIC对可见光相机采集的题记图像进行超像素分割,并提取超像素的颜色特征距和纹理特征距;最后,用偏振度约束区域项,特征距引导边界项,进行Grab Cut分割,得到毛笔文字分割结果。实验结果表明,本算法与未考虑偏振和特征距信息的图割算法相比,分割效果得到较大改善。研究结果可为书法研究和文字拓本的数字化存储提供有力的科学支持,也为题记的实体去污修复过程提供充足的科学指引和实验环境。

基于权值优化与纹理特征的快速人脸分割算法

针对传统Grab Cut在GMM迭代估计阶段仅单纯地考虑像素点的RGB彩色信息,当前景细节区域与它的周围区域颜色差异较大时容易发生分割错误,以及基于像素的运算导致分割效率不高的问题,提出一种结合权值优化与CS-LBP纹理特征的改进算法。该算法利用多尺度分水岭对图像进行预分割,构建区域邻接图;然后对每个区域进行颜色和纹理特征的提取,通过权值迭代优化算法使区域的数据项权值与周边分块区域的权值相关联,采用自适应参数将纹理约束项引入能量函数,并将改进算法应用于人脸图像分割,有效改善了分割效果。实验结果表明,该算法分割结果更加准确,效率更高。

应用于刹车盘复杂背景去除的改进Grab Cut分割算法

针对无序分拣过程中车间光照不均导致的分割结果不准确问题,提出一种改进的Grab Cut图像分割算法。该算法采用自适应中值滤波去除图像表面噪声;通过限定对比度自适应直方图均衡化提升图像整体亮度,增强对比度;进一步使用Laplacian算子对刹车盘区域进行锐化处理;在此基础上对刹车盘图像复杂背景进行去除;最后通过仿真实验对比分割效果、PSNR、误分割率、分割准确性和运行时间来评价算法模型。实验结果表明:提出的改进Grab Cut分割算法相较于原始算法能有效降低光照不均对刹车盘复杂图像背景去除的影响,使分割准确率提高了12.5%,分割结果与实际刹车盘模型相比误差小,为刹车盘图像复杂背景去除提供参考。

基于Grab Cut和区域生长的服装图像前景提取算法

针对Grab Cut算法应用于服装检索系统中服装图像的前景提取时所存在的交互式和复杂背景提取效果差问题,首先提出了一种全自动化的Grab Cut算法,以实现自动根据背景情况,对单一背景和复杂背景图像分别采用不同的方法生成初始矩形框并进行前景提取.由于该算法仍存在欠分割或过分割现象,故将该算法与区域生长算法相结合,给出了一种结合区域生长的全自动化Grab Cut算法.实验结果表明,无论对于单一背景还是复杂背景的图像,改进算法的前景提取效果都明显优于传统算法,不仅能准确获取服装前景区域,而且对于服装内部的过分割问题也有很大的改善.