检索结果-南通市图书馆

Position-aware pushing and grasping synergy with deep reinforcement learning in clutter

CAAI Transactions on Intelligence Technology 2024年第3期9卷 738-755页

作者： Min Zhao Guoyu Zuo Shuangyue Yu Daoxiong Gong Zihao Wang ouattara sie Intelligent Robotics Laboratory Faculty of Information TechnologyBeijing University of TechnologyBeijingChina Beijing Key Laboratory of Computational Intelligence and Intelligent Systems BeijingChina Laboratory of Biomechatronics and Intelligent Robotics(BIRO) Department of Mechanical and Aerospace EngineeringNorth Carolina State UniversityRaleighNorth CarolinaUSA

The positional information of objects is crucial to enable robots to perform grasping and pushing manipulations in *** effectively perform grasping and pushing manipu-lations,robots need to perceive the position information of objects,including the co-ordinates and spatial relationship between objects(e.g.,proximity,adjacency).The authors propose an end-to-end position-aware deep Q-learning framework to achieve efficient collaborative pushing and grasping in ***,a pair of conjugate pushing and grasping attention modules are proposed to capture the position information of objects and generate high-quality affordance maps of operating positions with features of pushing and grasping *** addition,the authors propose an object isolation metric and clutter metric based on instance segmentation to measure the spatial re-lationships between objects in cluttered *** further enhance the perception capacity of position information of the objects,the authors associate the change in the object isolation metric and clutter metric in cluttered environment before and after performing the action with reward function.A series of experiments are carried out in simulation and real-world which indicate that the method improves sample efficiency,task completion rate,grasping success rate and action efficiency compared to state-of-the-art end-to-end *** that the authors’system can be robustly applied to real-world use and extended to novel *** material is available at https://***/NhG\_k5v3NnM}{https://***/NhG\_k5v3NnM.

关键词： deep learning deep neural networks intelligent robots

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

3D reconstruction and defect pattern recognition of bonding wire based on stereo vision

引用

CAAI Transactions on Intelligence Technology 2024年第2期9卷 348-364页

作者： Naigong Yu Hongzheng Li Qiao Xu ouattara sie Essaf Firdaous Faculty of Information Technology Beijing University of TechnologyBeijingChina Beijing Key Laboratory of Computing Intelligence and Intelligent System Beijing University of TechnologyBeijingChina Engineering Research Center of Digital Community Ministry of EducationBeijingChina College of Robotic UniversitéFélix Houphouët‐BoignyAbidjanCôte d’Ivoire

Non-destructive detection of wire bonding defects in integrated circuits(IC)is critical for ensuring product quality after ***-processing-based methods do not provide a detailed evaluation of the three-dimensional defects of the bonding ***,a method of 3D reconstruction and pattern recognition of wire defects based on stereo vision,which can achieve non-destructive detection of bonding wire defects is *** contour features of bonding wires and other electronic components in the depth image is analysed to complete the 3D reconstruction of the bonding *** to filter the noisy point cloud and obtain an accurate point cloud of the bonding wire surface,a point cloud segmentation method based on spatial surface feature detection(SFD)was *** can extract more distinct features from the bonding wire surface during the point cloud segmentation ***,in the defect detection process,a directional discretisation descriptor with multiple local normal vectors is designed for defect pattern recognition of bonding *** descriptor combines local and global features of wire and can describe the spatial variation trends and structural features of *** experimental results show that the method can complete the 3D reconstruction and defect pattern recognition of bonding wires,and the average accuracy of defect recognition is 96.47%,which meets the production requirements of bonding wire defect detection.

关键词： bonding wire defect detection point cloud point cloud segmentation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Optimal Classification of Minerals by Microscopic Image Analysis Based on Seven-State “Deep Learning” Combined with Optimizers

引用

Open Journal of Applied Sciences 2024年第6期14卷 1550-1572页

作者： Kouadio Krah sie ouattara Gbele ouattara Alain Clement Joseph Vangah Laboratoire de Gnie Civil Gosciences et Sciences Gographiques Institut National Polytechnique Houphout Boigny (INPHB) Yamoussoukro Cte dIvoire Institut National Polytechnique Houphout Boigny (INPHB) Ecole Doctorale Polytechnique (EDP) Yamoussoukro Cte dIvoire Laboratoire des Sciences et Technologies de la Communication et de lInformation (LSTCI) Institut National Polytechnique Houphout Boigny (INP-HB) Yamoussoukro Cte dIvoire Ecole de Gomatique et du Territoire (EGT) Abidjan Cte dIvoire LARIS SFR MATHSTIC Universit dAngers Angers France Universit Virtuelle de Cte dIvoire Abidjan Cte dIvoire

The development of artificial intelligence (AI), particularly deep learning, has made it possible to accelerate and improve the processing of data collected in different fields (commerce, medicine, surveillance or security, agriculture, etc.). Most related works use open source consistent image databases. This is the case for ImageNet reference data such as coco data, IP102, CIFAR-10, STL-10 and many others with variability representatives. The consistency of its images contributes to the spectacular results observed in its fields with deep learning. The application of deep learning which is making its debut in geology does not, to our knowledge, include a database of microscopic images of thin sections of open source rock minerals. In this paper, we evaluate three optimizers under the AlexNet architecture to check whether our acquired mineral images have object features or patterns that are clear and distinct to be extracted by a neural network. These are thin sections of magmatic rocks (biotite and 2-mica granite, granodiorite, simple granite, dolerite, charnokite and gabbros, etc.) which served as support. We use two hyper-parameters: the number of epochs to perform complete rounds on the entire data set and the “learning rate” to indicate how quickly the weights in the network will be modified during optimization. Using Transfer Learning, the three (3) optimizers all based on the gradient descent methods of Stochastic Momentum Gradient Descent (sgdm), Root Mean Square Propagation (RMSprop) algorithm and Adaptive Estimation of moment (Adam) achieved better performance. The recorded results indicate that the Momentum optimizer achieved the best scores respectively of 96.2% with a learning step set to 10−3 for a fixed choice of 350 epochs during this variation and 96, 7% over 300 epochs for the same value of the learning step. This performance is expected to provide excellent insight into image quality for future studies. Then they participate in the development of

关键词： Classification Convolutional Neural Network Deep Learning Optimizers Transfer Learning Rock Mineral Images

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

New Approach to Rock Classification Based on Sparse Representations

引用

Open Journal of Applied Sciences 2024年第1期14卷 145-158页

作者： Wognin Joseph Vangah Bi G. Théodore Toa Alico Nango Jerôme ouattara sie Alain Clément Unité de Recherche et d’expertise Numérique (UREN) Université Virtuelle de C&#244te d’Ivoire (UVCI) Abidjan C&#244te d’Ivoire UFR Sciences et technologique Département de Physique Université polytechnique de Man (UPM) Man C&#244te d’Ivoire Classe Préparatoire des Grandes Ecoles (CPGE) Université de San Pédro (USP) San Pédro C&#244te d’Ivoire Institut National Polytechnique Houphouë t (INPHB) Yamoussoukro C&#244te d’Ivoire Laboratoire Angevin de Recherche en Ingénierie des Systèmes (LARIS) Institut Universitaire de Technologie (IUT) Université d’Angers Angers France

In geology, classification and lithological recognition of rocks plays an important role in the area of oil and gas exploration, mineral exploration and geological analysis. In other fields of activity such as construction and decoration, this classification makes sense and fully plays its role. However, this classification is slow, approximate and subjective. Automatic classification curbs this subjectivity and fills this gap by offering methods that reflect human perception. We propose a new approach to rock classification based on direct-view images of rocks. The aim is to take advantage of feature extraction methods to estimate a rock dictionary. In this work, we have developed a classification method obtained by concatenating four (4) K-SVD variants into a single signature. This method is based on the K-SVD algorithm combined with four (4) feature extraction techniques: DCT, Gabor filters, D-ALBPCSF and G-ALBPCSF, resulting in the four (4) variants named K-Gabor, K-DCT, KD-ALBPCSF and KD-ALBPCSF respectively. In this work, we developed a classification method obtained by concatenating four (4) variants of K-SVD. The performance of our method was evaluated on the basis of performance indicators such as accuracy with other 96% success rate.

关键词： Rock Recognition Dictionary Signature Color Texture K-SVD Variants KD-ALBPCSF Et KG-ALBPCSF

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Construction of the rat brain spatial cell firing model on a quadruped robot

引用

CAAI Transactions on Intelligence Technology 2022年第4期7卷 732-743页

作者： Naigong Yu Yishen Liao Hejie Yu ouattara sie Faculty of Information Technology Beijing University of TechnologyBeijingChina Beijing Key Laboratory of Computational Intelligence and Intelligent System BeijingChina Engineering Research Center of Digital Community Ministry of EducationBeijingChina College of Robotic UniversitéFélix Houphouet-BoignyAbidjanCote d'Ivoire

Physiological studies have shown that rats in a dark environment rely on the limbs and vestibule for their self-motion information,which can maintain the specific firing patterns of grid cells and hippocampal CA3 place *** the development stage of rats,grid cells are considered to come from place cells,and place cells can be encoded by hippocampal theta *** on these,the quadruped robot is used as a platform in this ***,the sensing information of the robot's limbs and inertial measurement unit is obtained to solve its position in the *** the position information is encoded by theta cells and mapped to place cells through a neural *** obtaining the place cells with singlepeak firing fields,Hebb learning is used to adjust the connection weight of the neural network between place cells and grid *** order to verify the model,3-D simulation experiments are designed in this *** experiment results show that with the robot exploring in space,the spatial cells firing effects obtained by the model are consistent with the physiological research facts,which lay the foundation for the bionic environmental cognition model.

关键词： robot neural firing

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Wafer map defect patterns classification based on a lightweight network and data augmentation

引用

CAAI Transactions on Intelligence Technology 2023年第3期8卷 1029-1042页

作者： Naigong Yu Huaisheng Chen Qiao Xu Mohammad Mehedi Hasan ouattara sie Faculty of Information Technology Beijing University of TechnologyBeijingChina Beijing Key Laboratory of Computational Intelligence and Intelligent System BeijingChina Engineering Research Center of Digital Community Ministry of EducationBeijingChina College of Robotic UniversitéFélix Houphouët‐BoignyAbidjanCôte d'Ivoire

Accurately identifying defect patterns in wafer maps can help engineers find abnormal failure factors in production *** the wafer testing stage,deep learning methods are widely used in wafer defect detection due to their powerful feature extraction ***,most of the current wafer defect patterns classification models have high complexity and slow detection speed,which are difficult to apply in the actual wafer production *** addition,there is a data imbalance in the wafer dataset that seriously affects the training results of the *** reduce the complexity of the deep model without affecting the wafer feature expression,this paper adjusts the structure of the dense block in the PeleeNet network and proposes a lightweight network WM‐PeleeNet based on the PeleeNet *** addition,to reduce the impact of data imbalance on model training,this paper proposes a wafer data augmentation method based on a convolutional autoencoder by adding random Gaussian noise to the hidden *** method proposed in this paper has an average accuracy of 95.4%on the WM‐811K wafer dataset with only 173.643 KB of the parameters and 316.194 M of FLOPs,and takes only 22.99 s to detect 1000 wafer *** with the original PeleeNet network without optimization,the number of parameters and FLOPs are reduced by 92.68%and 58.85%,*** augmentation on the minority class wafer map improves the average classification accuracy by 1.8%on the WM‐811K *** the same time,the recognition accuracy of minority classes such as Scratch pattern and Donut pattern are significantly improved.

关键词： convolutional autoencoder lightweight network wafer defect detection

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

基于多线索的运动手部分割方法

引用

电子与信息学报 2017年第5期39卷 1088-1095页

作者：阮晓钢林佳于乃功朱晓庆 ouattara sie 北京工业大学电子信息与控制工程学院北京100124 计算智能与智能系统北京市重点实验室北京100124

分割运动手部时,为了不依赖不合理的假设和解决手脸遮挡问题,该文提出一种基于肤色、灰度、深度和运动线索的分割方法。首先,利用灰度与深度光流的方差信息来自适应提取运动感兴趣区域(Motion Region of Interest,MRoI),以定位人体运动... 详细信息

分割运动手部时,为了不依赖不合理的假设和解决手脸遮挡问题,该文提出一种基于肤色、灰度、深度和运动线索的分割方法。首先,利用灰度与深度光流的方差信息来自适应提取运动感兴趣区域(Motion Region of Interest,MRoI),以定位人体运动部位。然后,在MRoI中检测满足肤色与自适应运动约束的角点作为皮肤种子点。接着,根据肤色、深度与运动准则将皮肤种子点生长为候选手部区域。最后,通过边缘深度梯度、骨架提取和最优路径搜索从候选手部区域中分割出运动手部区域。实验结果表明,在不同情形下,特别是手脸遮挡时,该方法可以有效和准确地分割出运动手部区域。

关键词：运动手部分割多线索不依赖假设手脸遮挡

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Method of Estimation of Chemical Compounds of a Solution by Analysis of Video Images of Titration from a Semi-Automatic Approach

引用

Open Journal of Applied Sciences 2022年第6期12卷 1069-1082页

作者： Marcelin Sandje sie ouattara Diako Doffou Jerome Alain Clément Laboratory of Signals and Electrical Systems (L2SE)) Institut National Polytechnique Houphou&#235 t Boigny Yamoussoukro C&ocirc te d’Ivoire Institut National Polytechnique Houphouë t Boigny (INPHB) Yamoussoukro C&ocirc te d’Ivoire Ecole Supérieure des Technologies de l’Information et de la Communication (ESATIC) Abidjan C&ocirc te d’Ivoire Laboratoire de Recherche en Informatique et Télécommunication (LARIT) Abidjan C&ocirc te d’Ivoire Institut Universitaire de Technologie d’Angers (IUT) Angers France

To titrate or measure a chemical species in a solution is to estimate its quantity of matter or its molar concentration in a given solution. Several methods of estimating molar concentrations of chemical species exist, the main ones being Colorimetric titration, Conductimetric titration, pH metric titration. In practice, all these methods present approximative results because the operator repeats the experiment to ensure the reliability of the results. As a consequence, we have a prolonged time of the experiment which involves a cost in reagents. Given the repetitions of the same experiment, the final result is the average of the results of each experiment. The aim of this paper is to correct this subjectivity by implementing a semi-automatic approach based on colorimetric titration. At the end of the implementation of our approach, we compared our results to those of existing techniques. These results show the reliability of the calculation by the semi-automatic method. This method of estimating the volume at equivalence is fast because it is not manual and does not involve the use of geometric measuring instruments to find the volume at equivalence. This method improves the manual calculation of the volume at equivalence used in the laboratories in school and student environment.

关键词： Titration Turning Equivalence Point Volume at Equivalence

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

基于RGB-D数据的自适应局部时空特征提取方法

引用

北京工业大学学报 2016年第11期42卷 1643-1651页

作者：林佳阮晓钢于乃功 ouattara sie 朱晓庆北京工业大学电子信息与控制工程学院北京100124 北京工业大学计算智能与智能系统北京市重点实验室北京100124

对于一次学习手势识别,噪声和全局经验运动约束严重影响时空特征的精确与充分提取,为此提出了一种融合颜色和深度(RGB-D)信息的自适应局部时空特征提取方法.首先建立连续两灰度帧和两深度帧的金字塔以及相应的光流金字塔作为尺度空间.... 详细信息

对于一次学习手势识别,噪声和全局经验运动约束严重影响时空特征的精确与充分提取,为此提出了一种融合颜色和深度(RGB-D)信息的自适应局部时空特征提取方法.首先建立连续两灰度帧和两深度帧的金字塔以及相应的光流金字塔作为尺度空间.然后根据灰度和深度光流的水平与垂直方差自适应提取运动感兴趣区域(motion regions of interest,MRo Is).接着仅在MRo Is内检测角点作为兴趣点,当兴趣点的灰度和深度光流同时满足局部运动约束时即为关键点,局部运动约束是在每个MRo I内自适应确定的.最后在改进的梯度运动空间计算SIFT-like描述子.Chalearn数据库上的实验结果表明:提出方法得到了较高的识别准确率,其识别性能优于现已发表的方法.

关键词：手势识别一次学习时空特征自适应运动感兴趣区域

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

A Semi-Vectorial Morphological Segmentation Multi-Component Images of Coumarins on Thin Layer Combined with Laser for Better Separation

引用

Open Journal of Applied Sciences 2022年第6期12卷 1054-1068页

作者： Theodore Guié Toa Bi Marcelin Sandjé Régnima G. Oscar sie ouattara Alain Clement UFR Science and Technology University of Man Man Ivory Coast Laboratory of Communication and Information Science and Technology (LSTCI) National Polytechnic Institute Houphou&#235 t Boigny Yamoussoukro C&ocirc te d’Ivoire University Institute of Technology of Angers (IUT) Angers France

In this work, we propose an approach for the separation of coumarins from thin-layer morphological segmentation based on the acquisition of multicomponent images integrating different types of coumarins. The first step is to make a segmentation by region, by thresholding, by contour, etc. of each component of the digital image. Then, we proceeded to the calculations of parameters of the regions such as the color standard deviation, the color entropy, the average color of the pixels, the eccentricity from an algorithm on the matlab software. The mean color values atR = 91.20 in red, atB = 213.21 in blue showed the presence of samidin in the extract. The color entropy values HG = 5.25 in green and HB = 4.04 in blue also show the presence of visnadine in the leaves of Desmodium adscendens. These values are used to consolidate the database of separation and discrimination of the types of coumarins. The relevance of our coumarin separation or coumarin recognition method has been highlighted compared to other methods, such as the one based on the calculation of frontal ratios which cannot discriminate between two coumarins having the same frontal ratio. The robustness of our method is proven with respect to the separation and identification of some coumarins, in particular samidin and anglicine.

关键词： Identification Thin Layer Secondary Metabolites Coumarins Image Acquisition Segmentation Standard Deviation Entropy Average Color Algorithm Matlab

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：