检索结果-内蒙古大学图书馆

A corner-clustering method for detection of slab management numbers sprayed on steel slabs

visual COMPUTER 2022年第1期38卷 357-369页

作者： Peng, Yiping Ge, Junhui Qin, Hui Ge, Xiaojun Xiao, Changyan Hunan Univ Natl Engn Lab Robot Visual Percept & Control Tech Changsha Peoples R China

To achieve manufacturing and logistics informatization management for steelworks, it is of crucial importance to automatically recognize the slab management numbers (SMNs) sprayed on the steel slabs. However, due to the poor quality of spraying and various interferences, SMN detection is a major challenge for subsequent recognition in the steel-slab product line. This paper proposes a corner-clustering method, which can extract the SMN from a changeable background precisely and promptly. In our method, the FAST algorithm is modified to extract the image corners by adaptively adjusting the local threshold of corner detecting with the change of image contrast. Then, the DBSCAN algorithm is implemented to group the corners into several clusters, which includes the SMN regions and interference regions. Finally, a classifier based on HOG features and SVM is applied to discriminate SMN and non-SMN regions. For experimental validation, the proposed method was implemented to a substantial amount of acquired images. A good performance has been achieved as the detection accuracy can reach as high as 98.96% for SMN on the steel slabs.

关键词： SMN detection Computer vision Steel slabs DBSCAN cluster Corner detection

来源：评论

学校读者我要写书评

暂无评论

Pharmaceutical Foreign Particle Detection: An Efficient Method Based on Adaptive Convolution and Multiscale Attention

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2022年第6期6卷 1302-1313页

作者： Yi, Junfei Zhang, Hui Mao, Jianxu Chen, Yurong Zhong, Hang Wane, Yaonan Hunan Univ Natl Engn Lab Robot Visual Percept & Control Tech Coll Elect & Informat Engn Changsha 410082 Hunan Peoples R China Hunan Univ Coll Robot Natl Engn Lab Robot Visual Percept & Control Tech Changsha 410082 Hunan Peoples R China

The detection of pharmaceutical product quality is indispensable and crucial in drug manufacture. In particular, the detection of liquid pharmaceutical products is generally performed manually and offline. However, this type of method is inefficient and possesses low precision due to limited personal sensing and eyesight capabilities. Since recent advanced computational intelligence (CI) algorithms have achieved great successes in computer vision, CI (e.g., deep neural networks (DNNs)) is expected to provide efficient and powerful tools that will substantially improve the decision-making of autonomous systems. Moreover, with the current automatic detection methods, it is still a challenge to detect tiny particles efficiently in liquid products. This article proposes an end-to-end deep learning (DL) method with adaptive convolution and multiscale attention to locate and classify foreign particles. First, we present a pixel-adaptive feature extraction (PAFE) method for extracting fine-grained features and reducing the intraclass disparities between particles. Following that, a multiscale attention-based feature fusion (MAFF) method, which effectively fuses the pixel-level and semantic-level information of particles, is proposed. Finally, we use a feature-selective anchor-free detection (FSAD) method to quickly detect foreign particles in liquid pharmaceuticals. To confirm the above initiatives, we validate the proposed method on a liquid pharmaceutical dataset, achieving a missed detection rate of 3.6 percent. The speed of our method is an order of magnitude faster than that of other methods, possibly reaching 15 frames per second (FPS). In addition, we test the model's transferability on a wine dataset.

关键词： Pharmaceuticals Feature extraction Liquids Object detection Convolution Inspection Task analysis Automatic detection methods computational intelligence algorithms adaptive convolution multiscale attention anchor-free

来源：评论

学校读者我要写书评

暂无评论

Iterative Fine Point-Set Matching of a Free-Form Surface Based on the Point-to-Sphere Distance

引用

IEEE-ASME TRANSACTIONS ON MECHATRONICS 2022年第6期27卷 5668-5678页

作者： Xie, He Wang, Yaonan Zhang, Hui Tang, Yongpeng Hunan Univ Natl Engn Lab Robot Visual Percept & Control Tech Changsha 410082 Peoples R China

Three-dimensional point-set matching that aligns the moving point set with the fixed design model is an increasingly popular technique in manufacturing automation, which also increases the demand for matching performance. In this article, an iterative fine matching algorithm based on point-to-sphere distance is proposed to balance convergence accuracy, stability, and speed. By considering the neighborhood of a fixed point as a spherical surface, a point-to-sphere distance from a moving point to the design model is derived to improve the distance calculation accuracy with respect to unknown motion parameters. A point-to-sphere iterative closest point (ICP) matching method is presented, which translates the matching into a nonlinear optimization problem. Using the Newton method, a second-order Taylor expansion is applied to iteratively solve the motion parameters. Theoretical analysis verifies the advantages in convergence performance. It is proven that the proposed method can show faster convergence speed than point-to-point ICP and better convergence stability than point-to-plane ICP in large initial poses. Experiments implementing five models verify the feasibility of the point-to-sphere distance and the corresponding matching method.

关键词： Convergence free-form surface point-set matching sphere

来源：评论

学校读者我要写书评

暂无评论

control-oriented modeling and optimization for the temperature and airflow management in an air-cooled data-center

引用

NEURAL COMPUTING & APPLICATIONS 2022年第7期34卷 5225-5240页

作者： Fang, Qiu Zhou, Jiakang Wang, Shi Wang, Yaonan Hunan Univ Natl Engn Lab Robot Visual Percept & Control Tech Changsha 410082 Peoples R China

This paper presents a method for minimizing the power consumption of a data-center cooling system by optimizing the airflow pattern and the supplied cold air temperature simultaneously. To discover the potential benefits of reorganizing the rack flow rates, a gray-box fast-temperature evaluation model is proposed for the first time, which reflects the thermal relationship among the components of the data center and has low computational complexity. Next, a model-based constrained nonlinear optimization problem is formulated with the aim of minimizing the power consumption of both cooling fans and air conditioners. Meanwhile, the safety thermal guidelines are considered as the main constraints. At last, the optimal settings of rack airflow rates and supplied cold air temperature are obtained by solving the optimization problems. The simulation results show that the proposed method can yield an effective thermal management tool and reduce significant cooling power for air-cooled data centers.

关键词： Thermal management Data center modeling Power optimization Temperature evaluation

来源：评论

学校读者我要写书评

暂无评论

Circle detection with model fitting in polar coordinates for glass bottle mouth localization

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING techNOLOGY 2022年第1-2期120卷 1041-1051页

作者： Zhou, Xianen Wang, Yaonan Zhu, Qing Zhang, Hui Chen, Qinhui Hunan Univ Coll Elect & Informat Engn Natl Engn Lab Robot Visual Percept & Control Tech Changsha 410082 Peoples R China

Glass bottle mouth localization is an essential procedure for quality inspection based on machine vision. However, the real center of the bottle mouth is difficult to detect with traditional methods in the presence of continuous noises. To overcome this problem, a novel circle detection method based on a model fitting and least-squares technique named MFLS is proposed to improve accuracy. First, the edge points of the bottle mouth are obtained by radial scanning which is a simple and fast operation. Second, the mathematical model of the circle in polar coordinates is built according to the geometric features of the circle. We use this model to delete the noise points to improve the positioning accuracy. Finally, the bottle mouth location is obtained by least-squares circle detection. This method is tested using our designed machine vision system. A total of 144 bottle mouth images obtained by our machine vision system are used to evaluate the performances of the proposed algorithm. The experimental results show that the proposed method has strong anti-interference capability and high detection accuracy.

关键词： Image processing Bottle mouth positioning Denoise Circle detection

来源：评论

学校读者我要写书评

暂无评论

Cooperative circumnavigation control of multiple unicycle-type robots with non-identical input constraints

引用

IET control THEORY AND APPLICATIONS 2022年第9期16卷 889-901页

作者： Yu, Yangguang Miao, Zhiqiang Wang, Xiangke Shen, Lincheng Natl Univ Def Technol Coll Intelligence Sci & Technol Changsha 410073 Peoples R China Hunan Univ Coll Elect & Informat Engineeting Changsha Peoples R China Natl Engn Lab Robot Visual Petcept & Control Tech Changsha Peoples R China

For the robot control problems, the input constraint is an issue that must be carefully considered. Considering the control inputs of the robots in the multi-robot system are constrained by different saturations in reality, we address the cooperative circumnavigation control problem of multiple unicycle-type robots with non-identical and unknown input constraints in this paper. A distributed control law is designed to drive the robots constrained by different and unknown input saturations to achieve the cooperative circumnavigation around a moving target. The algorithm proposed in this paper largely reduces the requirement for the maneuverability of the robots to achieve the cooperative circumnavigation. As long as the robots owns the basic maneuverability of circumnavigating around the target, it is proved rigorously that the proposed control algorithm can achieve the desired cooperation circumnavigation of the multi-robot system. The effectiveness of the proposed method is validated by a numerical simulation.

关键词： different input saturations distributed control law mobile robots control algorithm unknown input saturations multiple unicycle-type robots desired cooperation circumnavigation multi-robot systems path planning robot control problems nonidentical input constraints numerical analysis different saturations multirobot system control system synthesis circumnavigation control problem unknown input constraints distributed control control inputs input constraint

来源：评论

学校读者我要写书评

暂无评论

DeepSeed Local Graph Matching for Densely Packed Cells Tracking

引用

IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2021年第3期18卷 1060-1069页

作者： Liu, Min Liu, Yalan Qian, Weili Wang, Yaonan Hunan Univ Coll Elect & Informat Engn Changsha Peoples R China Natl Engn Lab Robot Visual Percept & Control Tech Changsha Peoples R China

The tracking of densely packed plant cells across microscopy image sequences is very challenging, because their appearance change greatly over time. A local graph matching algorithm was proposed to track such cells by exploiting the tight spatial topology of neighboring cells, and then an iterative searching strategy was used to grow the correspondence from a seed cell pair. Thus, the performance of the existing tracking approach heavily relies on the robustness of finding seed cell pair. However, the existing local graph matching algorithm cannot guarantee the correctness of the seed cell pair, especially in unregistered image sequences or image sequences with large time intervals. In this paper, we propose a DeepSeed local graph matching model to find seed cell pair robustly, by combining local graph matching and CNN-based similarity learning, which uses cells' spatial-temporal contextual information and cell pairs' similarity information. The CNN-based similarity learning is designed to learn cells' deep feature and measure cell pairs' similarity. Compared with the existing plant cell matching methods, the experimental results show that the DeepSeed local graph matching method can track most cells in unregistered image sequences. Moreover, the DeepSeed tracking algorithm can accurately track cells across image sequences with large time intervals.

关键词： Image sequences Feature extraction Microscopy Image segmentation Image edge detection Cells (biology) Topology Cell tracking CNN-based similarity learning Local graph matching DeepSeed

来源：评论

学校读者我要写书评

暂无评论

Deep residual deconvolutional networks for defocus blur detection

引用

IET IMAGE PROCESSING 2021年第3期15卷 724-734页

作者： Zeng, Kai Wang, Yaonan Mao, Jianxu Zhou, Xianen Hunan Univ Sch Elect & Informat Engn Changsha Peoples R China Hunan Univ Natl Engn Lab Robot Visual Percept & Control Tech Changsha Peoples R China

Accurate defocus blur detection has instigated wide research interest for the last few years. However, it is still a meaningful yet challenging machine vision task, and most methods rely on prior knowledge. Convolutional neural networks have proved the huge success for different tasks within the computer vision, and machine learning flew. A simple yet effective method of defocus blur detection was proposed in this paper, which by applying the deep residual convolutional encoder-decoder network. The aims of DRDN is to automatically generate pixel-level predictions for defocus blur images, and reconstruct output detection results of the same size as the input, which by performing several deconvolution operations at multiple scales through the transposed convolution, and skip connection. Afterwards, we used the slide window detection strategy and traversed the input image with a certain stride. Experiments on challenging benchmarks of defocus blur detection show that our algorithm achieved state-of-the-art performance, and powerfully balanced the detection accuracy, and detection time.

关键词： Optical, image and video signal processing Computer vision and image processing techniques Neural nets

来源：评论

学校读者我要写书评

暂无评论

Real-Time Classification of Rubber Wood Boards Using an SSR-Based CNN

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2020年第11期69卷 8725-8734页

作者： Liu, Shihui Jiang, Wenbo Wu, Lehui Wen, He Liu, Min Wang, Yaonan Hunan Univ Coll Elect & Informat Engn Changsha 410012 Peoples R China Natl Engn Lab Robot Visual Percept & Control Tech Changsha 410012 Peoples R China

The classification of wood types plays an important role in many fields, especially in construction industry and furniture manufacturing. In order to manufacture rubber wood furniture with highly uniform color and texture, wood boards of different colors and textures should be classified elaborately. Many traditional methods have been applied in wood classification relying on extracting features using handcrafted descriptors designed by experienced experts, but it is not easy to construct robust features in various conditions. In this article, we present a split-shuffle-residual (SSR)-based CNN that can learn features automatically from wood images for real-time classification of rubber wood boards. Specifically, we introduce an SSR module that combines channel split and shuffle operations with residual structure to reduce the computation cost while maintaining high classification accuracy. In each module, the input is split into two low-dimensional branches, and the channel shuffle operation is used to enable the information communication between the input and the two separated branches, which is regarded as the feature reuse that enlarges network capacity without increasing complexity. The comprehensive experiments demonstrate that our algorithm outperforms other traditional classification methods and the state-of-the-art deep learning classification networks, yielding an accuracy of 94.86%. Furthermore, the analysis of running time indicates that the SSR-based CNN can be employed for wood classification in real time, which takes only 26.55 ms to handle a single image.

关键词： Rubber Image color analysis Feature extraction Real-time systems Machine learning Image resolution Cameras CNN deep learning image classification real time rubber wood

来源：评论

学校读者我要写书评

暂无评论

Viewpoints Planning for Active 3-D Reconstruction of Profiled Blades Using Estimated Occupancy Probabilities (EOP)

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2021年第5期68卷 4109-4119页

作者： Peng, Weixing Wang, Yaonan Miao, Zhiqiang Feng, Mingtao Tang, Yongpeng Hunan Univ Coll Elect & Informat Engn Changsha 410082 Peoples R China Natl Engn Lab Robot Visual Percept & Control Tech Changsha 410082 Peoples R China

Reconstructing 3-D models of blades plays an increasingly important role in manufacturing. However, the scanning equipment cannot acquire a complete model of a blade with one scanning due to its discontinuous and complex spatial surface. How to plan the viewpoints in presence of the thin walled and free-form properties of blades is a challenging task. In this article, we propose a novel viewpoint planning algorithm using estimated occupancy probabilities. Existing viewpoint planning methods do not consider the enough overlaps, which are important for data registration. We predict surface overlaps using an estimated OctoMap. OctoMap is an efficient probabilistic framework for 3-D occupancy grid mapping. However, the occupancy probabilities of occluded voxels in the original OctoMap remain unknown, which makes it impossible to calculate the overlap of candidate viewpoints. Hence, a recursive Bayesian filter is designed to estimate occupancy probabilities of occluded voxels. With more specific occupancy probabilities, the overlap of a viewpoint is predicted by the ray tracing technology. Experiments on four different profiled blades synthetic datasets show that our algorithm outperforms existing methods in terms of controlling overlap rate. The efficiency of our method is confirmed by real world experiments with low registration failure frequency in reconstruction.

关键词： Blades Surface reconstruction Planning Three-dimensional displays Surface topography Manipulators Market research Autonomous reconstruction next-best-view profiled blades recursive state estimation

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：