检索结果-内蒙古大学图书馆

International Conference on Applications and Techniques in Cyber Intelligence, ATCI 2018

作者： Yu, Zhang School of Mechano-Electronic Engineering Xidian University Xi’an China

ISBN: (纸本)9783319987750

To achieve higher requirements for industrial robots in practical applications, the image pre-processing algorithms, key feature extraction and recognition algorithms, and trajectory planning and generation algorithms for wheel hub images were studied to realize image feature of wheel hub and pre-processing before recognition. Then, the problem of misunderstanding in corner detection was solved. The identification of wheel hub images, the planning and generation of the processing trajectory of wheel hub were completed. Finally, this research was applied to the industrial robot image recognition automatic processing system. The experiment verified the practical feasibility of the industrial robot trapped image recognition automatic processing system. It is concluded that the future intelligent robot can better serve human beings. © Springer Nature Switzerland AG 2019.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

Analysis of sub-pixel laser spot detection in laser triangulation systems 11

Analysis of sub-pixel laser spot detection in laser triangul...

引用

Conference on Optical Measurement systems for Industrial Inspection xi held at SPIE Optical Metrology Symposium

作者： Kienle, Patrick Nallar, Elif Koehler, Michael H. Jakobi, Martin Koch, Alexander W. Tech Univ Munich Inst Measurement Syst & Sensor Technol Theresienstr 90-N5 D-80333 Munich Germany

ISBN: (数字)9781510627925

ISBN: (纸本)9781510627925

Laser spot detection is an important step of laser triangulation and limits its accuracy. Common methods to determine the center position include circle fitting, the Hough transformation, the gray centroid method or Gaussian fitting. As these algorithms were often tested in different set-ups and under various conditions, they generally lead to diverse results. The aim of this contribution is to investigate the algorithms in a more objective and realistic approach. After a short introduction to laser triangulation, basic information about laser spot center detection is given. Fundamental limitations of the laser spot detection are then considered and analyzed. The investigations are followed by evaluations of measurements in a real laser triangulation setup. Through this approach we could show that the influence of the spatial quantization and the quantization due to the limited bit depth of the detector can be in a similar range as the deviation due to speckle noise in the image. By using adapted image processing steps, the performance of the laser spot center determination could be improved significantly.

关键词： laser spot detection laser triangulation distance measurement image processing sub-pixel laser point detection

来源：评论

学校读者我要写书评

暂无评论

An incremental compression storage algorithm for slicing 3D model of DLP Printer

An incremental compression storage algorithm for slicing 3D ...

引用

第三十九届中国控制会议

作者： Yaojun Ma Wenhua Guo Chenlong He Tao Chen xi Sun State Key Laboratory for Manufacturing Systems Engineering Xi'an Jiaotong University

This paper presents a new binary image lossless compression algorithm for Digital Light processing（DLP） *** the continuity of 3D model slicing images and the features of the pixels in slicing images, this algorithm is characterized by delta-encoding and two-stage compression to facilitate image compression, which is simple to implement. Compared with other algorithms used for image compression, the proposed one achieves the best performance when the same test cases are treated.

关键词： Additive manufacturing DLP printers Data compression image processing

来源：评论

学校读者我要写书评

暂无评论

An incremental compression storage algorithm for slicing 3D model of DLP Printer

An incremental compression storage algorithm for slicing 3D ...

引用

Chinese Control Conference (CCC)

作者： Yaojun Ma Wenhua Guo Chenlong He Tao Chen xi Sun State Key Laboratory for Manufacturing Systems Engineering Xi’an Jiaotong University Xi’an National Innovation Institute of Additive Manufacturing Université de technologie Belfort-Montbéliard

ISBN: (数字)9789881563903

ISBN: (纸本)9781728165233

This paper presents a new binary image lossless compression algorithm for Digital Light processing (DLP) printers. Considering the continuity of 3D model slicing images and the features of the pixels in slicing images, this algorithm is characterized by delta-encoding and two-stage compression to facilitate image compression, which is simple to implement. Compared with other algorithms used for image compression, the proposed one achieves the best performance when the same test cases are treated.

关键词： image coding Printers Solid modeling Software Three-dimensional displays Printing Electronic mail

来源：评论

学校读者我要写书评

暂无评论

A Hardware-Efficient Post-processing Algorithm for Motion Compensated Frame Rate Up-Conversion

A Hardware-Efficient Post-Processing Algorithm for Motion Co...

引用

IEEE International Symposium on Circuits and systems (IEEE ISCAS)

作者： Wang, Hang Wang, Tiancheng Mi, Yunqi Sun, Hongbin Zheng, Nanning Xi An Jiao Tong Univ Xian 710049 Shaanxi Peoples R China

ISBN: (纸本)9781728103976

Post-processing is an important module in motion compensated frame rate up-conversion design, and has a direct impact on the image quality of interpolated frame. However, how to balance between image quality and computational efficiency is still very challenging for post-processing, especially in hardware design. This paper proposes a hardware-efficient post-processing algorithm which leverages the temporal and spatial constraints to locally refine interpolated pixels. Moreover, we employ the quantization and approximation techniques to further reduce the computational intensity of the proposed post-processing algorithm. The quality of interpolated frame has been greatly improved both in objective and subjective aspects. The proposed post-processing algorithm is extensively evaluated by a set of video test sequences. Evaluation results demonstrate that, compared with the reference designs, the proposed algorithm can improve PSNR by at least 1.69 dB with comparable computational complexity.

关键词： Hardware Optimization Real-time systems image quality Quantization (signal) Interpolation Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

A new nonconvex approach to low-rank matrix completion with application to image inpainting

引用

MULTIDIMENSIONAL systems AND SIGNAL processing 2019年第1期30卷 145-174页

作者： Yu, Yongchao Peng, Jigen Yue, Shigang Xinyang Normal Univ Sch Math & Stat Xinyang 464000 Peoples R China Xi An Jiao Tong Univ Sch Math & Stat Xian 710049 Shaanxi Peoples R China Guangzhou Univ Sch Math & Informat Sci 230 GuangZhou Univ City Outer Ring Rd Guangzhou 510006 Guangdong Peoples R China Univ Lincoln Sch Comp Sci Lincoln LN6 7TS England

The problem of recovering a low-rank matrix from partial entries, known as low-rank matrix completion, has been extensively investigated in recent years. It can be viewed as a special case of the affine constrained rank minimization problem which is NP-hard in general and is computationally hard to solve in practice. One widely studied approach is to replace the matrix rank function by its nuclear-norm, which leads to the convex nuclear-norm minimization problem solved efficiently by many popular convex optimization algorithms. In this paper, we propose a new nonconvex approach to better approximate the rank function. The new approximation function is actually the Moreau envelope of the rank function (MER) which has an explicit expression. The new approximation problem of low-rank matrix completion based on MER can be converted to an optimization problem with two variables. We then adapt the proximal alternating minimization algorithm to solve it. The convergence (rate) of the proposed algorithm is proved and its accelerated version is also developed. Numerical experiments on completion of low-rank random matrices and standard image inpainting problems have shown that our algorithms have better performance than some state-of-art methods.

关键词： Low-rank matrix completion Moreau envelope Proximal alternating minimization image Inpainting

来源：评论

学校读者我要写书评

暂无评论

Addressing Irregularity in Sparse Neural Networks Through a Cooperative Software/Hardware Approach

引用

IEEE TRANSACTIONS ON COMPUTERS 2020年第7期69卷 968-985页

作者： Zeng, xi Zhi, Tian Zhou, Xuda Du, Zidong Guo, Qi Liu, Shaoli Wang, Bingrui Wen, Yuanbo Wang, Chao Zhou, Xuehai Li, Ling Chen, Tianshi Sun, Ninghui Chen, Yunji Chinese Acad Sci Inst Comp Technol ICT State Key Lab Comp Architecture Beijing 100864 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Cambricon Technol Beijing Peoples R China Univ Sci & Technol China Hefei 230052 Peoples R China Chinese Acad Sci Inst Software Beijing 100864 Peoples R China CAS Ctr Excellence Brain Sci & Intelligence Techn Shanghai Res Ctr Brian Sci & Brain Inspired Intel Inst Brain Intelligence Technol Zhangjiang Lab BITZJLab Shanghai Peoples R China

Neural networks have become the dominant algorithms rapidly as they achieve state-of-the-art performance in a broad range of applications such as image recognition, speech recognition, and natural language processing. However, neural networks keep moving toward deeper and larger architectures, posing a great challenge to hardware systems due to the huge amount of data and computations. Although sparsity has emerged as an effective solution for reducing the intensity of computation and memory accesses directly, irregularity caused by sparsity (including sparse synapses and neurons) prevents accelerators from completely leveraging the benefits, i.e., it also introduces costly indexing module in accelerators. In this article, we propose a cooperative software/hardware approach to address the irregularity of sparse neural networks efficiently. Initially, we observe the local convergence, namely larger weights tend to gather into small clusters during training. Based on that key observation, we propose a software-based coarse-grained pruning technique to reduce the irregularity of sparse synapses drastically. The coarse-grained pruning technique, together with local quantization, significantly reduces the size of indexes and improves the network compression ratio. We further design a multi-core hardware accelerator, Cambricon-SE, to address the remaining irregularity of sparse synapses and neurons efficiently. The novel accelerator have three key features: 1) selector modules to filter unnecessary synapses and neurons, 2) compress/decompress modules for exploiting the sparsity in data transmission (which is rarely studied in previous work), and 3) a multi-core architecture with elevated throughput to meet the real-time processing requirement. Compared against a state-of-the-art sparse neural network accelerator, our accelerator is 1.20x and 2.72x better in terms of performance and energy efficiency, respectively. Moreover, for real-time video analysis tasks, Cambricon-SE

关键词： Accelerator architecture deep neural networks sparsity

来源：评论

学校读者我要写书评

暂无评论

基于CEVA XM4 DSP平台D2C算法实时实现

引用

单片机与嵌入式系统应用 2022年第5期22卷 49-52,78页

作者：蒙敏荣王萍西安奥比拓疆科技有限公司西安710075 西安交通大学

深度图像与彩色图像对齐算法将同一时刻深度相机产生的深度图像与彩色图像对齐,其在嵌入式平台的实时实现是3D应用小型化的重要步骤。基于AR9201平台的CEVA XM4 DSP具有低功耗、高计算的特点,本文结合CEVA DSP的指令特点,提出一系列针对... 详细信息

深度图像与彩色图像对齐算法将同一时刻深度相机产生的深度图像与彩色图像对齐,其在嵌入式平台的实时实现是3D应用小型化的重要步骤。基于AR9201平台的CEVA XM4 DSP具有低功耗、高计算的特点,本文结合CEVA DSP的指令特点,提出一系列针对D2C算法的优化方法,使其满足工程指标要求。工程实践结果表明,优化后的D2C算法在系统工程环境中表现良好,该优化算法经过DSP多核并行处理后,分辨率为960P的深度图像与彩色图像对齐,平均帧率达到30 fps,并且对齐精度满足工程需求。此外,该算法的优化方法也为其他图像处理算法在类似嵌入式平台的实时实现提供了参考。

关键词： CEVA DSP 单指令多数据 D2C 矢量化多核并行处理

来源：评论

学校读者我要写书评

暂无评论

image Matching Algorithm based on ORB and K-Means Clustering

Image Matching Algorithm based on ORB and K-Means Clustering

引用

Information Science, Computer Technology and Transportation (ISCTT), International Conference on

作者： Liye Zhang Fudong Cai Jinjun Wang Changfeng Lv Wei Liu Guoxin Guo Huanyun Liu Yixin xing School of Computer Science and Technology Shandong University of Technology Zibo China Electric Power Automation Division Shandong Senter Electronic Zibo China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China Jinan Xintongda Electronic Technology Co. Ltd Jinan China

ISBN: (数字)9781728185750

ISBN: (纸本)9781728185767

With the rapid development of science and technology, image processing technology plays an important role in the field of computer vision. In order to improve the matching speed and real-time requirements, this paper proposes an image matching algorithm based on ORB and K-means clustering, which can effectively improve the accuracy of image feature point location and the accuracy and efficiency of image feature matching, and reduce the time consumption. The algorithm uses sub-pixel interpolation to optimize the traditional ORB algorithm, which improves the accuracy and characteristics of clustering calculation.

关键词： Interpolation Information science image matching Clustering algorithms Transportation Real-time systems Stereo vision

来源：评论

学校读者我要写书评

暂无评论

Hybrid telecentric triangulation sensor system with real-time field-dependent deconvolution 11

Hybrid telecentric triangulation sensor system with real-tim...

引用

Conference on Optical Measurement systems for Industrial Inspection xi held at SPIE Optical Metrology Symposium

作者： Faulhaber, Andreas Gronle, Marc Haist, Tobias Pruss, Christof Baroud, Yousef Osten, Wolfgang Simon, Sven Univ Stuttgart Inst Tech Opt Pfaffenwaldring 9 D-70569 Stuttgart Germany Univ Stuttgart Inst Parallele & Verteilte Syst Univ Str 38 D-70569 Stuttgart Germany

ISBN: (数字)9781510627925

ISBN: (纸本)9781510627925

High-resolution optical inspection techniques typically require expensive imaging systems. One possible approach for reducing the overall cost of such systems is to combine optics of limited performance with digital image restoration techniques. In this contribution, we introduce a new hybrid system based on the combination of a field-programmable-gate-array (FPGA), a large telecentric lens with strong field dependent chromatic aberrations and different types of object-adapted projections for 2D and 3D inspection tasks. The optical design tries to minimize cost and weight by replacing the - typically very large - first refractive group of the object-sided telecentric lens by one thin diffractive optical element. This approach can correct the field-dependent aberrations very well. Unfortunately, strong chromatic aberrations are unavoidable. For restoration, we use digital image processing by means of advanced deconvolution algorithms. The necessary number of operations for the strong field-dependent aberrations is extremely high. We combine algorithmic approaches (convolutions using singular-value decomposition) and parallelization directly on the FPGA to achieve live restoration (15 Hz) for a custom-built image sensor with three megapixels. The power consumption is low and a compact processing unit is realized. This hybrid (digital-optical) imaging system is used for 2D- and 3D inspection based on adaptive triangulation. One approach is based on inverse fringe projection. Ray-tracing based on the sensor setup and a reference CAD-model of the part to be tested is used for computing a fringe mask. This mask is inscribed on a spatial light modulator, which then projects the fringes towards the object. If the object under test is without faults, high-frequency equidistant straight-line fringes will result on the image sensor and low height measurement uncertainties at low lateral resolutions, even for non-cooperative objects, are achievable. The importance of a large de

关键词： hybrid measurement system telecentric imaging diffractive optical element inverse fringe projection real-time deconvolution image enhancement

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：