检索结果-内蒙古大学图书馆

Alternative Underwater image Restoration Based on Unsupervised Learning and Autoencoder with Degradation Block 17

Alternative Underwater Image Restoration Based on Unsupervis...

18th Latin American Robotics symposium (LARS) / 12th brazilian symposium on Robotics (SBR) / 11th Workshop on Robotics in Education (WRE)

作者： Mello Jr, Claudio D. Moreira, Bryan U. Drews-Jr, Paulo L. J. Botelho, Silvia C. Univ Fed Rio Grande FURG Ctr Ciencias Comp NAUTEC Rio Grande RS Brazil

ISBN: (纸本)9780738111537

Underwater image restoration represents a challenge to computer vision and image processing based on machine learning. Recent methodologies to tackle this problem are based on learning. However, the lack of paired image datasets leads the researches to synthesize datasets. We present a new unsupervised learning algorithm that no requires paired dataset to train an encoder-decoder-like neural network for underwater image restoration. Encoder-decoder network learns to represent its input data in a latent representation and reconstruct then in the output. During the training stage, our algorithm applies the output image to a degradation block based on image formation model that reinforces its degradation. The degraded and input images are matched using a loss function. After the training process, we are able to obtain a restored image from the decoder. We focus on underwater inspection and our method relies on small dataset and a light neural network. Underwater images are used to evaluate and validate our algorithm. The qualitative and quantitative results show the improvement provided by our method.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

CHOPIN: Scalable graphics Rendering in Multi-GPU Systems via Parallel image Composition

CHOPIN: Scalable Graphics Rendering in Multi-GPU Systems via...

引用

IEEE symposium on High-Performance computer Architecture

作者： Xiaowei Ren Mieszko Lis The University of British Columbia

The appetite for higher and higher 3D graphics quality continues to drive GPU computing requirements. To satisfy these demands, GPU vendors are moving towards new architectures, such as MCM-GPU and multi-GPUs, that connect multiple chip modules or GPUs with high-speed links (e.g., NVLink and XGMI) to provide higher computing capability. Unfortunately, it is not clear how to adequately parallelize the rendering pipeline to take advantage of these resources while maintaining low rendering latencies. Current implementations of Split Frame Rendering (SFR) are bottlenecked by redundant computations and sequential inter-GPU synchronization, and fail to scale as the GPU count increases. In this paper, we propose CHOPIN, a novel SFR scheme for multi-GPU systems that exploits the parallelism available in image composition to eliminate the bottlenecks inherent to existing solutions. CHOPIN composes opaque sub-images out-of order, and leverages the associativity of image composition to compose adjacent sub-images of transparent objects asynchronously. To mitigate load imbalance across GPUs and avoid inter-GPU network congestion, CHOPIN includes two new scheduling mechanisms: a draw-command scheduler and an image composition scheduler. Detailed cycle-level simulations on eight real-world game traces show that, in an 8-GPU system, CHOPIN offers speedups of up to 1.56× (1.25× gmean) compared to the best prior SFR implementation.

关键词： Three-dimensional displays Pipelines graphics processing units computer architecture Parallel processing Rendering (computer graphics) Synchronization

来源：评论

学校读者我要写书评

暂无评论

Development of a Robotic System with Movements Based on computer Vision Detection 5th

Development of a Robotic System with Movements Based on Comp...

引用

5th brazilian Technology symposium, BTSym 2019

作者： de Souza, Gabriel Gomes de Lima, Bruno Luis Soares dos Santos, Rodrigo Vieira de Almeida, Fábio Jesus Moreira Engineering School Mackenzie Presbyterian University São Paulo Brazil

ISBN: (纸本)9783030575472

Nowadays, with the increasing use of robots, and the high level of education required to program and interact with these machines, it becomes necessary to develop platforms that make the human–machine interaction simpler and more precise. In the present work, a control system was developed for robotic manipulators based on computer vision and image processing. An algorithm was developed in Python based on the OpenCV open-source library, which identifies gesture commands captured by a webcam and, from a user interface, transforms them into specific movements to be performed by a prototype manipulator that was designed and built by the authors. The prototype, built-in MDF, has a range of 180 mm and 3 degrees of freedom, and its movements are made from the activation of 3 step motors. The activation of the motors takes place from a firmware that was developed for the Arduino microcontroller, which receives the gestural command that was detected. It was possible to establish critical operating conditions of the developed system in relation to the ambient brightness, distance from the operator to the webcam and the mechanical accuracy of the manipulator's motor response. From the technologies applied in this work, it may be possible to develop control systems by gestures for other robotic mechanisms. © 2021, Springer Nature Switzerland AG.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

Amber: A 367 GOPS, 538 GOPS/W 16nm SoC with a Coarse-Grained Reconfigurable Array for Flexible Acceleration of Dense Linear Algebra

Amber: A 367 GOPS, 538 GOPS/W 16nm SoC with a Coarse-Grained...

引用

symposium on VLSI Technology

作者： Alex Carsello Kathleen Feng Taeyoung Kong Kalhan Koul Qiaoyi Liu Jackson Melchert Gedeon Nyengele Maxwell Strange Keyi Zhang Ankita Nayak Jeff Setter James Thomas Kavya Sreedhar Po-Han Chen Nikhil Bhagdikar Zachary Myers Brandon D’ Agostino Pranil Joshi Stephen Richardson Rick Bahr Christopher Torng Mark Horowitz Priyanka Raina Stanford University CA USA

Amber is a system-on-chip (SoC) with a coarse-grained reconfigurable array (CGRA) for acceleration of dense linear algebra applications such as machine learning (ML), image processing, and computer vision. It achieves a peak energy efficiency of 538.0 INT16 GOPS/W and 483.3 BFloat16 GFLOPS/W. We maximize CGRA utilization and minimize reconfigurability overhead through (1) dynamic partial reconfiguration of the CGRA that enables higher resource utilization by allowing multiple applications to run at once, (2) efficient streaming memory controllers supporting affine access patterns, and (3) low-overhead transcendental and complex arithmetic operations. Compared to a CPU, a GPU, and an FPGA, Amber achieves up to 3902x, 152x, and 88x better energy-delay product (EDP).

关键词： Memory management graphics processing units Linear algebra Very large scale integration Streaming media Throughput Central processing Unit

来源：评论

学校读者我要写书评

暂无评论

The Development of VR Technology and computer Technology Integration Application

The Development of VR Technology and Computer Technology Int...

引用

Advances in Informatics, Electronics and Education (ISAIEE), International symposium on

作者： Li Zhu Yan Li Lu Bai Qingdi Yu Mengqi Li Jiangxi Science and Technology Normal University Nanchang China

With the progress and development of science and technology, virtual reality(VR) technology has been widely used in military, medical, aerospace, architectural design, entertainment and other fields. VR technology is a comprehensive computer graphics technology, which is composed of multimedia technology, human It is a technology developed by a variety of science and technology such as computer interaction technology, network technology, stereoscopic display technology and simulation technology. This paper starts with the product characteristics of VR, studies and summarizes the characteristics that should be possessed at all levels in the integration of VR technology and computer, including composition characteristics, experience characteristics, technical characteristics and application characteristics, etc. The technical characteristics of VR products, and the research on VR interactive input methods. This paper systematically summarizes the interactive input characteristics of VR technology and computer technology, and then combines the traditional user interface design theories and compares the differences and commonalities between VR interfaces and traditional interfaces, and proposes information display strategies with VR characteristics. Interface presentation strategy and visual design strategy. The final results of the study show that, comparing the scores of the experimental group and the control group, the scores of the experimental group are higher than those of the control group. Therefore, VR technology can help to improve teaching results in classroom teaching.

关键词： Technological innovation Solid modeling Statistical analysis Military computing Stereo image processing Education User interfaces

来源：评论

学校读者我要写书评

暂无评论

Exploring Double Cross Cyclic Interpolation in Unpaired image-to-image Translation 32

Exploring Double Cross Cyclic Interpolation in Unpaired Imag...

引用

32nd SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI) / symposium on Virtual and Augmented Reality (SVR)

作者： Lopez, Jorge Mauricio, Antoni Camara, Guillermo Univ Catolica San Pablo Dept Comp Sci Arequipa Peru Univ Fed Ouro Preto Dept Comp Sci Ouro Preto MG Brazil

ISBN: (纸本)9781728152271

The unpaired image-to-image translation consists of transferring a sample a in the domain A to an analog sample b in the domain B without intensive pixel-to-pixel supervision. The current vision focuses on learning a generative function that maps both domains but ignoring the latent information, although its exploration is not explicit supervision. This paper proposes a cross-domain GAN-based model to achieve a bi-directional translation guided by latent space supervision. The proposed architecture provides a double-loop cyclic reconstruction loss in an exchangeable training adopted to reduce mode collapse and enhance local details. Our proposal has outstanding results in visual quality, stability, and pixel-level segmentation metrics over different public datasets.

关键词： Cross domain interpolation Latent space exploration Unpaired image to image Translation

来源：评论

学校读者我要写书评

暂无评论

Quality of Experience of Immersive Media – New Challenges 23

Quality of Experience of Immersive Media – New Challenges

引用

Proceedings of the 29th brazilian symposium on Multimedia and the Web

作者： Mylene C.Q. Farias Computer Science Texas State University USA

ISBN: (纸本)9798400709081

In the past decade, significant progress in imaging and computing technologies has unleashed the creation of more accurate representations of the physical world, enabling immersive and interactive experiences that more closely resemble reality [1]. As a consequence, immersive applications have attracted a lot of interdisciplinary attention, with the development of multimodal human-computer interactions that allow users to fully immerse themselves within realistic or virtual environments or to interact with real/virtual elements seamlessly blended with the physical world [6]. Immersive experiences can be found at different points along the “virtuality continuum,” ranging from photorealistic settings, through mixed reality approaches, to completely virtual environments. In this scenario, high-speed connections and high-quality imaging systems are essential for the development of next-generation immersive experiences and applications in areas such as healthcare, education/training, arts & entertainment, remote work, marketing, and automotive. But the success of these emerging applications will depend on the quality of experience (QoE) they provide users [5]. As defined by Qualinet [2], QoE refers to the “degree of delight or annoyance of applications or services resulting from the fulfillment of his or her expectations with respect to the utility and/or enjoyment of the application or service in the light of the users personality and current state.” For immersive technologies, immersive media experiences (IMEx) extend the concept of QoE by encompassing elements such as the sense of presence, immersion, and motion sickness, among others [7]. Both QoE and IMEx are shaped by three influencing factors (IF): the system, the context, and the human user. For immersive experiences, the system IF plays an important role, affecting immersion, presence, and interaction itself. This impact has been extensively studied in the literature, with several studies analyzing the effect of

关键词： image processing immersive media light lields machine learning point clouds quality of experience virtual reality

来源：评论

学校读者我要写书评

暂无评论

NIID-Net: Adapting Surface Normal Knowledge for Intrinsic image Decomposition in Indoor Scenes

引用

IEEE TRANSACTIONS ON VISUALIZATION AND computer graphics 2020年第12期26卷 3434-3445页

作者： Luo, Jundan Huang, Zhaoyang Li, Yijin Zhou, Xiaowei Zhang, Guofeng Bao, Hujun Zhejiang Univ State Key Lab CAD&CG Hangzhou Peoples R China ZJU SenseTime Joint Lab 3D Vis Hangzhou Peoples R China

Intrinsic image decomposition, i.e.. decomposing a natural image into a reflectance image and a shading image, is used in many augmented reality applications for achieving better visual coherence between virtual contents and real scenes. The main challenge is that the decomposition is ill-posed. especially in indoor scenes where lighting conditions are complicated. while real training data is inadequate. To solve this challenge, we propose NIID-Net, a novel learning-based framework that adapts surface normal knowledge for improving the decomposition. The knowledge learned from relatively more abundant data for surface normal estimation is integrated into intrinsic image decomposition in two novel ways. First, normal feature adapters are proposed to incorporate scene geometry features when decomposing the image. Secondly, a map of integrated lighting is proposed for propagating object contour and planarity information during shading rendering. Furthermore, this map is capable of representing spatially-varying lighting conditions indoors. Experiments show that NIID-Net achieves competitive performance in reflectance estimation and outperforms all previous methods in shading estimation quantitatively and qualitatively. The source code of our implementation is released at https://***/zju3dv/NIIP-Net.

关键词： Intrinsic image decomposition image processing augmented reality

来源：评论

学校读者我要写书评

暂无评论

PATTERN-BASED AUGMENTED REALITY APPLICATION for the DISSEMINATION of CULTURAL HERITAGE 28

PATTERN-BASED AUGMENTED REALITY APPLICATION for the DISSEMIN...

引用

28th CIPA symposium on Great Learning and Digital Emotion, CIPA 2021

作者： Boutsi, A.-M. Verykokou, S. Soile, S. Ioannidis, C. Laboratory of Photogrammetry School of Rural Surveying and Geoinformatics Engineering NTUA Greece

Augmented Reality (AR) is more than an added value for Cultural Heritage (CH);it is vital for its sustainability, promotion and dissemination, increasing accessibility in CH even during difficult periods of time, like the Covid-19 pandemic. In order to be meaningful and engaging, an AR application should have the following characteristics: easiness of use, high-quality representations and compatibility. This paper presents a marker-less mobile AR application for the display and inspection of high-resolution 3D cultural assets, overlayed on a particular location in the real-world scene. Instead of predefined markers, an image captured by the user is exploited as a pattern for real-time feature matching, pose estimation and scene augmentation. Our approach is based on pure computer vision and photogrammetric techniques, implemented using native C++ and Java code for Android mobile platforms. It is built with the use of the OpenCV library and the OpenGL ES graphics API without any dependencies of AR Software Development Kits (SDKs). Therefore, it supports cross-vendor portability regarding mobile model devices and hardware specifications. The evaluation of the developed application examines the performance of various matching techniques and the overall responsiveness of processing and 3D rendering on mid-range and low-end smartphones. The results showcase the reliability and responsiveness of the pattern recognition as well as the potential of the 3D graphics engine to render and overlay complex 3D models balancing between visual quality and time. The proposed methodology is applied to the Ciborium of the church of St. Charalabos, located at St. Stephen's Monastery in Meteora, Greece. © 2021 A.-M. Boutsi et al.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Face Recognition Using LBP on an image Transformation Based on Complex Network Degrees 32

Face Recognition Using LBP on an Image Transformation Based ...

引用

32nd SIBGRAPI Conference on graphics, Patterns and images (SIBGRAPI) / symposium on Virtual and Augmented Reality (SVR)

作者： Boas da Costa, Murilo Villas Villar Couto, Cynthia Martins Couto, Leandro Nogueira Univ Fed Uberlandia Fac Comp Uberlandia MG Brazil Univ Sao Paulo USP Sao Carlos Inst Phys IFSC Sao Paulo Brazil

ISBN: (纸本)9781728152271

Automated visual face recognition involves acquiring descriptive features from the image. Local Binary Patterns (LBP) is a powerful method to that end, capably characterizing local features. An crucial limitation of LBP, however, is that the feature vector's size becomes unmanageable when the method employed on even moderately large regions. In order to describe larger scale features, this work proposes a descriptor based on applying the LBP histogram applied to an image transformation based on node degree data derived from a complex network representation of the original image. The complex network generation heuristic and parameters are discussed. The complex network representation is shown to be able to condense larger scale image patterns into a local value that can be handled by LBP. LBP applied to this image transformation yields results that outperform LBP. We validate our proposed approach by applying our method to a face recognition task using three challenging databases. Results demonstrate that, for a large enough complex network generation radius, our method consistently outperforms LBP, while using a feature vector of the same size.

关键词： Complex networks Local binary patterns Texture recognition

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：