检索结果-内蒙古大学图书馆

Normal-Based Bas-Relief Modelling via Near-Lighting Photometric Stereo

COMPUTER GRAPHICS FORUM 2020年第1期39卷 204-219页

作者： Wei, M. Song, Z. Nie, Y. Wu, J. Ji, Z. Guo, Y. Xie, H. Wang, J. Wang, F. L. Nanjing Univ Aeronaut & Astronaut Sch Comp Sci & Technol Nanjing Peoples R China Nanjing Univ State Key Lab Novel Software Technol Nanjing Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen Peoples R China Hangzhou Dianzi Univ Sch Comp Sci & Technol Hangzhou Peoples R China Educ Univ Hong Kong Dept Math & Informat Technol Hong Kong Peoples R China Open Univ Hong Kong Sch Sci & Technol Hong Kong Peoples R China

We present a near-lighting photometric stereo (NL-PS) system to produce digital bas-reliefs from a physical object (set) directly. Unlike both the 2D image and 3D model-based modelling methods that require complicated interactions and transformations, the technique using NL-PS is easy to use with cost-effective hardware, providing users with a trade-off between abstract and representation when creating bas-reliefs. Our algorithm consists of two steps: normal map acquisition and constrained 3D reconstruction. First, we introduce a lighting model, named the quasi-point lighting model (QPLM), and provide a two-step calibration solution in our NL-PS system to generate a dense normal map. Second, we filter the normal map into a detail layer and a structure layer, and formulate detail- or structure-preserving bas-relief modelling as a constrained surface reconstruction problem of solving a sparse linear system. The main contribution is a WYSIWYG (i.e. what you see is what you get) way of building new solvers that produces multi-style bas-reliefs with their geometric structures and/or details preserved. The performance of our approach is experimentally validated via comparisons with the state-of-the-art methods.

关键词： compression algorithms modelling computational geometry curves and surfaces

来源：评论

学校读者我要写书评

暂无评论

Binary Outer Product Expansion of Convolutional Kernels

引用

IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING 2020年第4期14卷 871-883页

作者： Sun, Zhaohui H. Kitware Inc Clifton Pk NY 12065 USA

Convolutional neural networks (CNNs) have found great success in many artificial intelligence applications. At the heart of a CNN is the operation of convolution between multi-channel data and learned kernels. It is usually implemented as a floating-point large matrix multiplication, a major bottleneck of computational speed and memory usage. In this paper, we propose a binary outer product expansion (BOPE) method to represent a kernel matrix or tensor as a weighted sum of the outer products between binary vectors of values +1 or -1. This allows for network compression and simplified computation at the same time. Our theoretical analysis shows such a decomposition converges to the original matrix given a sufficient number of binary vectors. We present computational methods to estimate outer product weights using either optimized or random binary base vectors. Significant data compression can be achieved for a highly redundant matrix, since weights and binary vectors require less storage than array elements. In addition, most floating-point multiplication in matrix convolution can be replaced by addition and binary XOR, lessening computation and memory requirements. We propose a compact convolutional layer in which highly redundant convolutional kernels are projected onto binary vectors, and represented as a weighted sum of outer products. It is shown that the number of weights in AlexNet, VGG-19 and ResNet-50 can be reduced 3.45, 6.87 and 2.95 times respectively with less than a 1% loss in the top-1 and top-5 classification accuracy on ImageNet, and MobileNetV2 can be reduced 2.31 times with a 2% loss. Compared to the standard CNN, this compact convolutional network has fewer trainable weights, is better regularized, and is easier to train from fewer training samples. Therefore, it is particularly suited for devices with limited computation, memory, and battery power.

关键词： Convolution Matrix decomposition Kernel Standards Convolutional neural networks Data compression Training compression algorithms convolutional neural networks deep learning mobile computing

来源：评论

学校读者我要写书评

暂无评论

An Energy-Efficient Implementation of Group Pruned CNNs on FPGA

引用

IEEE ACCESS 2020年 8卷 217033-217044页

作者： Pang, Wei Wu, Chenglu Lu, Shengli Southeast Univ Natl ASIC Syst Engn Res Ctr Nanjing 210096 Peoples R China

In recent years, convolutional neural network (CNN)-based artificial intelligence algorithms have been widely applied to object recognition and image classification tasks. However, the high performance of convolutional neural networks comes at the cost of high-intensity computing and enormous numbers of parameters, which pose substantial challenges to terminal implementations. An end-to-end FPGA-based accelerator is proposed in this work that efficiently processes fine-grained pruned CNNs. A group pruning algorithm with group sparse regularization (GSR) is introduced to solve internal buffer misalignments and load imbalances of the accelerator after fine-grained pruning. A mathematical model of accelerator access and transmission is established to explore the optimal design scale and calculation mode. The accelerator is optimized by designing sparse processing elements and by scheduling the on- and off-chip buffers. The proposed approach reduces the computation of a state-of-the-art large-scale CNN, VGG16, by 86.9% with an accuracy loss on CIFAR-10 of only 0.48%. The accelerator achieves 188.41 GOPS at 100 MHz and consumes 8.15 W when implemented on a Xilinx VC707, making it more energy-efficient than previous approaches.

关键词： Field programmable gate arrays Mathematical model Optimization Energy efficiency Filtering algorithms Convolutional neural networks Feature extraction Neural network hardware accelerator architectures compression algorithms field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

Compressed Holistic ConvNet Representations for Detecting Loop Closures in Dynamic Environments

引用

IEEE ACCESS 2020年 8卷 60552-60574页

作者： Wang, Shuo Lv, Xudong Liu, Xiaomin Ye, Dong Harbin Inst Technol Sch Instrumentat Sci & Engn Harbin 150001 Peoples R China Harbin Inst Technol Sch Elect & Informat Engn Harbin 150001 Peoples R China Jiamusi Univ Informat & Elect Technol Inst Jiamusi 154002 Peoples R China

Detecting loop closures in dynamic environments is a severe challenge for the simultaneous localization and mapping (SLAM) system. Convolutional neural networks (ConvNet) could provide high-level and abstract representations extracted directly from images as image descriptors. Some novel ConvNet-based methods have been presented. In dynamic environments, they perform better than the state-of-the-art methods which use hand-crafted features. In this paper, (1) We proposed a flexible loop closure detection workflow based on the holistic representations;(2) In this workflow, a post-processing method is applied to the raw holistic ConvNet representations for redundant information compression;(3) In addition, a compression ratio is introduced in (2) to determine how much information will be retained depending on background change and moving objects. We evaluated our workflow in four open datasets. The experimental results demonstrate that the proposed workflow performs better than many state-of-the-art methods and ConvNet-based approaches.

关键词： Loop closure detection holistic representations descriptors convolutional neural network compression algorithms

来源：评论

学校读者我要写书评

暂无评论

A novel algorithm for high compression rates focalized on electrical power quality signals

引用

HELIYON 2021年第3期7卷 e06475页

作者： Ruiz, Milton Simani, Silvio Inga, Esteban Jaramillo, Manuel Univ Politecn Salesiana Quito Ecuador BUnivers Ferrara Ferrara Italy

This research proposes a high-performance algorithm for the compression rate of electrical power quality signals, using wavelet transformation. To manage the massive amount of data the telecommunications networks are constantly acquiring it is necessary to study techniques for data compression, which will save bandwidth and reduce costs extensively by avoiding having massive data storage facilities. First biorthogonal wavelet level six transform is applied, however after compression, the reconstructed signal will have a different amplitude and it will be shifted when compared to the original one. Then, normalization is used (for amplitude correction between the original signal and reconstructed one) by multiplying the reconstructed signal by the result of the division between the original signal maximum magnitude and the reconstructed signal maximum magnitude. Thirdly, the ripple in the reconstructed signal is eliminated by applying a moving average filter. Finally, the shifting is corrected by finding the difference between the maximum points in a cycle of the original signal and the reconstructed one. After the compression algorithm was performed the best rates are 99.803% for compression rate, RTE 99.9479%, NMSE 0.000434, and Cross-Correlation 0.999925. Finally, this works presents two new performance criteria, compression time and recovery time, both of them in a real scenario will determinate how fast the algorithm can perform.

关键词： compression algorithms Data compression Data processing Power quality (PQ) Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

A Low-Overhead Encoding Scheme to Extend the Lifetime of Nonvolatile Memories

引用

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 2020年第10期39卷 2516-2529页

作者： Feng, Dan Xu, Jie Hua, Yu Tong, Wei Liu, Jingning Li, Chunyan Chen, Yiran Huazhong Univ Sci & Technol Sch Comp Sci & Technol Minist Educ ChinaEngn Res Ctr Data Storage Syst Wuhan Natl Lab OptoelectKey Lab Informat Storage Wuhan 430074 Peoples R China Duke Univ Dept Elect & Comp Engn Durham NC 27708 USA

Emerging nonvolatile memories (NVMs) are promising to replace DRAM as main memory. However, NVMs suffer from limited write endurance and high write energy. Encoding method reduces the bit flips of NVMs by exploiting additional tag bits to encode the data. The effect of the encoding method is limited by the capacity overhead of the tag bits. In this article, we propose to exploit the space saved by compression to store the tag bits of the encoding method. We observe that the saved space size of each compressed cache line varies, and different encoding methods have different tradeoffs between capacity overhead and effect. To fully exploit the space saved by compression for improving lifetime, we select the proper encoding method according to the saved space size. To improve the compression coverage and compression ratio, we select an efficient compression scheme from two compression algorithms and provide more space for data encoding. Still, some data patterns cannot be compressed by any compression technique. We use the Flip-N-Write with 3.1% capacity overhead to encode uncompressible cache lines. The experimental results show that our scheme reduces the bit flips by 32.5%, decreases the energy consumption by 22.6% and improves the lifetime by 69.9% with 3.5% capacity overhead.

关键词： Encoding Phase change materials Nonvolatile memory Random access memory Data compression Resistance compression algorithms Bit flips compression encoding lifetime nonvolatile memories (NVMs)

来源：评论

学校读者我要写书评

暂无评论

Adaptive Header compression Algorithm in Narrow Band Internet of Things

Adaptive Header Compression Algorithm in Narrow Band Interne...

引用

IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)

作者： Hao Liu Chenhong Zhou Tieyi Yang College of Microelectronics Southeast University Wuxi China

ISBN: (数字)9781728180281

ISBN: (纸本)9781728180298

As an Internet of Things (IOT) network to realize the Internet of Everything, Narrowband Internet of Things (NB-IoT) is widely applied in large-scale small data services, such as meter reading and streetlamp control. Currently, NB-IoT protocols are carried by complete IP, realize network transmission by using the TCP/UDP transport protocols, and implement header compression through robust header compression (ROHC). The two-way reliable R, two-way optimization O, and one-way U modes of the ROHC algorithm have the drawbacks of a high feedback cost, dependence of the feedback effect on the network quality, and desynchronization of decompressor. Therefore, an optimized Markov chain prediction model was added to the U mode of ROHC, and an adaptive header compression algorithm (ROHC-M), which could adjust the state of compression according to the channel conditions, was developed. Compared with the one-way mode algorithm, the proposed ROHC-M algorithm decreased the header size by 0.96 bytes on average and increased the throughput by 10%.

关键词： Predictive models Markov processes Prediction algorithms Internet of Things IP networks compression algorithms Narrowband

来源：评论

学校读者我要写书评

暂无评论

Octree-Based compression for Geiger-Mode LiDAR

Octree-Based Compression for Geiger-Mode LiDAR

引用

IEEE National Conference on Aerospace and Electronics (NAECON)

作者： Brenton Sundlie Applied Sensing Division University of Dayton Research Institute Dayton OH USA

ISBN: (纸本)9781665448604

This paper presents an octree-based compression algorithm for LiDAR point cloud data. This solution is presented as an alternative to LASzip, the current state-of-the-art in LiDAR compression, that provides an average 60% higher compression ratio on Geiger-mode data, and is capable of natively compressing both LAS and BPF file formats.

关键词： Point cloud compression Band-pass filters Laser radar Conferences Aerospace electronics compression algorithms

来源：评论

学校读者我要写书评

暂无评论

A Novel Dictionary Management Scheme of LZW compression Algorithm Based on Insignificant Dictionary Area

A Novel Dictionary Management Scheme of LZW Compression Algo...

引用

IEEE International Conference on Signal and Image Processing (ICSIP)

作者： Xiaoyong Cheng Bing Li Jiaxin Wu Wenhui Li Chao Luo Jiayi Su School of Microelectronics Southeast University School of Cyber Science and Engineering Southeast University School of Software Engineering Southeast University Southeast University Shenzhen Research Institute China

ISBN: (纸本)9781665446006

In order to avoid the possible degradation of the compression ratio, the dictionary management scheme is employed when the dictionary of Lempel-Ziv-Welch (LZW) algorithm is filled. Dictionary reset (DR) and least recently used (LRU) are two dictionary management schemes widely used. However, DR trades compression ratio for less time overhead and LRU obtains a high compression ratio while time and memory are sacrificed. This paper proposes a novel insignificant dictionary area LZW (IDA-LZW) which has a high and stable compression ratio while maintaining acceptable compression time and excellent decompression time. The proposed dictionary management scheme called IDA consists of dictionary partition and impact factor (IF) which returns the dictionary area should be cleared for new entries. Three variants of IDA-LZW and LZW with DR and LRU are implemented and show that the proposed scheme achieves the best average compression while consuming reasonable resources. Furthermore, comparisons are made with the results in the paper recently published to prove the proposed scheme is valuable.

关键词： Degradation Dictionaries Image coding Conferences Memory management compression algorithms

来源：评论

学校读者我要写书评

暂无评论

Lightweight Run-Time Working Memory compression for Deployment of Deep Neural Networks on Resource-Constrained MCUs

Lightweight Run-Time Working Memory Compression for Deployme...

引用

Asia and South Pacific Design Automation Conference

作者： Zhepeng Wang Yawen Wu Zhenge Jia Yiyu Shi Jingtong Hu University of Pittsburgh Pittsburgh Pennsylvania US University of Notre Dame Notre Dame Indiana US

ISBN: (数字)9781450379991

ISBN: (纸本)9781728180571

This work aims to achieve intelligence on embedded devices by deploying deep neural networks (DNNs) onto resource-constrained microcontroller units (MCUs). Apart from the low frequency (e.g., 1-16 MHz) and limited storage (e.g., 16KB to 256KB ROM), one of the largest challenges is the limited RAM (e.g., 2KB to 64KB), which is needed to save the intermediate feature maps of a DNN. Most existing neural network compression algorithms aim to reduce the model size of DNNs so that they can fit into limited storage. However, they do not reduce the size of intermediate feature maps significantly, which is referred to as working memory and might exceed the capacity of RAM. Therefore, it is possible that DNNs cannot run in MCUs even after compression. To address this problem, this work proposes a technique to dynamically prune the activation values of the intermediate output feature maps in the runtime to ensure that they can fit into limited RAM. The results of our experiments show that this method could significantly reduce the working memory of DNNs to satisfy the hard constraint of RAM size, while maintaining satisfactory accuracy with relatively low overhead on memory and run-time latency.

关键词： Runtime Design automation Microcontrollers Neural networks Random access memory Read only memory compression algorithms

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：