检索结果-内蒙古大学图书馆

15th International Workshop on design and Architecture for signal and image processing, dasip 2022, held jointly with the 17th International conference on High-Performance Embedded architectures and Compilers, HiPEAC 2022

15th International Workshop on Design and Architecture for S...

引用

15th International Workshop on design and Architecture for signal and image processing, dasip 2022, held jointly with the 17th International conference on High-Performance Embedded architectures and Compilers, HiPEAC 2022

ISBN: (纸本)9783031127472

the proceedings contain 13 papers. the special focus in this conference is on design and Architecture for signal and image processing. the topics include: Exploring Fully Convolutional Networks for the Segmentation of Hyperspectral Imaging Applied to Advanced Driver Assistance Systems;an Adaptable Cognitive Microcontroller Node for Fitness Activity Recognition;towards Real-Time and Energy Efficient Siamese Tracking – A Hardware-Software Approach;Low Latency Architecture design for Decoding 5G NR Polar Codes;Efficient Software and Hardware Implementations of a QCSP Communication System;Dynamic Pruning for Parsimonious CNN Inference on Embedded Systems;DL-CapsNet: A Deep and Light Capsule Network;Comparative Study of Scheduling a Convolutional Neural Network on Multicore MCU;influence of Dataflow Graph Moldable Parameters on Optimization Criteria;QoS Aware design-Time/Run-Time Manager for FPGA-Based Embedded Systems;fixed-Point Code Synthesis Based on Constraint Generation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Face and Face Mask Detection Using Convolutional Neural Network 1

引用

13th International conference on Intelligent Human Computer Interaction (IHCI)

作者： Zainal, Muhammad Mustaqim Ambar, Radzi Abd Wahab, Mohd Helmy Poad, Hazwaj Mhd Abd Jamil, Muhammad Mahadi Choon, Chew Chang Univ Tun Hussein Onn Malaysia Fac Elect & Elect Engn Dept Elect Engn Batu Pahat 86400 Johor Malaysia Univ Tun Hussein Onn Malaysia Computat Signal Image & Intelligence Res Focus Gr Batu Pahat 86400 Johor Malaysia

ISBN: (数字)9783030984045

ISBN: (纸本)9783030984045;9783030984038

the COVID-19 outbreak has posed a severe healthcare concern in Malaysia. Wearing a mask is the most effective way to prevent infections. However, some Malaysians refuse to wear a face mask for a variety of reasons. this work proposes a real-time face and face mask detection method using image processing technique to promote wearing face mask. Haar Cascade is used for the face detection to extract the features of the human faces as a method of approach. On the other hand, the face mask detection utilizes convolutional neural network (CNN) to train a model using the MobileNetV2 training model designed using Python, Keras and Tensorflow. OpenCV package was used as the interface for the algorithms to be connected to a web camera. Based on the performance metric calculation of detection rate analysis of the experimental results, the face detection rate is at 90% true and 10% false detection, which shows very good detection rate. Furthermore, the training accuracy and validation accuracy for the face mask detector are efficiently near to 1.0, proving a steady accuracy over the time. Training loss and validation loss are almost near to zero and decreasing over time, reassuring the algorithm performance is accurate and efficient for a datasets of 4000 images.

关键词： Face mask detection Face detection image processing Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

2019 conference on design and architectures for signal and image processing, dasip 2019

2019 Conference on Design and Architectures for Signal and I...

引用

13th conference on design and architectures for signal and image processing, dasip 2019

ISBN: (纸本)9781728140742

the proceedings contain 12 papers. the topics discussed include: using time-of-flight sensors for people counting applications;CNN hardware acceleration on a low-power and low-cost APSoC;POLYCiNN: multiclass binary inference engine using convolutional decision forests;mapping and frequency joint optimization for energy efficient execution of multiple applications on multicore systems;FPGA-Based acceleration of expectation maximization algorithm using high-level synthesis;SparseCCL: connected components labeling and analysis for sparse images;distilling the knowledge in CNN for WCE screening tool;real-time implementation of adaptive correlation filter tracking for 4K video stream in Zynq ultrascale+ MPSoC;and speeding-up CNN inference through dimensionality reduction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High speed linear array CCD image data acquisition system based on machine learning 13

High speed linear array CCD image data acquisition system ba...

引用

13th EAI International conference on Mobile Multimedia Communications, Mobimedia 2020

作者： Li, Kai-Yong Qinghai Nationalities University Physics and Electronic Information Engineering Xining810007 China

ISBN: (纸本)9781631902710

A high speed linear CCD (Charge Coupled Device) image data acquisition system based on machine learning was designed to solve the problem of poor signal stability of traditional high speed linear CCD image data acquisition system. Set up the overall system architecture. On this basis, complete the system hardware design through CCD sensor, A/D converter, CCD drive controller, RAM (Random Access Memory) read-write controller and PC;through the CCD driver module, CCD signal processing module, image information reading module, image cache module, image information conversion mode and image information display module, the system software design was completed. thus, the design of high-speed linear array CCD image data acquisition system based on machine learning was completed. Compared with the traditional high-speed linear CCD image data acquisition system, the experimental results show that the proposed high-speed linear CCD image data acquisition system based on machine learning has higher signal stability. Copyright © 2020 EAI.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

A New Approximate Multiplier design for Digital signal processing 13

A New Approximate Multiplier Design for Digital Signal Proce...

引用

13th IEEE International conference on ASIC

作者： Zhao, Yue Li, Tong Dong, Feng Wang, Qin He, Weifeng Jiang, Jianfei Shanghai Jiao Tong Univ Dept Micro Nano Elect Shanghai 200240 Peoples R China Beijing iQIYI Sci & Technol Co Ltd Shanghai Peoples R China

ISBN: (纸本)9781728107356

In this paper, a new approximate multiplier is proposed, which can decrease the multiplication complexity with the improved area and power performance by using OR and AND gates. To evaluate the efficiency of the proposed approximate multiplier, design parameters are compared with exact multiplier and recently proposed approximate designs. Experiment results reveal that the power consumption of the proposed approximate multiplier is only 32% of that in the exact multiplier. the proposed approximate multipliers are further evaluated in image sharpening and edge detection applications. the peak signal to noise ratio (PSNR) and structural similarity (SSIM) of our proposed approximate multipliers show that it can be used in image processing.

关键词： Approximate computing low power digital signal processing multiplier image processing

来源：评论

学校读者我要写书评

暂无评论

Annotated 360-Degree image and Video Databases: A Comprehensive Survey 13

Annotated 360-Degree Image and Video Databases: A Comprehens...

引用

13th IEEE International conference on signal processing and Communication Systems (ICSPCS)

作者： Elwardy, Majed Zepernick, Hans-Jurgen Sundstedt, Veronica Blekinge Inst Technol SE-37179 Karlskrona Sweden

ISBN: (纸本)9781728121949

the advances in 5G mobile networks are expected to enable immersive interconnected mobile multimedia systems. As humans are the final judges of the quality of immersive multimedia, it is essential to engage a suitable ground truth in the design of such systems. Databases annotated with results from subjective tests constitute such ground truth given as opinion scores, head movements, eye tracking data, psychophysiological data, and other data related to the viewers' behavior. On this basis, perception-based quality assessment of algorithms, systems, and services can be performed, and objective perceptual quality models can be developed. In this paper, a comprehensive survey of publicly available annotated 360-degree image and video databases is provided. the survey may guide the selection of ground truth on 360-degree images and videos to support quality assessment and modeling research. Further, the survey reveals the need for establishing new annotated databases that address the full range of subjective aspects of immersive multimedia.

关键词： Immersive multimedia 360-degree images 360-degree videos ground truth annotated databases

来源：评论

学校读者我要写书评

暂无评论

Rolling element bearing fault diagnosis using convolutional neural network and vibration image

引用

COGNITIVE SYSTEMS RESEARCH 2019年 53卷 42-50页

作者： Hoang, Duy-Tang Kang, Hee-Jun Univ Ulsan Grad Sch Elect Engn Ulsan South Korea Univ Ulsan Sch Elect Engn Ulsan South Korea

Detecting in prior bearing faults is an essential task of machine health monitoring because bearings are the vital components of rotary machines. the performance of traditional intelligent fault diagnosis methods depend on feature extraction of fault signals, which requires signal processing techniques, expert knowledge, and human labor. Recently, deep learning algorithms have been applied widely in machine health monitoring. With the capacity of automatically learning complex features of input data, deep learning architectures have great potential to overcome drawbacks of traditional intelligent fault diagnosis. this paper proposes a method for diagnosing bearing faults based on a deep structure of convolutional neural network. Using vibration signals directly as input data, the proposed method is an automatic fault diagnosis system which does not require any feature extraction techniques and achieves very high accuracy and robustness under noisy environments. (C) 2018 Elsevier B.V. All rights reserved.

关键词： Bearing fault diagnosis Convolutional neural network Deep learning Machine learning

来源：评论

学校读者我要写书评

暂无评论

A New Approximate Multiplier design for Digital signal processing

A New Approximate Multiplier Design for Digital Signal Proce...

引用

International conference on ASIC

作者： Yue Zhao Tong Li Feng Dong Qin Wang Weifeng He Jianfei Jiang Shanghai Jiao Tong University Shanghai China Beijing iQIYI Science & Technology Co. Ltd. Shanghai China

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic Hardware design Tool Based on Reusing Transformation

Automatic Hardware Design Tool Based on Reusing Transformati...

引用

International conference on ASIC

作者： Chongzhou Fang Zaichen Zhang Xiaohu You Chuan Zhang Lab of Efficient Architectures for Digital-communication and Signal-processing (LEADS) National Mobile Communications Research Laboratory Southeast University Nanjing China Purple Mountain Laboratories Nanjing China

Automatic hardware design is currently drawing research attentions as it has the potential to free designers from low level manual design process. In this paper, we propose an automatic hardware design tool, which is able to automatically perform reusing transformation on circuits. With the number of available computation modules as input, the proposed hardware design tool automatically designs circuit and generates corresponding register transfer level (RTL) codes in term of Verilog HDL. Our FPGA implementation results show that this design tool can efficiently perform resource planning according to user specifications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ANN Based Adaptive Successive Cancellation List Decoder for Polar Codes

ANN Based Adaptive Successive Cancellation List Decoder for ...

引用

International conference on ASIC

作者： Wenqing Song Yuxiang Fu Qinyu Chen Li Li Chuan Zhang Lab of Efficient Architectures for Digital-communication and Signal-processing (LEADS) School of Electronic Science and Engineering Nanjing University Nanjing China Purple Mountain Laboratories Nanjing China

Combined with cyclic redundancy check (CRC), SC list (SCL) decoder can achieve outstanding error correction performance, which is more obvious with increasing list size. However, the corresponding decoding complexity and latency increase with the list size. To this end, the selection of list size becomes essential for practical applications. A new artificial neural network (ANN) based framework is proposed in this paper to design a hardware-friendly adaptive SCL (DL-ASCL) decoder. First, the list size at each stage is predicted by an ANN predictor. the performance achieved based on the proposed DL-ASCL algorithm is close to the optimal SCL decoder with the same list size, especially in the high signal-to-noise ratio (SNR) region. Meanwhile, the computational complexity is significantly reduced compared with the conventional ones. Numerical results have demonstrated that the proposed deep learning based adaptive SCL decoder can achieve 56% computational complexity reduction compared with the conventional SCL decoder for the polar code with length 128 and rate 1/2. the hardware architecture of the adaptive SCL decoder based on the predicted list size is proposed and the folding technique is also adopted, which helps reduce the hardware cost by about 25%.

关键词：

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：