检索结果-内蒙古大学图书馆

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Yuhan Jiang Zhongyuan Wang Jie Hua Jinbi Liang Zengmin xu National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China School of Mathematics and Computing Science Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In this paper, we introduce a new dataset for air conditioner refrigerant leak smoke detection, called ACRL-10K. The dataset is designed to develop algorithms for detecting refrigerant leak smoke faults during air conditioner recycling. It contains a total of 10,724 images covering three common scenarios of air conditioner refrigerant leak: loading port, refrigerant extraction, and disassembly. All images are sourced from 656 video segments of real air conditioner recycling scenarios, captured by surveillance cameras deployed on an environmental company’s recycling production line. The annotations for the refrigerant leak smoke in the images are performed by industry experts to ensure high accuracy and consistency. To the best of our knowledge, ACRL-10K is the first dataset specifically designed for refrigerant leak smoke detection. Based on the ACRL-10K dataset, we present the performance of mainstream object detectors, including the YOLO series, as a baseline to conduct the following work: 1) preliminarily summarize the challenges of using the dataset for refrigerant leak smoke detection; 2) show the detection results of benchmark methods; and 3) make a comparison to identify the strengths and weaknesses of the baseline algorithms. In practice, the ACRL-10K dataset would hopefully advance research and applications in refrigerant leak early warning during air conditioner dismantling and recycling processes.

关键词： YOLO image segmentation Accuracy Surveillance Loading signal processing algorithms Production Detectors Cameras Recycling

来源：评论

学校读者我要写书评

暂无评论

Design of RNS-KSA Based 2D FIR Filter

Design of RNS-KSA Based 2D FIR Filter

引用

Information Technology, Electronics and Intelligent Communication Systems (ICITEICS), IEEE International conference on

作者： Raghavendra Reddy B. Rajesh A. Nandini Prem Kumar K. S. Chakradhar Dept. of Electronics and Communications Engineering (ECE) Mohan Babu University (Erstwhile Sree Vidyanikethan Engineering College) Tirupati India School of Engineering Electronics and Communication Engineering Mohan Babu University (Erstwhile Sree Vidyanikethan Engineering College) Tirupati India

ISBN: (数字)9798350382693

ISBN: (纸本)9798350382709

Two-dimensional finite impulse response filters have the benefits of phase linearity and assured stability, making them appealing in applications. 2D Finite Impulse Response (FIR) filters serve a significant role in different applications, such as image processing, medical field, pattern recognition, robot vision, and seismic or geophysical signal processing. This paper presents a novel RNS-based 2D Finite Impulse Response (FIR) filter using Residue Number System (RNS) and floating-point arithmetic operations, in which Residue Number System (RNS) provides substantially lower ranges of numbers in arithmetic computations than starting numbers and Floating-point arithmetic provides more accuracy and dynamic range than fixed-point arithmetic. The Floating Point Adder in the filter is designed using a Kogge-Stone parallel prefix adder (KSA) to improve addition speed. The proposed novel 2D FIR filter can process 32, 48, and 64-bit data by just changing the corresponding RNS moduli selection which makes it a better choice over a fixed-point-based 2D FIR filter. This filter is designed in Verilog HDL for kernel sizes 3x3, 5x5 and 7x7 and synthesized using Altera's Quartus software for FPGA Board Cyclone III (EP3C16F484C6) to evaluate the design parameters of the filter.

关键词： Finite impulse response filters image processing Dynamic range Information filters Software Pattern recognition Hardware design languages

来源：评论

学校读者我要写书评

暂无评论

Efficient Approximate Checkerboard K-SVD for Resource Constrained Embedded Systems

Efficient Approximate Checkerboard K-SVD for Resource Constr...

引用

Irish signals and Systems conference (ISSC)

作者： Yun Wu John McAllister School of Electrical Electronic Engineering and Computer Science Queen's University Belfast Belfast United Kingdom

ISBN: (数字)9798350352986

ISBN: (纸本)9798350352993

K-Singular Value Decomposition (K-SVD) is one of the key techniques in many signal processing and machine learning applications, such as image denoising, principal component analysis and dictionary learning. It is challenge to implement real-time K-SVD on resource constrained embedded systems, due to its exponentially increased computational complexity for large scale image or data dimensions. Approximate computing, as a trending paradigm in saving size, weight, and power (SWaP) in computation, trades the accuracy with complexity, so as to enable energy efficiency in modern computing systems. In this work, an approximate K-SVD based Dictionary Learning is studied primarily with sub-divided data blocks using reduced precision. The scalability of checkerboard K-SVD performance and arithmetic approximation are quantified with reconstructed image quality and computational complexity. It enables the efficient implementation by showing up to 16x estimated speed up and 98% reduction in memory foot-print using checkerboard division, and averagely 37% memory foot-print savings with approximate computing.

关键词： image quality Embedded systems Dictionaries Memory management Approximate computing Machine learning Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Radiometric Resolution Measurement for TerraSAR-x Sensor by Realizing Man-Made Homogeneous Regions

Radiometric Resolution Measurement for TerraSAR-X Sensor by ...

引用

signal, Information and Data processing (ICSIDP), IEEE International conference on

作者： xin Lin Quan Chen JingJun Mao Junying Gao Shaojie Ai Jing He Kaizhi Wang Shanghai Institute of Satellite Engineering Shanghai China School of Future Technology Tianjin University Tianjin China Department of Electronic Engineering Shanghai Jiao Tong University China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

A homogeneous region exhibiting a stable and high backscattering coefficient is crucial for the radiometric calibration and performance evaluation of synthetic aperture radar (SAR) systems. However, creating such a region in practice presents significant challenges. This study presents a new method for creating a uniform region with consistent backscattering, defined by a known backscattering coefficient, using specially designed metal grids. This method is applied to evaluate the radiometric resolution of the TerraSAR-x *** proposed man-made grid-structured target, referred to as the metal grid, is constructed from aluminum. The backscattering coefficients of this grid were measured across various incident angles and frequencies in a microwave anechoic chamber. Radar cross-section (RCS) measurements confirm the target's strong backscattering properties. Using this designed target, homogeneous regions with high backscattering were created at Shanghai Jiao Tong University, China. Two spaceborne experiments conducted by the TerraSAR-x satellite over the test area were carried out to assess the radiometric resolution of the SAR sensor. The experimental results demonstrate that the radiometric resolution values derived from the TerraSAR-x images closely align with the reference values provided in the product specifications. Additionally, the developed strong backscattering homogeneous region proves to be highly effective and well-suited for SAR radiometric calibration and other related applications.

关键词： Microwave measurement image resolution Radar cross-sections Spaceborne radar Satellite broadcasting Calibration Microwave radiometry Synthetic aperture radar signal resolution Backscatter

来源：评论

学校读者我要写书评

暂无评论

PhysID: Physics-based Interactive Dynamics from a Single-view image

PhysID: Physics-based Interactive Dynamics from a Single-vie...

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Sourabh Vasant Gothe Ayon Chattopadhyay Gunturi Venkata Sai Phani Kiran Pratik Vibhav Agarwal Jayesh Rajkumar Vachhani Sourav Ghosh Parameswaranath VM Barath Raj KR Samsung R&D Institute India Bangalore

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Transforming static images into interactive experiences remains a challenging task in computer vision. Tackling this challenge holds the potential to elevate mobile user experiences, notably through interactive and AR/VR applications. Current approaches aim to achieve this either using pre-recorded video responses or requiring multi-view images as input. In this paper, we present PhysID, that streamlines the creation of physics-based interactive dynamics from a single-view image by leveraging large generative models for 3D mesh generation and physical property prediction. This significantly reduces the expertise required for engineering-intensive tasks like 3D modeling and intrinsic property calibration, enabling the process to be scaled with minimal manual intervention. We integrate an on-device physics-based engine for physically plausible real-time rendering with user interactions. PhysID represents a leap forward in mobile-based interactive dynamics, offering real-time, non-deterministic interactions and user-personalization with efficient on-device memory consumption. Experiments evaluate the zero-shot capabilities of various Multimodal Large Language Models (MLLMs) on diverse tasks and the performance of 3D reconstruction models. These results demonstrate the cohesive functioning of all modules within the end-to-end framework, contributing to its effectiveness.

关键词： Performance evaluation Solid modeling Three-dimensional displays Streaming media Aerodynamics Rendering (computer graphics) Real-time systems Mobile handsets Mesh generation Material properties

来源：评论

学校读者我要写书评

暂无评论

Secure Homomorphic Evaluation of Discrete Cosine Transform with High Precision 20

Secure Homomorphic Evaluation of Discrete Cosine Transform w...

引用

20th IEEE International conference on Trust, Security and Privacy in Computing and Communications (IEEE TrustCom)

作者： Cai, Zhiwei Zeng, Huicong Zheng, Peijia Cheng, Ziyan Luo, Weiqi Liu, Hongmei Guangdong Key Lab Informat Secur Technol Sch Comp Sci & Engn Guangzhou Peoples R China Chinese Acad Sci Inst Informat Engn State Key Lab Informat Secur Beijing Peoples R China

ISBN: (纸本)9781665416580

signal processing in the Encrypted Domain (SPED) has received considerable attention as it aims at privacy-preserving solutions for various applications. Discrete cosine transform (DCT) is a popular signal transform widely used in signal processing. It has many applications in speech processing, still picture coding, image and video transformation, compression coding, and so on. In this paper, we mainly study how to implement DCT in the encryption domain with high precision. We propose a new scheme to implement encrypted domain DCT. This scheme encodes a complex number as a unit root polynomial in the evaluation, and realizes the high precision representation of complex numbers. With this representation, this scheme can also realize the high precision representation of decimals. To improve the computational efficiency, we also propose a fast implementation of DCT in the encryption domain, which can significantly improve the DCT speed for large-scale matrices. We conducted experiments to verify the effectiveness and efficiency. When the matrix size is small, our original method has the advantages of both high accuracy and fast speed. When the matrix size is large, the fast implementation outperforms the original method.

关键词： signal processing in encrypted domain FFT Fast DCT Homomorphic encryption BGV cryptosystem

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study on the Potential of Unsupervised Deep Learning-based Feature Selection in Radiomics 44

A Comparative Study on the Potential of Unsupervised Deep Le...

引用

44th Annual International conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022

作者： Haueise, Tobias Liebgott, Annika Yang, Bin University Hospital Tuebingen Section on Experimental Radiology Tuebingen Germany Institute of Diabetes Research and Metabolic Diseases at Helmholtz Munich Tuebingen Germany Institute of Signal Processing and System Theory University of Stuttgart Stuttgart Germany

ISBN: (数字)9781728127828

ISBN: (纸本)9781728127828

In Radiomics, deep learning-based systems for medical image analysis play an increasing role. However, due to the better explainability, feature-based systems are still preferred, especially by physicians. Often, high-dimensional data and low sample size pose different challenges (e.g. increased risk of overfitting) to machine learning systems. By removing irrelevant and redundant features from the data, feature selection is an effective way of pre-processing. The research in this study is focused on unsupervised deep learning-based methods for feature selection. Five recently proposed algorithms are compared regarding their applicability and efficiency on seven data sets in three different sample applications. It was found that deep learning-based feature selection leads to improved classification results compared to conventional methods, especially for small feature subsets. Clinical Relevance - The exploration of distinctive features and the ability to rank their importance without the need for outcome information is a potential field of application for unsupervised feature selection methods. Especially in multiparametric radiology, the number of features is increasing. The identification of new potential biomarkers is important both for treatment and prevention. © 2022 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Imperceptible Transfer Attack on Large Vision-Language Models

Imperceptible Transfer Attack on Large Vision-Language Model...

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： xiaowen Cai Daizong Liu Runwei Guan Pan Zhou School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Wangxuan Institute of Computer Technology Peking University Beijing China Department of Electrical Engineering and Electronics University of Liverpool Liverpool United Kingdom

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In spite of achieving significant progress in recent years, Large Vision-Language Models (LVLMs) are proven to be vulnerable to adversarial examples. Therefore, there is an urgent need for an effective adversarial attack to identify the deficiencies of LVLMs in security-sensitive applications. However, existing LVLM attackers generally optimize adversarial samples against a specific textual prompt with a certain LVLM model, tending to overfit the target prompt/network and hardly remain malicious once they are transferred to attack a different prompt/model. To this end, in this paper, we propose a novel Imperceptible Transfer Attack (ITA) against LVLMs to generate prompt/model-agnostic adversarial samples to enhance such adversarial transferability while further improving the imperceptibility. Specifically, we learn to apply appropriate visual transformations on image inputs to create diverse input patterns by selecting the optimal combination of operations from a pool of candidates, consequently improving adversarial transferability. We conceptualize the selection of optimal transformation combinations as an adversarial learning problem and employ a gradient approximation strategy with noise budget constraints to effectively generate imperceptible transferable samples. Extensive experiments on three LVLM models and two widely used datasets with three tasks demonstrate the superior performance of our ITA.

关键词： Visualization Noise Adversarial machine learning Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

EventZoom: Learning to Denoise and Super Resolve Neuromorphic Events

EventZoom: Learning to Denoise and Super Resolve Neuromorphi...

引用

IEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Duan, Peiqi Wang, Zihao W. Zhou, xinyu Ma, Yi Shi, Boxin Peking Univ NELVT Dept Comp Sci & Technol Beijing Peoples R China Northwestern Univ Dept Comp Sci & Engn Evanston IL 60208 USA Peking Univ Inst Artificial Intelligence Beijing Peoples R China

ISBN: (纸本)9781665445092

We address the problem of jointly denoising and super resolving neuromorphic events, a novel visual signal that represents thresholded temporal gradients in a space-time window. The challenge for event signal processing is that they are asynchronously generated, and do not carry absolute intensity but only binary signs informing temporal variations. To study event signal formation and degradation, we implement a display-camera system which enables multi-resolution event recording. We further propose Event-Zoom, a deep neural framework with a backbone architecture of 3D U-Net. Event-Zoom is trained in a noise-to-noise fashion where the two ends of the network are unfiltered noisy events, enforcing noise-free event restoration. For resolution enhancement, EventZoom incorporates an event-to-image module supervised by high resolution images. Our results showed that EventZoom achieves at least 40x temporal efficiency compared to state-of-the-art (SOTA) event denoisers. Additionally, we demonstrate that EventZoom enables performance improvements on applications including event-based visual object tracking and image reconstruction. EventZoom achieves SOTA super resolution image reconstruction results while being 10x faster.

关键词： Training Visualization image resolution Three-dimensional displays Neuromorphics Noise reduction image restoration

来源：评论

学校读者我要写书评

暂无评论

Towards a one millimeter thin foil camera

引用

INTERNATIONAL JOURNAL OF wavelets MULTIRESOLUTION AND INFORMATION processing 2022年第3期20卷

作者： Bimber, Oliver Kurmi, Indrajit Johannes Kepler Univ Linz Inst Comp Graph Altenberger Str 69 Comp Sci Bldg A-4040 Linz Austria

This paper summarizes our results and findings made throughout the past years on the way towards a one millimeter thin, flexible, and scalable foil camera. The sensor part of the camera consists of multiple thin-film luminescent concentrator (LC) layers, each of which is sensitive to a different band of the light spectrum. A special optical micro-structure cut into the edges of the LC layers multiplexes the transported light signal into a variant of the Radon transform of the image focused on the LC surface. For increasing the camera's depth of field beyond the sensor surface, various thin-film imaging layers, such as optical Soller collimators realized by means of x-ray lithography on a PMMA wafer, have been investigated. The flexibility and scalability of our thin-film camera has the potential to lead to new human-computer interfaces that are unconstrained in shape and sensing-distance. applications such as contact-less sensing, smart skin sensors for autonomous robots and industrial machines, and environment sensing for vehicles are imaginable.

关键词： Sensors thin-film optics flat cameras Radon transform luminescent concentrators Soller collimators image reconstruction machine learning depth sensing classification

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：