检索结果-内蒙古大学图书馆

International Conference on Biosignals, images and Instrumentation (ICBSII)

作者： Delpha Jacob Priyanka Kokil Subramanian S Jayanthi Thiruvengadam Department of Biomedical Engineering College of Engineering and Technology SRM Institute of Science and Technology Chennai Department of Electronics and Communication Engineering Advanced Signal and Image Processing (ASIP) Lab Indian Institute of Information Technology Design and Manufacturing Chennai Department of Respiratory Medicine SRM Medical College Hospital and Research Centre Kattankulathur Tamil Nadu India

ISBN: (数字)9798350350951

ISBN: (纸本)9798350350968

Snoring, a recurring habit often disregarded within the Indian community, can signal a grave underlying issue of Obstructive Sleep Apnea (OSA). OSA is a severe sleep disorder characterized by recurrent interruptions in breathing for more than 10 seconds during sleep, typically due to partial or complete airway obstructions. Neglecting OSA can lead to a range of significant health risks, including increased likelihood of occupational accidents, motor vehicle accidents, heightened susceptibility to severe depression, cardiac and cerebrovascular diseases, and reduced life expectancy. The main objective of the study is to detect snoring while at sleep and also to classify it as normal snoring and OSA snoring. Arduino nano 33 BLE sense is used to capture the snore signal, it houses a built-in MP34DT05 sensor. The sensor has a signal-to-noise ratio of 64dB and sensitivity of - 26dBFS ± 3dB. This captures the sound signal of the individual, it is further processed to extract the Mel-filter bank energy features, Mel Frequency Cepstral Coefficients and Spectrogram features. The features are further used to build a model and the same is trained using edge impulse to classify the signal. The dataset is divided into training, testing, and validation sets, with 80% of the data allocated to training, 20% to testing, and an additional 20% within the training data set aside for validation purposes. The results for the two class classification (snoring and non snoring) indicate that the spectrogram-based approach achieved an accuracy rate of 96.9%, while the other two methods yielded accuracy rates of 93.8%. The accuracy for three class classification (normal, snoring and OSA snoring) using the Embedded Machine Learning (EML) approach is 88%. The proposed study demonstrates enhanced accuracy in identifying OSA by snoring compared to previous research. This autonomous system can facilitate the detection of OSA through the analysis of snoring patterns, subsequently alerting the subjec

关键词： Training Performance evaluation Accuracy Embedded systems Training data Machine learning Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird'View Representations in Autonomous Driving

Understanding the Robustness of 3D Object Detection with Bir...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zijian Zhu Yichi Zhang Hai Chen Yinpeng Dong Shu Zhao Wenbo Ding Jiachen Zhong Shibao Zheng Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Dept. of Comp. Sci. and Tech. THBI Lab Institute for AI Tsinghua University BNRist Center Zhongguancun Laboratory Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province School of Computer Science and Technology Anhui University SAIC Motor AI Lab

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations; 2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features; 3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Open-World, Diverse, Cross-Spatial-Temporal Benchmark for Dynamic Wild Person Re-Identification

arXiv

引用

arXiv 2024年

作者： Zhang, Lei Fu, Xiaowei Huang, Fuxiang Yang, Yi Gao, Xinbo The School of Microelectronics and Communication Engineering Chongqing University Chongqing400044 China Peng Cheng Lab Shenzhen China The College of Computer Science and Technology Zhejiang University Hangzhou310058 China The Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Chongqing400065 China

Person re-identification (ReID) has made great strides thanks to the data-driven deep learning techniques. However, the existing benchmark datasets lack diversity, and models trained on these data cannot generalize well to dynamic wild scenarios. To meet the goal of improving the explicit generalization of ReID models, we develop a new Open-World, Diverse, Cross-Spatial-Temporal dataset named OWD with several distinct features. 1) Diverse collection scenes: multiple independent open-world and highly dynamic collecting scenes, including streets, intersections, shopping malls, etc. 2) Diverse lighting variations: long time spans from daytime to nighttime with abundant illumination changes. 3) Diverse person status: multiple camera networks in all seasons with normal/adverse weather conditions and diverse pedestrian appearances (e.g., clothes, personal belongings, poses, etc.). 4) Protected privacy: invisible faces for privacy critical applications. To improve the implicit generalization of ReID, we further propose a Latent Domain Expansion (LDE) method to develop the potential of source data, which decouples discriminative identity-relevant and trustworthy domain-relevant features and implicitly enforces domain-randomized identity feature space expansion with richer domain diversity to facilitate domain-invariant representations. Our comprehensive evaluations with most benchmark datasets in the community are crucial for progress, although this work is far from the grand goal toward open-world and dynamic wild applications. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A No-Reference Quality Assessment Method for Digital Human Head

A No-Reference Quality Assessment Method for Digital Human H...

引用

IEEE International Conference on image processing

作者： Yingjie Zhou Zicheng Zhang Wei Sun Xiongkuo Min Xianghe Ma Guangtao Zhai Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China School of Information and Control Engineering China University of Mining Technology China Peng Cheng Laboratory China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

In recent years, digital humans have been widely applied in augmented/virtual reality (A/VR), where viewers are allowed to freely observe and interact with the volumetric content. However, the digital humans may be degraded with various distortions during the procedure of generation and transmission. Moreover, little effort has been put into the perceptual quality assessment of digital humans. Therefore, it is urgent to carry out objective quality assessment methods to tackle the challenge of digital human quality assessment (DHQA). In this paper, we develop a novel no-reference (NR) method based on Transformer to deal with DHQA in a multi-task manner. Specifically, the front 2D projections of the digital humans are rendered as inputs and the vision transformer (ViT) is employed for the feature extraction. Then we design a multi-task module to jointly classify the distortion types and predict the perceptual quality levels of digital humans. The experimental results show that the proposed method well correlates with the subjective ratings and outperforms the state-of-the-art quality assessment methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks

arXiv

引用

arXiv 2024年

作者： Zhang, Lei Zhou, Yuhang Yang, Yi Gao, Xinbo School of Microelectronics and Communication Engineering Chongqing University Chongqing400044 China Peng Cheng Lab Shenzhen China College of Computer Science and Technology Zhejiang University Hangzhou310058 China Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Chongqing400065 China

—Despite providing high-performance solutions for computer vision tasks, the deep neural network (DNN) model has been proved to be extremely vulnerable to adversarial attacks. Current defense mainly focuses on the known attacks, but the adversarial robustness to the unknown attacks is seriously overlooked. Besides, commonly used adaptive learning and fine-tuning technique is unsuitable for adversarial defense since it is essentially a zero-shot problem when deployed. Thus, to tackle this challenge, we propose an attack-agnostic defense method named Meta Invariance Defense (MID). Specifically, various combinations of adversarial attacks are randomly sampled from a manually constructed Attacker Pool to constitute different defense tasks against unknown attacks, in which a student encoder is supervised by multi-consistency distillation to learn the attack-invariant features via a meta principle. The proposed MID has two merits: 1) Full distillation from pixel-, feature- and prediction-level between benign and adversarial samples facilitates the discovery of attack-invariance. 2) The model simultaneously achieves robustness to the imperceptible adversarial perturbations in high-level image classification and attack-suppression in low-level robust image regeneration. Theoretical and empirical studies on numerous benchmarks such as imageNet verify the generalizable robustness and superiority of MID under various attacks. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A NO-REFERENCE QUALITY ASSESSMENT METHOD FOR DIGITAL HUMAN HEAD

arXiv

引用

arXiv 2023年

作者： Zhou, Yingjie Zhang, Zicheng Sun, Wei Min, Xiongkuo Ma, Xianghe Zhai, Guangtao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China School of Information and Control Engineering China University of Mining Technology China Peng Cheng Laboratory China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Extended State Observer Based Fault-Tolerant Predictive Control for a Four-Mecanum Wheels Mobile Robot

Extended State Observer Based Fault-Tolerant Predictive Cont...

引用

IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems

作者： Binghao Yang Dongliang Wang Ziling Wen Wu Wei Wenji Li Zhun Fan Key Lab of Digital Signal and Image Processing of Guangdong Province Shantou University Guangdong China School of Department of Electronic and Information Engineering Shantou University Guangdong China Key Laboratory of Autonomous Systems and Networked Control Ministry of Education Guangzhou Guangdong China School of Automation Science and Engineering South China University of Technology Guangzhou Guangdong China

ISBN: (数字)9798331506056

ISBN: (纸本)9798331506063

The application of unmanned vehicles in industrial cargo transportation is becoming increasingly widespread, particularly playing a significant role in transporting heavy-duty goods. However, when performing such tasks, whether in single-vehicle transportation or multi-vehicle collaborative transportation, the occurrence of wheel failures can potentially lead to serious safety accidents. Therefore, this paper proposes a fault-tolerant control scheme, establishing a kinematic model considering disturbances and failures, and adopts model predictive control for trajectory tracking. Additionally, an extended state observer is introduced to observe system states and counteract disturbances. To address potential failure issues, a controller reconstruction strategy is proposed. Finally, the effectiveness and superiority of the controller is validated through numerical simulation and comparative experiment.

关键词： Fault tolerance Trajectory tracking Fault tolerant systems Wheels Transportation Kinematics Predictive models Safety State estimation Predictive control

来源：评论

学校读者我要写书评

暂无评论

Hybrid model sprite generation: A high-quality, fast and robust algorithm

引用

International Journal of Electrical Engineering 2005年第3期12卷 215-223页

作者： Chi, Cheng-Jan Chen, Chin-Hsing Yang, Dyi-Lang Image Processing Lab. EE Department National Cheng Kung Univ. Taiwan Taiwan ASUS Corp. Electrical Engineering Dept. National Cheng Kung University Department of Electronic Engineering Kaohsiung Municipal Kaohsiung Industrial High School Taiwan Taiwan Office of Academic Affairs Department of Electronic Communication Engineering National Kaohsiung Marine University Taiwan Taiwan

Sprite generation, the core of the sprite coding, is a developing technique included in the MPEG-4 standard. It achieves high subjective quality with low bitrates. The affine and perspective GME (Global Motion Estimation) methods are demonstrated in the MPEG-4 Verification Model (MPEG-4 VM), MPEG-4 Optimization Model (MPEG-4 OM) and many other algorithms. The affine model GME, provides limited image quality, is robust and fast. The perspective model GME generates sprites with better quality, however it suffers from the time-wasting and error propagation problem. A new method to generate sprites in this paper combines the existing affine and perspective GME algorithms to produce high sprites quickly without losing robustness. In order to generate high quality sprites, the proposed "Hybrid Model GME" method uses the affine model GME as an initial search, then switches to the perspective model GME if necessary. To accelerate the speed, a nearest neighborhood (NN) kernel is used to replace the bilinear method for image warping. Experimental results show that the image quality is much improved even when camera movements are more complex and quick. The computation speed is between 10 and 17 times faster than the MPEG-4 VM. If the sprites can be divided into several pieces, the computation speed can be about 1.46 times faster ahead.

关键词： Algorithms

来源：评论

学校读者我要写书评

暂无评论

Frequency-Aware Physics-Inspired Degradation Model for Real-World image Super-Resolution

arXiv

引用

arXiv 2021年

作者： Dong, Zhenxing Cao, Hong Shen, Wang Gan, Yu Ling, Yuye Zhai, Guangtao Su, Yikai John Hopcroft Center for Computer Science Shanghai Jiao Tong University China Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Department of Electrical and Computer Engineering University of Alabama TuscaloosaAL35401 United States State Key Lab of Advanced Optical Communication Systems and Networks Shanghai Jiao Tong University China

Current learning-based single image super-resolution (SISR) algorithms underperform on real data due to the deviation in the assumed degradation process from that in the real-world scenario. Conventional degradation processes consider applying blur, noise, and downsampling (typically bicubic downsampling) on high-resolution (HR) images to synthesize low-resolution (LR) counterparts. However, few works on degradation modelling have taken the physical aspects of the optical imaging system into consideration. In this paper, we analyze the imaging system optically and exploit the characteristics of the real-world LR-HR pairs in the spatial frequency domain. We formulate a real-world physics-inspired degradation model by considering both optics and sensor degradation;The physical degradation of an imaging system is modelled as a low-pass filter, whose cut-off frequency is dictated by the object distance, the focal length of the lens, and the pixel size of the image sensor. In particular, we propose to use a convolutional neural network (CNN) to learn the cutoff frequency of real-world degradation process. The learned network is then applied to synthesize LR images from unpaired HR images. The synthetic HR-LR image pairs are later used to train an SISR network. We evaluate the effectiveness and generalization capability of the proposed degradation model on real-world images captured by different imaging systems. Experimental results showcase that the SISR network trained by using our synthetic data performs favorably against the network using the traditional degradation model. Moreover, our results are comparable to that obtained by the same network trained by using real-world LR-HR pairs, which are challenging to obtain in real scenes. © 2021, CC BY.

关键词： Cutoff frequency

来源：评论

学校读者我要写书评

暂无评论

A multi-user oriented live free-viewpoint video streaming system based on view interpolation

arXiv

引用

arXiv 2021年

作者： Hu, Jingchuan Guo, Shuai Dong, Yu Zhou, Kai Xu, Jun Song, Li Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai200240 China Cooperative Medianet Innovation Center Shanghai Jiao Tong University Shanghai200240 China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China

As an important application form of immersive multimedia services, free-viewpoint video(FVV) enables users with great immersive experience by strong interaction. However, the computational complexity of virtual view synthesis algorithms poses a significant challenge to the real-time performance of an FVV system. Furthermore, the individuality of user interaction makes it difficult to serve multiple users simultaneously for a system with conventional architecture. In this paper, we novelly introduce a CNN-based view interpolation algorithm to synthesis dense virtual views in real time. Based on this, we also build an end-to-end live free-viewpoint system with a multi-user oriented streaming strategy. Our system can utilize a single edge server to serve multiple users at the same time without having to bring a large view synthesis load on the client side. We analysis the whole system and show that our approaches give the user a pleasant immersive experience, in terms of both visual quality and latency. Copyright © 2021, The Authors. All rights reserved.

关键词： Multimedia services

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：