检索结果-内蒙古大学图书馆

Stereo vision Meta-Lens-Assisted Driving vision

ACS PHOTONICS 2024年第7期11卷 2546-2555页

作者： Liu, Xiaoyuan Li, Wuyang Yamaguchi, Takeshi Geng, Zihan Tanaka, Takuo Tsai, Din Ping Chen, Mu Ku City Univ Hong Kong State Key Lab Terahertz & Millimeter Waves Kowloon Hong Kong 999077 Peoples R China City Univ Hong Kong Dept Elect Engn Kowloon Hong Kong 999077 Peoples R China RIKEN Ctr Adv Photon Innovat Photon Manipulat Res Team Saitama 3510198 Japan RIKEN Cluster Pioneering Res Metamat Lab Saitama 3510198 Japan Tokushima Univ Inst PostLED Photon Tokushima 7708506 Japan City Univ Hong Kong Ctr Biosyst Neurosci & Nanotechnol Hong Kong 999077 Peoples R China Tsinghua Univ Inst Data & Informat Tsinghua Shenzhen Int Grad Sch Shenzhen 518071 Guangdong Peoples R China

Object detection and depth perception are key foundations of object tracking and machine navigation, facilitating a thorough perception and understanding of the surrounding environment. Currently, autonomous vehicles employ complex and bulky systems with high cost and energy consumption to achieve demanding multimodal vision. An imperative exists for the development of compact and reliable technology to enhance the cost-effectiveness and efficiency of autonomous driving systems. Meta-lens, a novel flat optical device, has an artificial nanoantenna array to manipulate the light properties. It is lightweight, ultrathin, and easy to integrate, making it suitable for various applications. We developed a stereo vision meta-lens imaging system for assisted driving vision, a comprehensive perception including imaging, object detection, instance segmentation, and depth information. The compact system comprises a band-pass filter, a stereo vision meta-lens, and a complementary metal oxide semiconductor (CMOS) sensor. In comparison to traditional two-camera-based stereo vision systems, the meta-lens stereo vision imaging system eliminates the need for distortion correction or camera calibration. A tailored data processing pipeline is proposed with an intensity and depth gradient cross-validation optimization mechanism and three deep learning modules for object detection, instance segmentation, and stereo matching foundations. Final assisted driving vision provides multimodal perception by integrating the raw image, instance labels, bounding boxes, segmentation masks in depth pseudo color, and depth information for each detected object. Our assisted driving vision based on a stereo meta-lens system offers a comprehensive perception for scene understanding of machines, benefiting the applications of human-computer interaction, machine navigation, autonomous driving, and augmented reality.

关键词： meta-lens stereo vision depth sensing image segmentation recognition

来源：评论

学校读者我要写书评

暂无评论

Learning Location From Shared Elevation Profiles in Fitness Apps: A Privacy Perspective

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2024年第1期23卷 581-596页

作者： Meteriz-Yildiran, Ulku Yildiran, Necip Fazil Kim, Joongheon Mohaisen, David Meta Menlo Pk CA 94025 USA Google Mountain View CA 94043 USA Korea Univ Dept Elect Engn Seoul 02841 South Korea Univ Cent Florida Dept Comp Sci Orlando FL 32816 USA

The extensive use of smartphones and wearable devices has facilitated many useful applications. For example, with Global Positioning System (GPS)-equipped smart and wearable devices, many applications can gather, process, and share rich metadata, such as geolocation, trajectories, elevation, and time. For example, fitness applications, such as Runkeeper and Strava, utilize the information for activity tracking and have recently witnessed a boom in popularity. Those fitness tracker applications have their own web platforms and allow users to share activities on such platforms or even with other social network platforms. To preserve the privacy of users while allowing sharing, several of those platforms may allow users to disclose partial information, such as the elevation profile for an activity, which supposedly would not leak the location of the users. In this work, and as a cautionary tale, we create a proof of concept where we examine the extent to which elevation profiles can be used to predict the location of users. To tackle this problem, we devise three plausible threat settings under which the city or borough of the targets can be predicted. Those threat settings define the amount of information available to the adversary to launch the prediction attacks. Establishing that simple features of elevation profiles, e.g., spectral features, are insufficient, we devise both natural language processing (NLP)-inspired text-like representation and computer vision-inspired image-like representation of elevation profiles, and we convert the problem at hand into text and image classification problem. We use both traditional machine learning- and deep learning-based techniques and achieve a prediction success rate ranging from 59.59% to 99.80%. The findings are alarming, highlighting that sharing elevation information may have significant location privacy risks.

关键词： Location privacy privacy breach privacy in social media fitness applications natural language processing applied machine learning

来源：评论

学校读者我要写书评

暂无评论

A review of recent advances in data-driven computer vision methods for structural damage evaluation: algorithms, applications, challenges, and future opportunities

引用

ARCHivES OF COMPUTATIONAL METHODS IN ENGINEERING 2025年 1-33页

作者： Pan, Xiao Yang, Tony T. Y. Li, Jun Ventura, Carlos Malaga-Chuquitaype, Christian Li, Chaobin Su, Ray Kai Leung Brzev, Svetlana Hong Kong Univ Sci & Technol Dept Civil & Environm Engn Clear Water Bay Hong Kong Peoples R China Univ British Columbia Dept Civil Engn Vancouver BC Canada Curtin Univ Ctr Infrastruct Monitoring & Protect Perth WA Australia Imperial Coll London Dept Civil & Environm Engn London England Univ Hong Kong Dept Civil Engn Hong Kong Peoples R China

Computer vision techniques have gained great traction in civil infrastructure inspection and monitoring. This paper conducted a systematic review of recent data-driven computer vision algorithms in structural damage detection published during the past 5 years. The theories of prevalent computer vision models are first reviewed with an emphasis on the progressive innovation in algorithms' architecture. Then, recent applications of computer vision models for structural damage evaluation are discussed, which are classified into different structural categories by their material types (i.e., concrete, steel, masonry, timber) at three hierarchical levels including damage recognition, localization, and quantification. In particular, the paper also highlights the current state of using computer vision for damage assessment of timber structures, which remains under-explored compared to concrete and steel structures. Next, the paper scrutinizes existing structural damage inspection guidelines to identify key technological gaps between the capability of existing computer vision methods and manual inspection practices in the field. Finally, the paper summarizes existing challenges and recommends future research opportunities including the integration of computer vision methods with multimodal large language models, sensor-fusion, and mobile inspection approaches.

关键词： Structural damage detection Structural health monitoring Computer vision image processing machine learning Deep learning Sensor fusion Unmanned aerial and ground vehicles

来源：评论

学校读者我要写书评

暂无评论

Compute-First Optical Detection for Noise-Resilient Visual Perception

引用

ACS PHOTONICS 2025年第2期12卷 1137-1145页

作者： Kim, Jungmin Yu, Nanfang Yu, Zongfu Univ Wisconsin Dept Elect & Comp Engn Madison WI 53706 USA Columbia Univ Dept Appl Phys & Appl Math New York NY 10027 USA

During machine visual perception, the optical signal from a scene is transferred into the electronic domain by detectors in the form of image data, which are then processed for the extraction of visual information. In noisy environments, such as a thermal imaging system, however, the neural performance faces a significant bottleneck due to the inherent degradation of data quality upon noisy detection. Here, we propose a concept of optical signal processing before detection to address this issue. We demonstrate that spatially redistributing optical signals through a properly designed linear transformer can enhance the detection noise resilience of visual perception, as benchmarked with MNIST classification. A quantitative analysis of the relationship between signal concentration and noise robustness supports our idea with its practical implementation in an incoherent imaging system. This compute-first detection scheme can advance infrared machine vision technologies for industrial and defense applications.

关键词： Optical processing linear transformation signal-to-noise ratio metasurface optical neuralnetwork visual perception

来源：评论

学校读者我要写书评

暂无评论

Hand Gesture Recognition on Edge Devices: Sensor Technologies, Algorithms, and processing Hardware

引用

SENSORS 2025年第6期25卷 1687-1687页

作者： Fertl, Elfi Castillo, Encarnacion Stettinger, Georg Cuellar, Manuel P. Morales, Diego P. Infineon Technol AG D-85579 Neubiberg Germany Univ Granada Dept Elect & Comp Technol E-18071 Granada Spain Univ Granada Dept Comp Sci & Artificial Intelligence E-18071 Granada Spain

Hand gesture recognition (HGR) is a convenient and natural form of human-computer interaction. It is suitable for various applications. Much research has already focused on wearable device-based HGR. By contrast, this paper gives an overview focused on device-free HGR. That means we evaluate HGR systems that do not require the user to wear something like a data glove or hold a device. HGR systems are explored regarding technology, hardware, and algorithms. The interconnectedness of timing and power requirements with hardware, pre-processing algorithm, classification, and technology and how they permit more or less granularity, accuracy, and number of gestures is clearly demonstrated. Sensor modalities evaluated are WIFI, vision, radar, mobile networks, and ultrasound. The pre-processing technologies stereo vision, multiple-input multiple-output (MIMO), spectrogram, phased array, range-doppler-map, range-angle-map, doppler-angle-map, and multilateration are explored. Classification approaches with and without ML are studied. Among those with ML, assessed algorithms range from simple tree structures to transformers. All applications are evaluated taking into account their level of integration. This encompasses determining whether the application presented is suitable for edge integration, their real-time capability, whether continuous learning is implemented, which robustness was achieved, whether ML is applied, and the accuracy level. Our survey aims to provide a thorough understanding of the current state of the art in device-free HGR on edge devices and in general. Finally, on the basis of present-day challenges and opportunities in this field, we outline which further research we suggest for HGR improvement. Our goal is to promote the development of efficient and accurate gesture recognition systems.

关键词： hand gesture recognition edge machine learning artificial intelligence algorithms signal processing radar WiFi 4G 5G LTE ultrasound lidar vision image processing AI accelerators

来源：评论

学校读者我要写书评

暂无评论

Transformer with multi-level grid features and depth pooling for image captioning

引用

machine vision AND applications 2024年第5期35卷 1-17页

作者： Bui, Doanh C. Nguyen, Tam V. Nguyen, Khang Vietnam Natl Univ Univ Informat Technol Ho Chi Minh City Vietnam Univ Dayton Dept Comp Sci Dayton OH USA

image captioning is an exciting yet challenging problem in both computer vision and natural language processing research. In recent years, this problem has been addressed by Transformer-based models optimized with Cross-Entropy loss and boosted performance via Self-Critical Sequence Training. Two types of representations are embedded into captioning models: grid features and region features, and there have been attempts to include 2D geometry information in the self-attention computation. However, the 3D order of object appearances is not considered, leading to confusion for the model in cases of complex scenes with overlapped objects. In addition, recent studies using only feature maps from the last layer or block of a pretrained CNN-based model may lack spatial information. In this paper, we present the Transformer-based captioning model dubbed TMDNet. Our model includes one module to aggregate multi-level grid features (MGFA) to enrich the representation ability using prior knowledge, and another module to effectively embed the image's depth-grid aggregation (DGA) into the model space for better performance. The proposed model demonstrates its effectiveness via evaluation on the MS-COCO "Karpathy" test split across five standard metrics.

关键词： image captioning Transformer Depth estimation Multi-level feature maps Grid features

来源：评论

学校读者我要写书评

暂无评论

EFL-LCNN: Enhanced face localization augmented light convolutional neural network for human emotion recognition

引用

MULTIMEDIA TOOLS AND applications 2024年第4期83卷 12089-12110页

作者： Bellamkonda, Sivaiah Settipalli, Lavanya Indian Inst Informat Technol Kottayam Dept Comp Sci & Engn Kottayam 686635 Kerala India Indian Inst Informat Technol Dept Cyber Secur Kottayam 686635 Kerala India

Facial expression is an inevitable aspect of human communication, and hence facial emotion recognition (FER) has become the basis for many machine vision applications. Many deep learning based FER models have been developed and shown good results on emotion recognition. However, FER using deep learning still suffering from illumination conditions, noise around the face such as hair, background, and other ambience conditions. To mitigate such issues and improve the performance of FER, we propose Enhanced Face Localization augmented Light Convolution Neural Network (EFL-LCNN). EFL-LCNN incorporates three phase pre-processing and Light CNN, a trimmed VGG16 model. Three phase pre-processing includes face detection, enhanced face region cropping for ambience noise removal and image enhancement using CLAHE for addressing illumination problems. Three phase pre-processing is followed by the implementation of Light CNN to improve FER performance with reduced complexity. The EFL-LCNN is rigorously tested on four publicly available benchmark datasets: JAFFE, CK, MUG and KDEF. It is observed from the empirical results that the EFL-LCNN boosted recognition accuracies significantly when compared with the state-of-the-art.

关键词： Convolutional Neural Networks Deep networks Facial emotion recognition Face localization Feature extraction image enhancement

来源：评论

学校读者我要写书评

暂无评论

Attention-Based image Caption Generation 5th

Attention-Based Image Caption Generation

引用

5th International Conference on Data Science, machine Learning and applications

作者： Manasa, M. Sowmya, D. Reddy, Y. Supriya Sreedevi, Pogula G Pulla Reddy Engn Coll Dept Comp Sci & Engn Data Sci Kurnool 5185007 India G Pulla Reddy Engn Coll Dept Comp Sci & Engn Kurnool 5185007 India Rajeev Gandhi Mem Coll Engn & Technol Dept Comp Sci & Engn Nandyal 518501 India

ISBN: (纸本)9789819780334;9789819780310;9789819780303

The automatic development of meaningful, detailed textual descriptions for supplied images is a difficult task in the fields of computer vision and natural language processing. As a result, an AI-powered image caption generator can be incredibly useful for producing captions. In this study, we present a unique method for creating picture captions utilizing an attention mechanism that concentrates on pertinent areas of the image while it creates captions. On benchmark datasets, our model, which uses deep neural networks to extract picture attributes and produce captions, obtains state-of-the-art results, confirming the effectiveness of the attention mechanism in raising the caliber of the generated captions. We also offer a thorough evaluation of the performance of our approach and talk about potential future directions for enhancing image caption generation.

关键词： image Caption Computer vision Natural Language processing Attention Mechanism Performance

来源：评论

学校读者我要写书评

暂无评论

image Segmentation Techniques: Statistical, Comprehensive, Semi-Automated Analysis and an Application Perspective Analysis of Mathematical Expressions

引用

ARCHivES OF COMPUTATIONAL METHODS IN ENGINEERING 2023年第1期30卷 457-495页

作者： Sakshi Kukreja, Vinay Chitkara Univ Inst Engn & Technol Ludhiana Punjab India

Segmentation has been a rooted area of research having diverse dimensions. The roots of image segmentation and its associated techniques have supported computer vision, pattern recognition, image processing, and it holds variegated applications in crucial domains. To compile the vast literature on machine learning and deep learning-based segmentation techniques and proffer statistical, comprehensive, semi-automated, and application-specific analysis, which could contribute to the ongoing research. 16,674 studies have been filtered out from the pool of 22,088 studies collocated by executing a search string on the Scopus database. These studies are analyzed for their meta-data, comprehensive content and reviewed to identify key research areas using the topic modeling-based method (LDA). Also, the segmentation role for mathematical expression recognition has been fathomed out. IEEE is a ubiquitous name in the terms of the renowned publisher, reputed journal (IEEE Access), and most cited affiliation (#10,472). Three out of five extracted topic solutions by the LDA model be evidence of streaming research areas in image segmentation. Medical image processing, machine vision and Object Identification are the accentuated domains in the context. The streamlining of comprehensive analysis puts forth neural network-based approaches as a trend. Inquisition of segmentation techniques for mathematical expressions articulate neural-based segmentation techniques (CNN, RNN, LSTM) as preeminent segmentation techniques and geometrical features as focused features of the process. To sum up, the purpose of the current study is to summarize the best available research on image segmentation after synthesizing the results of an assorted set of studies.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

A Survey on Graph Neural Networks and Graph Transformers in Computer vision: A Task-Oriented Perspective

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND machine INTELLIGENCE 2024年第12期46卷 10297-10318页

作者： Chen, Chaoqi Wu, Yushuang Dai, Qiyuan Zhou, Hong-Yu Xu, Mutian Yang, Sibei Han, Xiaoguang Yu, Yizhou Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China Chinese Univ Hong Kong Sch Sci & Engn Shenzhen 518172 Peoples R China Chinese Univ Hong Kong Future Network Intelligence Inst Shenzhen 518172 Peoples R China ShanghaiTech Univ Sch Informat Sci & Technol Shanghai 201210 Peoples R China Shanghai Engn Res Ctr Intelligent Vis & Imagi Shanghai 201210 Peoples R China

Graph Neural Networks (GNNs) have gained momentum in graph representation learning and boosted the state of the art in a variety of areas, such as data mining (e.g., social network analysis and recommender systems), computer vision (e.g., object detection and point cloud learning), and natural language processing (e.g., relation extraction and sequence learning), to name a few. With the emergence of Transformers in natural language processing and computer vision, graph Transformers embed a graph structure into the Transformer architecture to overcome the limitations of local neighborhood aggregation while avoiding strict structural inductive biases. In this paper, we present a comprehensive review of GNNs and graph Transformers in computer vision from a task-oriented perspective. Specifically, we divide their applications in computer vision into five categories according to the modality of input data, i.e., 2D natural images, videos, 3D data, vision + language, and medical images. In each category, we further divide the applications according to a set of vision tasks. Such a task-oriented taxonomy allows us to examine how each task is tackled by different GNN-based approaches and how well these approaches perform. Based on the necessary preliminaries, we provide the definitions and challenges of the tasks, in-depth coverage of the representative approaches, as well as discussions regarding insights, limitations, and future directions.

关键词： Task analysis Computer vision Three-dimensional displays Transformers Point cloud compression Visualization Videos Computer vision graph transformers graph neural networks medical image analysis point clouds and meshes vision and language

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：