检索结果-内蒙古大学图书馆

IEEE International Conference on Acoustics, Speech and Signal processing

作者： Seungwon Lee Jinhee Lee Joonki Paik Image Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging ScienceMultimedia and Film Chung-Ang University Seoul Korea

ISBN: (纸本)9781457705380

A multiple color-filter aperture (MCA) camera can provide depth information as well as color and intensity in the single-camera framework, where the MCA generates misalignment between color channels depending on the distance of a region-of-interest. In this paper, we present a simultaneous object tracking and depth estimation approach based on the color shifting property of an MCA camera. An object region is first extracted by using Markov Chain Monte Carlo (MCMC) sampling-based particle filter. The extracted object's region has color misalignment among RGB planes depending on the distance of the object. We estimate color shifting vectors (CSVs) between green-and-red (G-R) and green-and-blue (G-B) channels using a simplified elastic registration algorithm. Using the color shifting property of the MCA camera, the depth of the object's region is estimated from CSVs. From experimental results, we can show the MCA camera-based surveillance system can estimate depth information as well as track object.

关键词： Video surveillance particle filters image registration image color analysis image motion analysis tracking objects system buses compensatory amounts Maximum credible accidents color cast Cameras Misalignment Color SURVEILLANCE systems

来源：评论

学校读者我要写书评

暂无评论

Cross-user Gesture Recognition Based on Deep Domain Adaptation Networks

Cross-user Gesture Recognition Based on Deep Domain Adaptati...

引用

第43届中国控制会议

作者： Zhongzheng Fu Xinrun He Haoyuan Wang Xingjian Chen Yixuan Li Jian Huang Ministry of Education Key Laboratory of Image Processing and Intelligent Control Hubei Key Laboratory of Brain-inspired Intelligent Systems School of Artificial Intelligence and Automation Huazhong University of Science and Technology

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

This study introduces an innovative approach for gesture recognition in smart wearable devices using a deep domain adaptation model, focusing on the challenges posed by heterogeneous user environments and the need for precise, adaptable, and personalized gesture recognition systems. Traditional methods based on machine learning and deep learning techniques, while effective, struggle with the variance in data distribution among different users, leading to accuracy challenges. To address this,the study proposes the Domain Kernel-Alignment Adaptation Network(DKAN) model, utilizing a new Kernel-Aligned Multi-kernel Maximum Mean Discrepancy(KAMMD) method within deep networks. By calculating kernel alignments between source and target domains and adjusting weights of Gaussian kernels accordingly, DKAN emphasizes features conducive to transfer learning, enabling more accurate cross-user gesture recognition. The model achieves a significant average accuracy of 97.3% across 21 gestures, highlighting its potential in practical applications. This advancement addresses challenges in traditional gesture recognition methods and sets a new direction for future research in smart wearable technology.

关键词： Gesture recognition Kernel-alignment Domain adaptation

来源：评论

学校读者我要写书评

暂无评论

Adaptive regularized multichannel Blind deconvolution using alternating minimization

Adaptive regularized multichannel Blind deconvolution using ...

引用

IEEE International Advance Computing Conference, IACC

作者： Soniya James Vivek Maik Joonki Paik Department of Electronics and Communication The Oxford College of Engineering Bangalore India Image processing and Intelligent Systems Laboratory Chung-ang university Korea

ISBN: (纸本)9781479980482

Multichannel blind deconvolution is an ill posed problem where regularizers plays an important role. Adaptive regularization is used to obtain better quality restored image. This adds penalty weighted term along with image regularizer. The Isotropic TV image regularizers have chosen along with directional priors which preserves the over smoothing of the edges when compare to horizontal and vertical priors, thereby improving the Peak Signal to Noise Ratio(PSNR) of the reconstructed image. The Blind deconvolution problem can be solved using Alternating minimization algorithm as it is best suited for two unknown variables. The formulation of blind deconvolution can be l 1 regularized optimization and geometry can be l 2 . It results in hard optimization problem. The minimization step alternates between two sub optimization problems and this can be solve efficiently using Augmented Lagrangian method(ALM), where each iteration undergoes Bregman variable splitting or iterative method. This converted unconstrained problem in to constrained. This method can be applicable to medical images such as X Ray in order to reduce the amount of rays penetrating in to the body and to observe more details.

关键词： Minimization Deconvolution Optimization image restoration TV image reconstruction Convergence

来源：评论

学校读者我要写书评

暂无评论

WAVELENGTH-ADAPTIVE image FORMATION MODEL AND GEOMETRIC CLASSIFICATION FOR DEFOGGING UNMANNED AERIAL VEHICLE imageS

WAVELENGTH-ADAPTIVE IMAGE FORMATION MODEL AND GEOMETRIC CLAS...

引用

IEEE International Conference on Acoustics, Speech, and Signal processing

作者： Inhye Yoon Monson H. Hayes Joonki Paik Image Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul Korea

ISBN: (纸本)9781479903573

In this paper, we present an image enhancement algorithm based on the wavelength-adaptive image formation model and geometric classification for defogging UAV images. We first generate a labeled image using geometric class-based segmentation. We then generate a modified transmission map based on the wavelength-adaptive image formation model with scattering coefficients in the labeled image. We also estimate the atmospheric light from the modified transmission map instead of simply choosing the brightest pixel. The proposed method can significantly enhance the visibility of foggy UAV images compared with existing monochrome model-based defogging method. The proposed algorithm can enhance the visibility by removing atmospheric degradation factor in airborne images acquired by aerial platforms such as satellite, airplane, and UAV under critical weather conditions such as haze, fog, and smoke.

关键词： image enhancement image defogging unmanned aerial vehicle image enhancement images drone honey bees Unmanned Aerial Vehicle vehicle image enhancement algorithm image formation aerial platforms UNMANNED visibility ANTENNA Scattering coefficient BRIGHT

来源：评论

学校读者我要写书评

暂无评论

Deep Tracking Using Convolutional Features and Adaptive Frame Update

Deep Tracking Using Convolutional Features and Adaptive Fram...

引用

IEEE International Conference on Consumer Electronics - Berlin (ICCE-Berlin)

作者： Yeongbin Kim Hasil Park Joonki Paik Image Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul Korea

This paper presents a robust tracking algorithm using convolutional features. The proposed tracking algorithm consists of three steps: i) training correlation filters using features extracted by a convolutional neural network, ii) localizing the target position in the next frame by multiplying weight and correlation response of each layer, and iii) re-training correlation filters every 10-frame using the proposed position error score. Experimental results show that the proposed algorithm outperforms an existing deep learning-based tracker.

关键词： Correlation Feature extraction Target tracking Pattern recognition Object tracking image color analysis Silicon

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based number detection and recognition for gas meter reading

引用

IEIE Transactions on Smart processing and Computing 2019年第5期8卷 367-372页

作者： Son, Changeui Park, Seokmok Lee, JaeMin Paik, Joonki Department of Image Engineering Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul06974 Korea Republic of

The meter reading-system field has been researched from conventional methods centered on image processing technology to techniques based on learning methods such as machine learning or deep learning. The biggest problem for meter reading systems based on computer vision is difficulty in recognizing the various kinds of meters. In fact, there are more than five major manufacturers for the meters installed in Korea. There are different meter reading areas, ID regions, and number formats by version. Because of these problems, most of the meter reading is still done hands-on. In this paper, we present an automatic meter-reading system that can work simply and efficiently, compared to existing meter reading systems that need a skilled worker. Our meter reading system consists of three parts: i) detection of meter-reading and ID regions using You Only Look Once (YOLO), ii) digit segmentation for recognition, and iii) convolutional neural network (CNN)-based digit recognition. It is possible to robustly detect and recognize various meter types by using the method presented here. Therefore, it can provide an environment where gas meter checkers can work efficiently without inconvenient procedures. Copyrights © 2019 The Institute of Electronics and Information Engineers

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

GraphMFT: A graph network based multimodal fusion technique for emotion recognition in conversation

arXiv

引用

arXiv 2022年

作者： Li, Jiang Wang, Xiaoping Lv, Guoqing Zeng, Zhigang Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan430074 China Hubei Key Laboratory of Brain-inspired Intelligent Systems Wuhan430074 China

Multimodal machine learning is an emerging area of research, which has received a great deal of scholarly attention in recent years. Up to now, there are few studies on multimodal Emotion Recognition in Conversation (ERC). Since Graph Neural Networks (GNNs) possess the powerful capacity of relational modeling, they have an inherent advantage in the field of multimodal learning. GNNs leverage the graph constructed from multimodal data to perform intra- and inter-modal information interaction, which effectively facilitates the integration and complementation of multimodal data. In this work, we propose a novel Graph network based Multimodal Fusion Technique (GraphMFT) for emotion recognition in conversation. Multimodal data can be modeled as a graph, where each data object is regarded as a node, and both intra- and inter-modal dependencies existing between data objects can be regarded as edges. GraphMFT utilizes multiple improved graph attention networks to capture intra-modal contextual information and inter-modal complementary information. In addition, the proposed GraphMFT attempts to address the challenges of existing graph-based multimodal conversational emotion recognition models such as MMGCN. Empirical results on two public multimodal datasets reveal that our model outperforms the State-Of-The-Art (SOTA) approaches with the accuracy of 67.90% and 61.30%. Copyright © 2022, The Authors. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Wavelet-based enhancement of color image using combined local variance and entropy analysis

Wavelet-based enhancement of color image using combined loca...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Sinyoung Jun Eunsung Lee Sangjin Kim Joonki Paik Image Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul South Korea

ISBN: (纸本)9781424443147

This paper presents a novel wavelet-based image enhancement approach to reduce noise in a single-sensor color camera. Most traditional noise reduction methods tend to over-suppress high-frequency details. For overcoming this problem we first decompose the input image into flat and edge regions, and adaptively remove noise by multiplying alpha map and wavelet transform coefficients of LH, HL, and HH bands. After removing noise in the flat region, we further remove noise in edge regions by adaptive shrink of wavelet coefficients based on the entropy. Experimental result show the proposed algorithm is proved to be able to reduce noise without losing sharp details and is suitable for commercial low-cost such as digital cameras, CCTV, and surveillance systems.

关键词： Wavelet analysis Entropy Analysis of variance image analysis image color analysis Noise reduction Colored noise image enhancement Cameras Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

image restoration using alpha map-based fusion for multiple color aperture computational camera

Image restoration using alpha map-based fusion for multiple ...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Eunsung Lee Vivek Maik Sinyoung Jun Sangjin Kim Joonki Paik Image Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul South Korea

ISBN: (纸本)9781424443147;9781424443161

We present a novel image restoration approach by fusing multiple images acquired by a multiple color aperture computational camera for overcoming the limit of conventional image restoration algorithms, such as high computational load and post-processing artifacts. The proposed restoration framework utilizes color matching, alignment, and fusion of multiple images acquired by using multiple color apertures. The alpha map-based image fusion step successfully restores high-frequency components of meaningful edge regions. The proposed scheme can achieve automatic focusing and varying depth of filed at low cost for low-end consumer cameras.

关键词： image restoration Apertures Focusing Signal processing algorithms Color image fusion Smart cameras Costs Digital images Educational technology

来源：评论

学校读者我要写书评

暂无评论

Vaguelette-wavelet decomposition for real-time image restoration using directional wavelet bases

Vaguelette-wavelet decomposition for real-time image restora...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Wonseok Kang Eunsung Lee Sangjin Kim Joonki Paik Image Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul South Korea

Conventional image restoration filters, such as Wiener filter, often exhibit either noise amplification or over-smoothing problem. On the other hand, advanced image restoration techniques, such as iterative regularization or combined Fourier and wavelet domain thresholding techniques, is not suitable for real-time application because of high computational overhead. For overcoming these problems, we adopt vaguelette-wavelet decomposition (VWD) approach to realtime, space-frequency adaptive image restoration based on the estimated point spread-function (PSF) and directional wavelet bases.

关键词： image restoration Wavelet transforms Low pass filters Filtering algorithms Real time systems Noise

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：