检索结果-内蒙古大学图书馆

ieee International Conference on image processing (ICIP)

作者： Liu, Libo Fan, Xinxin Zhang, Xiaodong Hu, Qingmao Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

With the development of deep learning, deep convolution neural networks for medical image segmentation tasks have become more and more complex in pursuit of higher accuracy. In most scenarios, medical image segmentation pursues accuracy rather than speed, However, real-time performance is crucial in some scenarios, such as surgical navigation and diagnosis of acute stroke. So design of high-precision, lightweight and real-time medical image segmentation network has become an urgent need. To this end, a novel lightweight dual-domain network (LDD-Net) has been proposed in this paper. LDD-Net is comprised of two branches, learning respectively from the frequency domain and the spatial domain. In the frequency domain branch, the image spatial resolution is compressed via discrete cosine transform to have a large receptive field, so that better semantic context features can be learned. In the spatial domain branch, high-resolution feature representations with more details are learned. Finally, the learned features of these two branches are fused to yield high accuracy with low computational cost. The proposed method has been validated on two medical image segmentation datasets to yield the state-of-the-art performances with greatly reduced inference time and parameters of the learned models.

关键词： Medical image segmentation deep learning lightweight convolution neural networks lightweight dual-domain network

来源：评论

学校读者我要写书评

暂无评论

Reconstruction of Missing Multiband images for High Resolution Multispectral Sensors Using Wasserstein GAN 3

Reconstruction of Missing Multiband Images for High Resoluti...

引用

3rd ieee India Geoscience and Remote Sensing symposium, InGARSS 2023

作者： Hossain, Md Aminur Gupta, Ashutosh Paul, Subhajit Singh, Sanjay K. Naidu, S. Devakanth Dhar, Debajyoti Signal And Image Processing Area Space Applications Centre ISRO Ahmedabad India

ISBN: (纸本)9798350325591

Today's Multispectral (MX) imaging systems contain multiple bands with unprecedented high spatial resolution and swath. Due to the complex mechanisms involved in image acquisition and data transmission for such systems, the information in all or a subset of these bands may be lost, rendering the dataset unfit for end-use. In such scenarios, it is imperative to design methods that can faithfully reconstruct the data given the available subset of bands or a simultaneously acquired Panchromatic image (PAN). In this paper, we propose a method to reconstruct lost multiband regions in MX images using a Wasserstein Generative Adversarial Network (WGAN) with expert regularization. Specifically, we demonstrate the strength of our network by synthesizing RGB (Red, Green, Blue) bands from co-registered Near-InfraRed (NIR) and PAN images as input. Qualitative and quantitative results obtained for experiments performed on Cartosat-MX images show that our method is able to reconstruct images that are spatially and spectrally accurate. © 2023 ieee.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

LOW-COMPLEXITY MULTI-MODEL CNN IN-LOOP FILTER FOR AVS3 47

LOW-COMPLEXITY MULTI-MODEL CNN IN-LOOP FILTER FOR AVS3

引用

47th ieee International Conference on Acoustics, Speech and signal processing (ICASSP)

作者： Wang, Shen Fu, Yibing Zhu, Chen Song, Li Zhang, Wenjun Shanghai Jiao Tong Univ Inst Image Commun & Network Engn Shanghai Peoples R China Shanghai Jiao Tong Univ AI Inst MoE Key Lab Artificial Intelligence Shanghai Peoples R China

ISBN: (纸本)9781665405409

Convolutional neural network (CNN) has demonstrated powerful capabilities in many image/video processing tasks. In this paper, a low-complexity multi-model CNN in-loop filtering scheme is proposed for AVS3. Firstly, we carefully choose simplified ResNet as the lightweight single model of our proposed network. Subsequently, based on the selected single model, the multi-model iterative training framework is proposed to train a multi-model filter, where the network depth and the number of multi-models are customized for different ranges of bit rate to achieve the trade-off between model performance and computational complexity. Experimental results show that our method achieves on average 6.06% BD-rate reduction on Y component under all intra configuration. Compared to other CNN filters with comparable performance, our proposed multi-model filter can significantly reduce the decoder complexity, and the experimental results indicate that the decoding time can be saved by 26.6% on average.

关键词： Audio Video Coding standard (AVS3) In-Loop Filter Multi-Model CNN

来源：评论

学校读者我要写书评

暂无评论

SBSR: A Simple Residual Network for Efficient Burst Super-Resolution

SBSR: A Simple Residual Network for Efficient Burst Super-Re...

引用

2023 ieee International Conference on Multimedia and Expo Workshops, ICMEW 2023

作者： Lei, Min He, Kun Jiang, Chunlin Shao, Jie Sichuan Artificial Intelligence Research Institute Yibin China University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9798350313154

Burst Super-Resolution (BurstSR) attempts to restore a high resolution image from a misaligned, low-resolution RAW burst sequence. Current models for BurstSR are complex and require significant computational resources for training and practical application. This paper introduces a new, simplified model called Simple Residual Network for Burst Super-Resolution (SBSR), which includes multiple Simple Residual Networks (SRNs) that not only greatly reduce the parameters due to their simple structure, but also speed up the training and inference process with excellent feature integration ability, while maintaining good performance. Furthermore, we propose a Pre-trained Shallow Feature Extractor (PSFE) for contrastive loss to further improve the performance of SBSR. Experimental results show that SBSR surpasses existing methods in terms of the trade-off between performance and efficiency. Code is available at https://***/githublei-min/SBSR. © 2023 ieee.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Online Learning on Non-Stationary Data Streams for image Recognition using Deep Embeddings

Online Learning on Non-Stationary Data Streams for Image Rec...

引用

ieee symposium Series on computational intelligence (ieee SSCI)

作者： Vaquet, Valerie Hinder, Fabian Vaquet, Jonas Brinkrolf, Johannes Hammer, Barbara Bielefeld Univ Machine Learning Grp Bielefeld Germany

ISBN: (纸本)9781728190488

Deep neural networks offer state-of-the-art technologies for highly nonlinear domains such as image processing;yet their initial training requires large amounts of data, such that they are not directly suited for online learning scenarios for streaming data where class distributions or class labels may change over time. In this contribution, we investigate the suitability of a combination of recent online learning technologies, which have been proposed for learning with streaming data and concept drift in simpler settings, and deep representations of image data as provided by deep networks trained in batch mode, to offer flexible learning technologies for streaming data from the image domain.

关键词： streaming data learning with drift online classification

来源：评论

学校读者我要写书评

暂无评论

Various Algorithms and Techniques for Traffic Density Estimation 1

Various Algorithms and Techniques for Traffic Density Estima...

引用

1st International Conference on computational Science and Technology, ICCST 2022

作者： Venkat, Sanjay Sarkar, Swagata Shreemadhi, B. Siri, Karanam Poorna Bavanika, M. Sri Sairam Engineering College Artificial Intelligence and Data Science Chennai India

ISBN: (纸本)9781665476553

Traffic has been a major problem in recent times. Traffic management is a must for safer and faster transportation. Automatic smart signal controlling systems respond to day-to-day world traffic densities to provide precedence and reduction in cross-road delays for travelers. According to the traffic density, the time between signals is adjusted so that the waiting time in traffic reduces. The ML model is capable of detecting accidents and immediately sends notifications or alert messages to nearby hospitals. The model tracks the GPS location of the ambulance and ensures no red signal in its pathway. Zebra crossing signals are also included, the signal timings are switched based on the crossing crowd. Automatic Smart signal Control is a complete Machine Learning based project with some applications of IoT and Video / image processing. Implementation of the model all over the major signals and junctions provides faster and safer transportation. © 2022 ieee.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

An accelerated algorithm for ECG signal denoising 16

An accelerated algorithm for ECG signal denoising

引用

16th International Conference on signal-image Technology and Internet-Based Systems (SITIS)

作者： De Luca, Pasquale Galletti, Ardelio Marcellino, Livia Parthenope Univ Naples Dept Sci & Technol Naples Italy

ISBN: (纸本)9781665464956

The Electrocardiogram (ECG) signal is an important tool for cardiovascular diseases analysis. However, still today acquisition devices produce noisy signals that degrades the quality of information by corrupting important features. To improve the quality of the acquired data a filtering process is mandatory. Moreover, a real-time filtering of ECGs, in order to obtain a diagnosis as quickly as possible is a very interesting challenge. In this paper, we consider as denoising filter, the Savitzky-Golay method and we propose a parallel algorithm implementing it. The procedure exploits the computational power of Graphics processing Units (GPUs). Results in terms of performance and quality are provided.

关键词： ECG denoising SG filter parallel algorithms GP-GPU

来源：评论

学校读者我要写书评

暂无评论

Efficient Multiplication and Accumulation of Signed Numbers 8

Efficient Multiplication and Accumulation of Signed Numbers

引用

8th ieee International symposium on Smart Electronic Systems, iSES 2022

作者： Siddamshetty, Susheel Ujwal Nambi, Suresh Boppu, Srinivas Ghosh, Debapratim India Ceremorphic India Pvt. Ltd. India

ISBN: (纸本)9798350399226

Multiply and Accumulate (MAC) is an essential operation for domain-specific hardware accelerators used in the application domains such as digital signal processing, image processing, and artificial intelligence. Moreover, in artificial intelligence or machine learning accelerators, many inputs and weights need to be multiplied and accumulated in parallel to increase the performance. In this paper, we consider the problem of multiplying 32 pairs of 8-bit signed numbers and accumulating them in parallel. We use the Radix-4 Booth algorithm to generate the partial product rows for all 32 pairs of operands and group similar partial product rows as a set. Further, each set is compressed using a customized signed Wallace tree until two rows, which are added using a carry-lookahead adder. Our customized Wallace tree shows 1.3 x area improvement and reduced delay compared to a standard reduction tree when synthesized using a 5 nm process node's standard cell libraries. The proposed MAC design is also 5 % area-efficient compared to a compiler optimized MAC design. © 2022 ieee.

关键词： Digital signal processing

来源：评论

学校读者我要写书评

暂无评论

Automotive Scenarios for Trajectory Tracking using Machine Learning Techniques and image processing

Automotive Scenarios for Trajectory Tracking using Machine L...

引用

International symposium on Applied computational intelligence and Informatics ( SACI)

作者： Delia Moga Ioan Filip Department of Automation and Applied Informatics Politehnica University of Timisoara Timisoara Romania

This paper presents a study on using innovative machine learning techniques that can be applied in automotive traffic scenarios to increase a vehicle’s level of autonomy. The overtaking traffic scenario is treated for predicting the vehicle trajectory when overtaking another vehicle and the data is obtained by image processing using a video camera. Two different methods are compared, first by using classic tracking methods and a Kalman filter (as an adaptive filter) and second by using a machine learning technique - Support Vector Machine. The present article uses as inputs the data received from the camera and focuses on tracking selected objects and estimating their position using mainly image processing in automotive scenarios. The main purpose of this work is to experiment and compare different tracking modes to determine those that have the best performances in terms of runtime, memory usage and prediction accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PointRas: Uncertainty-Aware Multi-Resolution Learning for Point Cloud Segmentation

引用

ieee TRANSACTIONS ON image processing 2022年 31卷 6002-6016页

作者： Zheng, Yu Xu, Xiuwei Zhou, Jie Lu, Jiwen Tsinghua Univ Beijing Natl Res Ctr Informat Sci & Technol BNRis Dept Automat Beijing 100084 Peoples R China

In this paper, we propose an uncertainty-aware multi-resolution learning for point cloud segmentation, named PointRas. Most existing works for point cloud segmentation design encoder networks to obtain better representation of local space in point cloud. However, few of them investigate the utilization of features in the lower resolutions produced by encoders and consider the contextual learning between various resolutions in decoder network. To address this, we propose to utilize the descriptive characteristic of point clouds in the lower resolutions. Taking reference to core steps of rasterization in 2D graphics where the properties of pixels in high density are interpolated from a few primitive shapes in rasterization rendering, we use the similar strategy where prediction maps in lower resolution are iteratively regressed and upsampled into higher resolutions. Moreover, to remedy the potential information deficiency of lower-resolution point cloud, we refine the predictions in each resolution under the criterion of uncertainty selection, which notably enhances the representation ability of the point cloud in lower resolutions. Our proposed PointRas module can be incorporated into the backbones of various point cloud segmentation frameworks, and brings only marginal computational cost. We evaluate the proposed method on challenging datasets including ScanNet, S3DIS, NPM3D, STPLS3D and ScanObjectNN, and consistently improve the performance in comparison with the state-of-the-art methods.

关键词： Point cloud compression Three-dimensional displays Decoding signal resolution Shape Interpolation Semantics Point cloud segmentation semantic segmentation multi-resolution learning contextual learning

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：