检索结果-内蒙古大学图书馆

A fast learning approach for autonomous navigation using a deep reinforcement learning method

ELECTRONICS LETTERS 2021年第2期57卷 50-53页

作者： Ejaz, Muhammad Mudassir Tang, Tong Boon Lu, Cheng-Kai Univ Teknol Petronas Dept Elect & Elect Engn Seri Iskandar Perak Malaysia Univ Teknol Petronas Inst Hlth & Analyt Seri Iskandar Perak Malaysia

Deep reinforcement learning-based methods employ an ample amount of computational power that affects the learning process. This paper proposes a novel approach to speed up the training process and improve the performance of autonomous navigation for a tracked robot. The proposed model named "layer normalization dueling double deep Q-network" has been trained in a virtual environment and then implemented it to a tracked robot for testing in a real-world scenario. Depth images have been used instead of RGB images to preserve the temporal information. Features are extracted using convolutional neural networks, and actions are derived using the dueling double deep Q-network. The input data has been normalized before each convolutional layer, which reduces the covariate shift by 69%. This end-to-end network architecture of the proposed model provides stability to the network, relieves the burden of computational cost, and converges in much less number of episodes. Compared with three Q-variant models, the proposed model demonstrates outstanding performance in terms of episodic reward and convergence rate. The proposed model took 12.8% fewer episodes for training compared to other models.

关键词： Optical, image and video signal processing Robotics computer vision and image processing techniques Control engineering computing Reinforcement learning Neural nets

来源：评论

学校读者我要写书评

暂无评论

A novel video noise reduction method based on PDE, adaptive grouping, and thresholding techniques

引用

JOURNAL OF ENGINEERING-JOE 2021年第10期2021卷 605-620页

作者： Yahya, Ali Abdullah Tan, Jieqing Hu, Min Anqing Normal Univ Sch Comp & Informat Anqing 246011 Peoples R China Hefei Univ Technol Sch Comp & Informat Hefei Peoples R China

Undoubtedly, video block-matching and 3D filtering (VBM3D) has achieved a significant improvement in video denoising. Nevertheless, in practice, failure to distinguish between the different noise areas, ignoring noise variances and pixel intensity, false-similar patches, and poor matching are the challenges faced by the VBM3D filter. To avoid these drawbacks, a new video denoising algorithm is proposed. This algorithm based on the nature of the noise areas and the spatial distance between the reference block and its candidate blocks. In the algorithm, hard-thresholding in VBM3D is replaced by adaptive filtering. In this adaptive filter, soft-thresholding is applied to the heavily contaminated areas, whereas anisotropic diffusion filter is applied to the slight-noise areas. Applying adaptive filtering creates a balance between noise removal and edges conservation. To avert the occurrence of the poor choice of the threshold, noise variances, clean image coefficients, and pixel intensity are taken into consideration during computing the proposed adaptive threshold. Due to the strong possibility of similar correlative blocks happening in the vicinity, an adaptive grouping technique is proposed to compute the distance between a reference block and its candidate blocks. Applying this technique helps to reduce the occurrence of false-similar blocks and poor matching.

关键词： 3D filtering computer vision and image processing techniques candidate blocks adaptive filters slight-noise areas adaptive filtering noise removal edges conservation heavily contaminated areas adaptive threshold similar correlative blocks Optical, image and video signal processing different noise areas image matching adaptive filter video block-matching video noise reduction method adaptive grouping technique false-similar patches noise variances Filtering methods in signal processing VBM3D filter pixel intensity Video signal processing soft-thresholding video denoising algorithm thresholding techniques false-similar blocks video signal processing Integral transforms Interpolation and function approximation (numerical analysis) image recognition poor matching reference block anisotropic diffusion filter hard-thresholding filtering theory image denoising Other topics in statistics

来源：评论

学校读者我要写书评

暂无评论

WG²AN: Synthetic wound image generation using generative adversarial network

引用

JOURNAL OF ENGINEERING-JOE 2021年第5期2021卷 286-294页

作者： Sarp, Salih Kuzlu, Murat Wilson, Emmanuel Guler, Ozgur Old Dominion Univ Batten Coll Engn & Technol Norfolk VA 23529 USA eKare Inc Fairfax VA USA

In part due to its ability to mimic any data distribution, Generative Adversarial Network (GAN) algorithms have been successfully applied to many applications, such as data augmentation, text-to-image translation, image-to-image translation, and image inpainting. Learning from data without crafting loss functions for each application provides broader applicability of the GAN algorithm. Medical image synthesis is also another field that the GAN algorithm has great potential to assist clinician training. This paper proposes a synthetic wound image generation model based on GAN architecture to increase the quality of clinical training. The proposed model is trained on chronic wound datasets with various sizes taken from real hospital environments. Hyperparameters such as epoch count and dataset size for training tasks are studied to find optimum training conditions as well. The performance of the developed model was evaluated through a mean squared error (MSE) metric to determine the similarity between generated and actual wounds. Visual inspection is performed to examine generated wound images. The results show that the proposed synthetic wound image generation (WG(2)AN) model has great potential to be used in medical training and performs well in producing synthetic wound images with a 1000-image training dataset and 200 epochs of training.

关键词： computer vision and image processing techniques optimum training conditions chronic wound datasets text-to-image translation wounds medical computing medical image synthesis Biology and medical computing learning (artificial intelligence) data augmentation GAN architecture medical image processing Biomedical measurement and imaging GAN algorithm image-to-image translation Optical, image and video signal processing actual wounds feature extraction 1000-image training dataset synthetic wound images clinical training Patient diagnostic methods and instrumentation mean square error methods clinician training broader applicability data distribution image inpainting synthetic wound image generation model image classification Generative Adversarial Network algorithms medical training Other topics in statistics

来源：评论

学校读者我要写书评

暂无评论

Fast and robust motion averaging via angle constraints of multi-view range scans

引用

JOURNAL OF ENGINEERING-JOE 2021年第2期2021卷 104-113页

作者： Zhang, Xin Zhang, Yan Qu, Chengzhi Tan, Zhuangbin Sun Yat Sen Univ Sch Aeronaut & Astronaut Shenzhen CampusGongchang Rd Shenzhen 518106 Peoples R China

The motion averaging problem arises when recovering the motions for a set of scans in three-dimensional (3D) reconstruction. Motion averaging is taken as an optimisation problem, whose solution can be obtained via matrix decomposition in principal component analysis. The latest motion averaging methods utilize the Cauchy kernel function or overlap rate to construct the weighted matrix in the cost function, yielding weighted low-rank sparse matrix decomposition solutions. Nevertheless, the over-reliance on the initial value and high computational complexity remain two major problems. Here, we aim to improve the motion averaging performance via a fast and robust method based on the angle constraints of multiple scans. The additional term representing the angle constraint is added into the original cost function. By doing this, two benefits are facilitated: 1) the iteration times for the optimisation process are reduced;and 2) it effectively mitigates the over-reliance on the initial value and thus caters for outliers and random noise of initial motions. Compared with state-of-the-art motion averaging methods, it is indicated that the proposed method is more efficient and robust for numerical simulations of using both simulated motions and real 3D scanning data, given a large range of angle constraint values.

关键词： Algebra Optimisation techniques Interpolation and function approximation (numerical analysis) Optical, image and video signal processing Algebra Optimisation techniques Interpolation and function approximation (numerical analysis) Computational complexity computer vision and image processing techniques Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

LBTS-Net: A fast and accurate CNN model for brain tumour segmentation

引用

HEALTHCARE TECHNOLOGY LETTERS 2021年第2期8卷 31-36页

作者： Abdullah, Mohammed A. M. Alkassar, Sinan Jebur, Bilal Chambers, Jonathon Ninevah Univ Comp & Informat Engn Dept Mosul Iraq Univ Leicester Sch Engn Leicester Leics England

An accurate tumour segmentation in brain images is a complicated task due to the complext structure and irregular shape of the tumour. In this letter, our contribution is twofold: (1) a lightweight brain tumour segmentation network (LBTS-Net) is proposed for a fast yet accurate brain tumour segmentation;(2) transfer learning is integrated within the LBTS-Net to fine-tune the network and achieve a robust tumour segmentation. To the best of knowledge, this work is amongst the first in the literature which proposes a lightweight and tailored convolution neural network for brain tumour segmentation. The proposed model is based on the VGG architecture in which the number of convolution filters is cut to half in the first layer and the depth-wise convolution is employed to lighten the VGG-16 and VGG-19 networks. Also, the original pixel-labels in the LBTS-Net are replaced by the new tumour labels in order to form the classification layer. Experimental results on the BRATS2015 database and comparisons with the state-of-the-art methods confirmed the robustness of the proposed method achieving a global accuracy and a Dice score of 98.11% and 91%, respectively, while being much more computationally efficient due to containing almost half the number of parameters as in the standard VGG network.

关键词： convolution brain images Patient diagnostic methods and instrumentation neural nets brain Biology and medical computing accurate CNN model computer vision and image processing techniques LBTS-Net VGG-19 networks lightweight brain tumour segmentation network fast CNN model biomedical MRI standard VGG network Optical, image and video signal processing image segmentation Biomedical magnetic resonance imaging and spectroscopy lightweight convolution neural network image classification tumours robust tumour segmentation medical image processing learning (artificial intelligence) tumour labels Medical magnetic resonance imaging and spectroscopy tailored convolution neural network complext structure accurate tumour segmentation fast yet accurate brain tumour segmentation

来源：评论

学校读者我要写书评

暂无评论

An insulator inspection method based on deep learning applicable to multi-scale and occlusion conditions

引用

JOURNAL OF ENGINEERING-JOE 2021年第4期2021卷 216-225页

作者： Wu, Junpeng Tang, Shaobo Li, Xianglei Northeast Elect Power Univ Sch Elect Engn Jilin Jilin Peoples R China

As an important equipment of power system, the insulator's normal operation is the basis to ensure the safe operation of the power system. The insulator positioning and identification technology based on machine vision can quickly and accurately complete the inspection of insulators on site and effectively save the cost of operation and maintenance. This paper proposes an insulator inspection method based on region-convolutional neural networks (RCNNs). First, the dataset of the insulator image is preprocessed by means of data expansion. Then, the feature extraction of the insulator image is realised by using the zeiler fergus (ZF) network. The k-means clustering method is used to optimise the selection of anchor points. Meanwhile, the non-maximum suppression post-processing algorithm is improved, and a non-linear penalty factor is introduced to adapt to multi-scale and overlapping occlusion insulator inspection. Experimental results show that the improved faster RCNNs insulator inspection method can accurately obtain the coordinate frame and the corresponding probability value of the insulator object and improve the average precision by 10.43%, achieving the accurate inspection of the insulator object.

关键词： computer vision and image processing techniques power engineering computing maintenance image segmentation multiscale conditions Inspection and quality control nonlinear penalty factor probability deep learning (artificial intelligence) Optical, image and video signal processing faster RCNNs insulator inspection method insulator image feature extraction K-means clustering method Power engineering computing Power line supports, insulators and connectors pattern clustering machine vision Zeiler Fergus network insulator positioning nonmaximum suppression post-processing algorithm inspection identification technology RCNNs region-convolutional neural networks overlapping occlusion insulator inspection deep learning insulators convolutional neural nets Data handling techniques power system data expansion computer vision Other topics in statistics

来源：评论

学校读者我要写书评

暂无评论

Plant leaf classification and retrieval using multi-scale shape descriptor

引用

JOURNAL OF ENGINEERING-JOE 2021年第8期2021卷 467-475页

作者： Xu, Guoqing Li, Chen Nanyang Inst Technol Sch Informat Engn 80 ChangJiang Rd Nanyang Peoples R China North China Univ Technol Sch Comp Sci 5 Jinyuanzhuang Rd Beijing Peoples R China

Plant leaf classification is a significant and challenging research problem in computer vision area. In this study, an original multi-scale shape descriptor is presented to perform leaf classification and retrieval. Firstly, a novel iterative rule is proposed as scales generation method, which is parameter free. Secondly, leaf contour points are represented by angle information which is calculated using their neighbour points under each scale. The angle information representation is invariant to image rotation, translation and scaling. More importantly, it can describe leaf in a hierarchical way by capturing leaf features from global to local variations. Then Fast Fourier Transform operation is applied to make the representation more compact and independent from starting point. Subsequently, for leaf retrieval the dissimilarity of each pair of leaf under each scale is computed using city block metric. And support vector machine is used as classifier for leaf classification. Finally, experiments and comparisons with multiple state-of-the-art approaches are performed. The classification accuracy was 96.85% and 93.56% respectively on Swedish and Flavia leaf datasets. The mean average precision score was 66.42%, 76.69% and 44.14% respectively on Flavia, Swedish and MEW2012 leaf datasets. The results demonstrate that the proposed method has excellent performance.

关键词： Optical, image and video signal processing image recognition Other topics in statistics computer vision and image processing techniques Information retrieval techniques Biology and medical computing

来源：评论

学校读者我要写书评

暂无评论

Could you love one of these?

引用

Engineering and Technology 2021年第2期16卷 60-63页

作者： Birkett, Dea

What does it mean for a human to make an emotional connection to a piece of technology? Can we really feel for a machine, and can the machine feel anything back? 'ALEXAAAAA ...’ The most common name shouted out loud in our sitting rooms isn’t a beloved child’s, parent’s or spouse’s, but belongs to a piece of technology. In these socially distanced times, we’re directly communicating less and less with each other, more and more through and with technologies.

关键词： Robotics human feelings deep learning companionship image recognition machine learning deep learning (artificial intelligence) speech emotional intelligence emotion AI techniques artificial intelligence speech recognition facial expression classification sensor-based emotion recognition robot pets face recognition Control engineering computing Speech recognition and synthesis computer vision image classification computer vision and image processing techniques emotion recognition Speech processing techniques robot vision human-robot interaction acoustic prosodic feature analysis intelligent robots

来源：评论

学校读者我要写书评

暂无评论

H.266/VVC fast intra prediction using Sobel edge features

引用

ELECTRONICS LETTERS 2021年第1期57卷 11-13页

作者： Yang, Shih-Hsuan Hsiao, Sheng-Jung Natl Taipei Univ Technol Dept Comp Sci & Informat Engn Taipei Taiwan

Versatile video coding is the next-generation video coding standard. Compared with the previous high efficiency video coding standard, versatile video coding reduces 30% or more bitrate but requires significantly higher encoding complexity. This Letter proposes a fast intra prediction algorithm for partition type selection and mode decision of versatile video coding. The Sobel operator is employed to extract the gradient intensity and edge direction of coding blocks. Early skip conditions for partition types are developed based on the dominant edge indicated by block gradients. The intra prediction modes are further restricted to the directions close to the edge orientation of a coding block. Experimental results indicate that the proposed method in the Intra-only configuration saves 34.66% of the encoding time with a slight (0.61%) increase in Bjontegaard delta bit rate, which achieves the best tradeoff between acceleration and quality among all the investigated methods.

关键词： image and video coding image recognition computer vision and image processing techniques Video signal processing

来源：评论

学校读者我要写书评

暂无评论

YOU MAY ENTER: Automated ID checks face scrutiny

引用

Engineering and Technology 2021年第6期16卷 26-27页

作者： Courtney, Martin

This article discusses the use of a contactless AI-driven facial-recognition system being used for ID checks and queue management at the Tokyo Olympics 2020. This will be used for staff, volunteers, athletes and media who have already given their consent, not the general public. The system is based on NEC NeoFace Watch technology, and uses generalised matching face detection method, along with an artificial neural network model called the generalised learning vector quantisation algorithm, to search and select facial features for facial matching. The perturbation space method then coverts the two-dimensional images into three dimensions, allowing rotation of the candidates head. Further processing with illumination filters and adaptive regional blend matching method, minimises the impact of local changes such as hats etc. providing a better photograph match against a central database image. An IC chip embedded security lanyard pass, containing personal ID and authentication details will also be used. Data privacy concerns are discussed, especially due to the current use of NEC technology in criminal surveillance applications, with the Tokyo 2020 organisation responding with a promise to comply with local privacy law. Possibilities of using the technology to enhance Covid-19 security and aid in contact-tracing for the event is also discussed.

关键词： facial matching local privacy law data privacy artificial neural network model image matching management generalised matching face detection method contactless AI-driven facial-recognition system image recognition neural nets Spatial and pictorial databases Administration of other service industries visual databases Tokyo Olympics 2020 head rotation epidemics authentication details generalised learning vector quantisation algorithm IC chip embedded security lanyard pass personal ID vector quantisation illumination filters two-dimensional images queue management face recognition feature selection three dimensional images criminal surveillance applications central database image perturbation space method Data security Codes computer vision and image processing techniques Filtering methods in signal processing sport stereo image processing image filtering NEC NeoFace Watch technology facial feature selection contact-tracing adaptive regional blend matching method ID checks learning (artificial intelligence) Covid-19 security

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：