检索结果-内蒙古大学图书馆

1st International Conference on Neural Computing for Advanced Applications, NCAA 2020

作者： Zha, Zhong Yi Tang, Xue Song Wang, Bo Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Artificial Intelligence and Automation School Huazhong University of Science and Technology Wuhan430074 China College of Information and Science Donghua University Shanghai China

ISBN: (纸本)9789811576690

This paper presents an improved deep reinforcement learning (DRL) algorithm, namely Advanced Actor Critic (AAC), which is based on Actor Critic (AC) algorithm, to the video game Artificial intelligence (AI) training. The advantage distribution estimator, Normal Constraint (NC) function and exploration based on confidence are introduced to improve the AC algorithm, in order to achieve accurate value estimate, select continuous spatial action correctly, and explorate effectively. The aim is to improve the performance of conventional AC algorithm in a complex environment. A case study of video game StarCraft II mini-game AI training is employed. The results verify that the improved algorithm effectively improves the performance in terms of the convergence rate, maximum reward, average reward in every 100 episode, and time to reach a specific reward, etc. The analysis on how these modifications improve the performance is also given through interpretation of the feature layers in the mini-games. © Springer Nature Singapore Pte Ltd. 2020.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Learning from Noisy Labels with Coarse-to-Fine Sample Credibility Modeling 17th

Learning from Noisy Labels with Coarse-to-Fine Sample Cred...

引用

17th European Conference on Computer Vision, ECCV 2022

作者： Zhang, Boshen Li, Yuxi Tu, Yuanpeng Peng, Jinlong Wang, Yabiao Wu, Cunlin Xiao, Yang Zhao, Cairong YouTu Lab Shenzhen China Tongji University Shanghai China Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9783031250620

Training deep neural network (DNN) with noisy labels is practically challenging since inaccurate labels severely degrade the generalization ability of DNN. Previous efforts tend to handle part or full data in a unified denoising flow via identifying noisy data with a coarse small-loss criterion to mitigate the interference from noisy labels, ignoring the fact that the difficulties of noisy samples are different, thus a rigid and unified data selection pipeline cannot tackle this problem well. In this paper, we first propose a coarse-to-fine robust learning method called CREMA, to handle noisy data in a divide-and-conquer manner. In coarse-level, clean and noisy sets are firstly separated in terms of credibility in a statistical sense. Since it is practically impossible to categorize all noisy samples correctly, we further process them in a fine-grained manner via modeling the credibility of each sample. Specifically, for the clean set, we deliberately design a memory-based modulation scheme to dynamically adjust the contribution of each sample in terms of its historical credibility sequence during training, thus alleviating the effect from noisy samples incorrectly grouped into the clean set. Meanwhile, for samples categorized into the noisy set, a selective label update strategy is proposed to correct noisy labels while mitigating the problem of correction error. Extensive experiments are conducted on benchmarks of different modality, including image classification (CIFAR, Clothing1M etc.) and text recognition (IMDB), with either synthetic or natural semantic noises, demonstrating the superiority and generality of CREMA. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Electrode localization in 3D Ultrasound images using 3D phase grouping and Randomized Hough transform

Electrode localization in 3D Ultrasound images using 3D phas...

引用

International Conference on Genetic and Evolutionary Computing

作者： Qiu, Wu Ding, Mingyue Yuchi, Ming School of Life Science and Technology Image Processing and Intelligence Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9780769542812

A method to locate the axis of radio frequency ablation electrode(RFAE) in 3D Ultrasound(US) image is presented based on 3D phase-grouping in this paper. Firstly, all voxels in 3D US images are categorized into different groups which are called Line Support Region(LSR) according to the outer products of adjacent orientation vectors. And then, the RFAE axis is extracted with 3D Randomized Hough transform in the maximal LSR, instead of least squares fitting method;Finally, the endpoint of the RFAE axis is determined by searching along the axis with the probability distribution of voxels. The proposed method was tested in synthetic and 3D US agar phantom datas, the results are promising. © 2010 IEEE.

关键词： Hough transforms

来源：评论

学校读者我要写书评

暂无评论

Distributed optimization problem for second-order multi-agent networks with only position interaction 35

Distributed optimization problem for second-order multi-agen...

引用

第35届中国控制会议

作者： TRAN Ngoc-Tu LIU Xiao-Kang WANG Yan-Wu School of Automation Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control(Huazhong University of Science and Technology) Ministry of Education Hubei Provincial Collaborative Innovation Center for New Energy Microgrid China Three Gorges University

ISBN: (纸本)9781509009107

In this paper, distributed optimization problem is investigated under a second-order multi-agent network, in which each agent is described as the double integrator. The multi-agent network is introduced for solving a large scale optimization problem by the cooperation of coupled agents. Based on the interaction over the network, the optimal solution of the problem can be obtained. Since the existing distributed algorithms for second-order multi-agent network enforce each agent to transmit complete information(both state information and derivation information of the independent variable, i.e., corresponded position and velocity information of the agent), this paper is motivated to design the distributed algorithm with only using the position information of neighbors, which reduces the requirement on communication bandwidth. With the help of Lyapunov analysis and La Sallel's Invariance Principle, the optimal solution is derived and the optimization problem is solved via the second-order multi-agent network. Finally, a numerical example is presented to illustrate the theoretical result.

关键词： Second-order multi-agent networks Distributed optimization Consensus

来源：评论

学校读者我要写书评

暂无评论

Multi-Human Pose Estimation by Deep Learning-Based Sequential Approach for Human keypoint Position and Human Body Detection

引用

Journal of Shanghai Jiaotong University (Science) 2023年 1-11页

作者： Tahir, Rizwan Cai, Yunze Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China

Recent multimedia and computer vision research has focused on analyzing human behavior and activity using images. Skeleton estimation, known as pose estimation, has received a significant attention. For human pose estimation, deep learning approaches primarily emphasize on the keypoint features. Conversely, in the case of occluded or incomplete poses, the keypoint feature is insufficiently substantial, especially when there are multiple humans in a single frame. Other features, such as the body border and visibility conditions, can contribute to pose estimation in addition to the keypoint feature. Our model framework integrates multiple features, namely the human body mask features, which can serve as a constraint to keypoint location estimation, the body keypoint features, and the keypoint visibility via mask region-based convolutional neural network (Mask-RCNN). A sequential multi-feature learning setup is formed to share multi-features across the structure, whereas, in the Mask-RCNN, the only feature that could be shared through the system is the region of interest feature. By two-way up-scaling with the shared weight process to produce the mask, we have addressed the problems of improper segmentation, small intrusion, and object loss when Mask-RCNN is used, for instance, segmentation. Accuracy is indicated by the percentage of correct keypoint, and our model can identify 86.1% of the correct keypoints. © 2023, Shanghai Jiao Tong University.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

3D model retrieval using density-based silhouette descriptor

3D model retrieval using density-based silhouette descriptor

引用

2nd International Conference on Pattern Recognition Applications and Methods, ICPRAM 2013

作者： Tang, Qi Yang, Xin Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 China

ISBN: (纸本)9789898565419

In this paper we present a new content-based retrieval descriptor, density-based silhouette descriptor (DBS). It characterizes a 3D object with multivariate probability functions of its 2D silhouette features. The new descriptor is computationally efficient and induces a permutation property that guarantees invariance at the matching stage. Also, it is insensitive to small shape perturbations and mesh resolution. The retrieval performance on several 3D databases shows that the DBS provides state-of-art discrimination over a broad and heterogeneous set of shape categories.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

Integrating segmentation and classification accuracy for accuracy assessment in object-based image analysis

Integrating segmentation and classification accuracy for acc...

引用

2012 3rd IEEE/IET International Conference on Audio, Language and image processing, ICALIP 2012

作者： Li, Nan Huo, Hong Fang, Tao Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai China

ISBN: (纸本)9781467301718

An accuracy assessment method that integrates segmentation and classification accuracy is proposed to meet the requirements of object-based image analysis. Segmentation errors are measured by establishing the relationship between pixels and their corresponding segments according to the overlaps of segments and reference polygons. Then, two improved confusion matrices that take the segmentation errors into consideration are used: one for pixel-level classification results, and the other for object-level classification results. A final accuracy assessment combines the statistics of these two confusion matrices. The proposed method can be applied to segmentation scale selection in the hierarchical interpretation system. An experiment on a SPOT5 image demonstrates the effectiveness of this method for segmentation scale selection, which can guide the fusion of objects of different scales to obtain a higher accuracy. © 2012 IEEE.

关键词： image analysis

来源：评论

学校读者我要写书评

暂无评论

A new noise erosion operator for anisotropic diffusion

引用

Chinese Optics Letters 2004年第5期2卷 268-270页

作者：蔡超丁名跃周成平张天序 Institute for Pattern Recognition and Artificial Intelligence State Education Commission Key Lab for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074

A noise erosion operator based on partial differential equation (PDE) is introduced, which has an excellent ability of noise removal and edge preservation for two-dimensional (2D) gradient data. The operator is applied to estimate a new diffusion coefficient. Experimental results demonstrate that anisotropic diffusion based on this new erosion operator can efficiently reduce noise and sharpen object boundaries.

关键词： Anisotropic diffusion Diffusion

来源：评论

学校读者我要写书评

暂无评论

Uncalibrated Path Planning in the image Space for the Fixed Camera Configuration

引用

自动化学报 2013年第6期39卷 759-769页

作者： LIANG Xin-Wu HUANG Xin-Han WANG Min 1. Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing of Ministry of Education of China Shanghai 200240 China Department of Control Science and Engineering Huazhong University of Science and Technology Key Laboratory of Image Pro- cessing and Intelligent Control of Ministry of Education of China Wuhan 430074 China

基于图象的视觉 servoing 能被用来高效地控制机器人操纵者的运动。什么时候起始并且然而，需要的配置是远的是由许多研究人员，指出了如此的一条控制途径能由于它的本地性质受不了集中和稳定性问题。由指定足够的图象特征轨道在图象被... 详细信息

基于图象的视觉 servoing 能被用来高效地控制机器人操纵者的运动。什么时候起始并且然而，需要的配置是远的是由许多研究人员，指出了如此的一条控制途径能由于它的本地性质受不了集中和稳定性问题。由指定足够的图象特征轨道在图象被列在后面，我们能利用基于图象的视觉 servoing 的本地集中和稳定性避免这些问题。因此，路径在图象空间计划是在最近的年里的机器人学的一个活跃研究话题。然而，几乎所有为 camera-in-hand 配置的盒子相关结果被建立。在这篇论文，我们建议 uncalibrated 为改正照相机配置的盒子的视觉路径计划算法。这个算法在射影的空格直接计算图象特征的轨道以便他们与僵硬天体运动兼容。由把旋转和翻译的射影的代表分解成他们的各自的正规形式，我们能容易插入内推他们在射影的空间的路径。然后，在图象飞机的图象特征的轨道能经由射影的路径被产生。这样，特征点的知识组织并且照相机内在的参数没被要求。验证建议算法的可行性和表演，基于 puma560 机器人，操纵者在这被给的模拟结果糊。

关键词：路径规划算法摄像机内参数图像空间配置稳定性问题图片校准视觉伺服

来源：评论

学校读者我要写书评

暂无评论

A Fuzzy Optimal Sliding-Mode Guidance for Intercepting Problem

引用

IFAC Proceedings Volumes 2014年第3期47卷 3401-3406页

作者： Zhiwei Hou Mao Su Yongji Wang Lei Liu School of Automation Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan China

In this paper, a novel terminal guidance law is proposed to solve the problem of exo-atmospheric interception. It is designed based on the proportional navigation (PN) and the classical optimal sliding-mode guidance (OSMG). It overcomes the shortcoming of these two traditional guidance laws and inherits their merits. Particularly, in the scenario of exoatmospheric interception, when the maneuvering information of the targets are unavailable , the proposed guidance law has superior performance than the traditional guidance law. Briefly, to enhance the interceptive performance, we introduce the optimal control and sliding-mode control methods to the guidance law for maneuvering target's interception. On the other hand, the traditional proportional navigation law is introduced to intercept the target with a constant speed. After that, a fuzzy switching function is provided to harmonize both situations above, according to the real-time estimation of maneuver. To guarantee the stability of the law, a Lyapunov based condition is obtained. Finally, different from the two-dimensional simulation in most of the literatures of terminal guidance law researches, we illustrate our method in the nonlinear discrete three-dimensional simulation environment by the Runge-Kutta method. Compared with the pure OSMG and PN, the proposed law performs better.

关键词： Terminal guidance Optimal control Sliding-mode control Fuzzy control Lyapunov stability

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：