检索结果-内蒙古大学图书馆

7th Asian Conference on Pattern Recognition, ACPR 2023

作者： Deng, Yao Xiang, Xiang Key Lab of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9783031476365

In the context of Domain Incremental Learning for Semantic Segmentation, catastrophic forgetting is a significant issue when a model learns new geographical domains. While replay-based approaches have been commonly used to mitigate this problem by allowing the model to review past knowledge, they require additional storage space for old data, which may not be feasible in real-world applications. To address this limitation, we propose a style replay method that leverages the characteristics of low-level representations in CNN to require only one style feature for each domain, leading to a significant reduction in storage overhead. By fusing the style features of past domains with the semantic features of current data, our method enables style transfer for new domain data, thereby improving the model’s generalization ability to the domain. Through extensive experimental evaluations on various autonomous driving datasets, we demonstrate the efficacy of our proposed method in addressing the challenges of continual semantic segmentation under both label and domain shift, outperforming the previous state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Semantic Segmentation

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

Selective Bokeh Effect Transformation

Selective Bokeh Effect Transformation

引用

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Peng, Juewen Pan, Zhiyu Liu, Chengxin Luo, Xianrui Sun, Huiqiang Shen, Liao Xian, Ke Cao, Zhiguo Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control China Nanyang Technological University S-Lab Singapore

ISBN: (纸本)9798350302493

Bokeh effect transformation is a novel task in computer vision and computational photography. It aims to convert bokeh effects from one camera lens to another. To this end, we introduce a new concept of blur ratio, which represents the ratio of the blur amount of a target image to that of a source image, and propose a novel framework SBTNet based on this concept. For cat-eye simulation and lens type transformation, a two-channel coordinate map and a two-channel one-hot map are added as extra inputs. The core of the framework is a sequence of parallel FeaNets, along with a feature selection and integration strategy, which aims to transform the blur amount with arbitrary blur ratio. The effectiveness of the proposed framework is demonstrated through extensive experiments, and our solution has achieved the top LPIPS metric in NTIRE 2023 Bokeh Effect Transformation Challenge. © 2023 IEEE.

关键词： Color photography

来源：评论

学校读者我要写书评

暂无评论

Region of interest image encryption method based on panoramic segmentation and a novel coupled chaotic map

Region of interest image encryption method based on panorami...

引用

2022 International Conference on Artificial Intelligence, Virtual Reality, and Visualization, AIVRV 2022

作者： Zhang, Hangming Hu, Hanping School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Information Processing and Intelligent Control Ministry of Education Wuhan430074 China

ISBN: (纸本)9781510662988

Social media is a platform for people to share their lives and interact with others. image sharing is an integral component. Privacy information will inevitably be compromised during the process of sharing whole photos. Sometimes, it is not even caused by the person who shares the image but the third party who forwards the image. In the majority of cases, we do not attempt to protect the entirety of the media;rather, we seek to protect the most crucial portion, whether it is the background or specific objects, which decreasing superfluous cryptography procedures. Unfortunately, current research on such field is extremely rare. In this research, we established a novel pixel-level image encryption technique relying on Panoptic FCN panoramic segmentation and chaos for client-intended images on social media sites. Our suggested technology is capable of automated picture encryption on either the whole images or user-selected areas, whether they are rectangular or irregular, which is suited for all region of interest (ROI) encryption. Relying on a novel coupled chaotic map, this universal new encryption method flattens the array of the image ROI into a series of pixels. The module of Panoptic FCN can be replaced by any other panoptic segmentation models which are stronger in performance. Statistical and cryptographic evaluations demonstrate that our technique preserves the high efficiency for practical applications. © 2023 SPIE. All rights reserved.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

RP-MSTC∗: Multi-Agent Coverage Path Planning Algorithm Emphasizing Local Area Updates

RP-MSTC∗: Multi-Agent Coverage Path Planning Algorithm Emph...

引用

2023 International Conference on Neuromorphic Computing, ICNC 2023

作者： Yang, Yong He, Dingxin Mao, Huantao Chen, Hong Wu, Hongtao Liu, Zhi-Wei School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent ControlMinistry of Education Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9798350316889

Compared to traditional area coverage algorithms, this paper proposes a re-plannable multi-agent coverage path planning algorithm to address issues such as low coverage rate of multiple agents in large-scale scenarios like warehouses and inability to cope with local environmental changes. Initially, the MSTC∗ algorithm is utilized to create the coverage path based on the available map information. To address scenarios like idle areas for material placement, the method introduces local area detection and path re-planning to enhance the coverage rate. This paper verifies the feasibility and effectiveness of the algorithm under different maps through simulation experiments. Compared with the coverage situation of other coverage path planning algorithms in environments with local area updates, the algorithm proposed in this paper has a higher coverage rate in this scenario. © 2023 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Learning Probabilistic Coordinate Fields for Robust Correspondences

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2023年第10期45卷 12004-12021页

作者： Zhao, Weiyue Lu, Hao Ye, Xinyi Cao, Zhiguo Li, Xin Huazhong University of Science and Technology The Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Wuhan430074 China West Virginia University The Lane Department of Computer Science and Electrical Engineering MorgantownWV26506-6109 United States

We introduce Probabilistic Coordinate Fields (PCFs), a novel geometric-invariant coordinate representation for image correspondence problems. In contrast to standard Cartesian coordinates, PCFs encode coordinates in correspondence-specific barycentric coordinate systems (BCS) with affine invariance. To know when and where to trust the encoded coordinates, we implement PCFs in a probabilistic network termed PCF-Net, which parameterizes the distribution of coordinate fields as Gaussian mixture models. By jointly optimizing coordinate fields and their confidence conditioned on dense flows, PCF-Net can work with various feature descriptors when quantifying the reliability of PCFs by confidence maps. An interesting observation of this work is that the learned confidence map converges to geometrically coherent and semantically consistent regions, which facilitates robust coordinate representation. By delivering the confident coordinates to keypoint/feature descriptors, we show that PCF-Net can be used as a plug-in to existing correspondence-dependent approaches. Extensive experiments on both indoor and outdoor datasets suggest that accurate geometric invariant coordinates help to achieve the state of the art in several correspondence problems, such as sparse feature matching, dense image registration, camera pose estimation, and consistency filtering. Further, the interpretable confidence map predicted by PCF-Net can also be leveraged to other novel applications from texture transfer to multi-homography classification. © 1979-2012 IEEE.

关键词： image registration

来源：评论

学校读者我要写书评

暂无评论

Bearing Remaining Useful Life Prediction Combining Trajectory Similarity and Relevance Vector Machine 41

Bearing Remaining Useful Life Prediction Combining Trajector...

引用

第41届中国控制会议

作者： Zhuyi Li Kesen Fan Cong Zhang Sihang Zhang Yiming Wan Key Laboratory of Image Processing and Intelligent Control Ministry of Education Chinaand School of Artificial Intelligence and AutomationHuazhong University of Science and Technology Beijing Institute of Control Engineering

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Bearing remaining useful life(RUL) prediction is critical for safe operation of rotating *** this paper,we propose a combined RUL prediction approach that leverages both trajectory similarity and relevance vector machine(RVM).The similarity based prediction relies on historical degradation trajectories that are highly similar to the online data,hence would perform poorly if all historical trajectories have low similarity with the online *** RVM based prediction relies solely on a regression model learned from the available online data,thus gives an inaccurate prediction when insufficient data are available in the early stage of degradation.A weighted sum of these above two predictions is proposed to address the limitation of each single prediction method,whose weights are determined by solving a non-negative least squares fitting *** further improve RUL prediction accuracy,we distinguish between fast and slow degradation modes,so that each mode uses a different set of historical degradation trajectories and kernel *** doing so,we predict RUL under the identified *** case study using the PHM2012 dataset demonstrates the effectiveness of the proposed RUL prediction approach.

关键词： Bearing degeneration remaining useful life prediction relevance vector machine trajectory similarity

来源：评论

学校读者我要写书评

暂无评论

Grain condition inspection: one improved grey wolf algorithm for nodes deployment optimization combining with path planning of multi-inspection robots

引用

Soft Computing 2024年第20期28卷 11971-11986页

作者： Zhu, Chunhua Zhang, Jilong Yang, Jing Key Laboratory of Grain Information Processing and Control Ministry of Education Henan University of Technology Henan Zhengzhou450001 China Henan Key Laboratory of Grain Photoelectric Detection and Control Henan University of Technology Henan Zhengzhou450001 China Henan Engineering Laboratory of Grain Condition Intelligent Detection and Application Henan University of Technology Henan Zhengzhou450001 China

Grain inspection robots can detect abnormal information such as grain insects and impurities on the grain surface by deploying detection nodes, it has a significant for the safety of grain storage. Generally, the grey wolf optimization (GWO) algorithm has significant advantages such as fewer control parameters and easy implementation, is one of the commonly employed approaches aiming to solve the problem in many fields. However, the traditional GWO has the shortcomings such as poor population initialization diversity, slow convergence speed and easily fall into local optimal values, it is difficult to solve deployment of inspection nodes problem in the grain surface. In this study, an improved Latin Hypercube grey wolf optimization (LH-GWO) is presented to overcome the disadvantages of the traditional GWO algorithm in solving inspection node deployment problem. The LH-GWO algorithm contains two novel mechanisms which are the Latin Hypercube Sampling population initialization and an improved nonlinear convergence factor. Moreover, a grain surface boundary inspection nodes deployment strategy is proposed to optimize the location of nodes at the boundary. For verifying the effectiveness of the proposed LH-GWO, comparing with six commonly used algorithms based on benchmark functions experiment and coverage rate experiment. The experimental results demonstrate the merits of LH-GWO in terms of convergence speed, optimization accuracy and area coverage. Finally, the optimal inspection nodes are divided into three inspection regional areas by k-means algorithm clustering, and in each inspection regional area, the optimal inspection path of each robot is determined by solving the travel salesman problem (TSP). © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

An Optimal control-Based Distributed Reinforcement Learning Framework for A Class of Non-Convex Objective Functionals of the Multi-Agent Network

引用

IEEE/CAA Journal of Automatica Sinica 2023年第11期10卷 2081-2093页

作者： Zhe Chen Ning Li Department of Automation Shanghai Jiao Tong UniversityShanghai 200240 Key Laboratory of System Control and Information Processing Ministry of Education of ChinaShanghai 200240 Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240China Department of Automation Tsinghua UniversityBeijing 100084China IEEE

This paper studies a novel distributed optimization problem that aims to minimize the sum of the non-convex objective functionals of the multi-agent network under privacy protection, which means that the local objective of each agent is unknown to others. The above problem involves complexity simultaneously in the time and space aspects. Yet existing works about distributed optimization mainly consider privacy protection in the space aspect where the decision variable is a vector with finite dimensions. In contrast, when the time aspect is considered in this paper, the decision variable is a continuous function concerning time. Hence, the minimization of the overall functional belongs to the calculus of variations. Traditional works usually aim to seek the optimal decision function. Due to privacy protection and non-convexity, the Euler-Lagrange equation of the proposed problem is a complicated partial differential ***, we seek the optimal decision derivative function rather than the decision function. This manner can be regarded as seeking the control input for an optimal control problem, for which we propose a centralized reinforcement learning(RL) framework. In the space aspect, we further present a distributed reinforcement learning framework to deal with the impact of privacy protection. Finally, rigorous theoretical analysis and simulation validate the effectiveness of our framework.

关键词： Distributed optimization multi-agent optimal control reinforcement learning(RL)

来源：评论

学校读者我要写书评

暂无评论

Online Multi-Object Tracking Under Moving Unmanned Aerial Vehicle Platform Based on Object Detection and Feature Extraction Network

引用

Journal of Shanghai Jiaotong university(Science) 2024年第3期29卷 388-399页

作者：刘增敏王申涛姚莉秀蔡云泽 Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai 200240China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240China Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong UniversityShanghai 200240China JD Business Growth Department Beijing 100176China Institute of Marine Equipment Shanghai Jiao Tong UniversityShanghai 200240China

In order to solve the problem of small object size and low detection accuracy under the unmanned aerial vehicle(UAV)platform,the object detection algorithm based on deep aggregation network and high-resolution fusion module is ***,a joint network of object detection and feature extraction is studied to construct a real-time multi-object tracking *** the problem of object association failure caused by UAV movement,image registration is applied to multi-object tracking and a camera motion discrimination model is proposed to improve the speed of the multi-object tracking *** simulation results show that the algorithm proposed in this study can improve the accuracy of multi-object tracking under the UAV platform,and effectively solve the problem of association failure caused by UAV movement.

关键词： moving unmanned aerial vehicle(UAV)platform small object feature extraction image registration multi-object tracking

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：