检索结果-内蒙古大学图书馆

16th European Conference on Computer Vision, ECCV 2020

作者： Bin, Yanrui Cao, Xuan Chen, Xinya Ge, Yanhao Tai, Ying Wang, Chengjie Li, Jilin Huang, Feiyue Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Tencent Youtu Lab Shanghai China

ISBN: (纸本)9783030585280

Human pose estimation is the task of localizing body keypoints from still images. The state-of-the-art methods suffer from insufficient examples of challenging cases such as symmetric appearance, heavy occlusion and nearby person. To enlarge the amounts of challenging cases, previous methods augmented images by cropping and pasting image patches with weak semantics, which leads to unrealistic appearance and limited diversity. We instead propose Semantic Data Augmentation (SDA), a method that augments images by pasting segmented body parts with various semantic granularity. Furthermore, we propose Adversarial Semantic Data Augmentation (ASDA), which exploits a generative network to dynamically predict tailored pasting configuration. Given off-the-shelf pose estimation network as discriminator, the generator seeks the most confusing transformation to increase the loss of the discriminator while the discriminator takes the generated sample as input and learns from it. The whole pipeline is optimized in an adversarial manner. State-of-the-art results are achieved on challenging benchmarks. The code has been publicly available at https://***/Binyr/ASDA. © 2020, Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Time Series Anomaly Detection under Data Contamination 12

Unsupervised Time Series Anomaly Detection under Data Contam...

引用

12th International Conference on information Technology in Medicine and Education, ITME 2022

作者： Lin, Xiaohui Li, Zuoyong Huang, Xunhua Chen, Xinwei Fan, Haoyi Fuzhou University College of Computer and Data Science Fuzhou350108 China Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Fuzhou350121 China Harbin University of Science and Technology School of Computer Science and Technology Harbin150080 China Minjiang University Fujian Engineering and Research Center of New Chinese Lacquer Materials Fuzhou350121 China Zhengzhou University School of Computer and Artificial Intelligence Zhengzhou450001 China

ISBN: (纸本)9798350310153

Unsupervised learning utilizes unlabeled data to alleviate the reliance on large amounts of labeled data, and it has made great progress in time series anomaly detection. However, there are still some thorny issues unsolved, especially the incapability to maintain the robustness of the model when the time series dataset is contaminated. In this work, we propose an unsupervised time series anomaly detection method on data contamination, named distribution alignment autoencoder (DAAE), in which a temporal sliding reward function combines the adversarial distribution alignment to mine the contaminated data. Specifically, the dimensionality reduction and reconstruction of the time series are implemented by an autoencoder. Next, using two discriminators, the latent features obtained by dimensionality reduction are mapped to the Gaussian distribution, and the high-confidence normal time series are generated by sampling noise from the Gaussian distribution. Then, we compute the mean square error between high-confidence normal samples and the training data. Finally, we feed the error values to the temporal sliding reward function to mine the contaminated training samples. Experimental results compared with baselines on public datasets demonstrate the effectiveness of DAAE. © 2022 IEEE.

关键词： Contamination

来源：评论

学校读者我要写书评

暂无评论

Vehicle detection based on point cloud intensity and distance clustering 5

Vehicle detection based on point cloud intensity and distanc...

引用

2020 5th International Seminar on Computer Technology, Mechanical and Electrical Engineering, ISCME 2020

作者： Wang, Zhao Wang, Xing Fang, Bin Yu, Kun Ma, Jie School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China National Key Laboratory of Multispectral Information Processing Technology Huazhong University of Science and Technology Wuhan430074 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

In the intelligent transportation system, vehicle detection is one of the essential technologies in obstacle avoidance and navigation, however the existing vehicle detection methods cannot meet the actual needs. This paper presents a vehicle detection method combines the intensity and distance information of point cloud, which improves the segmentation performance of nearby objects. Specifically, the data of point cloud collected by lidar is preprocessed first. Then the processed point cloud is clustered by combining its coordinate and intensity information. Finally, the clustered suspected targets are fed to the random forest classifier. Our method can efficiently detect and classify targets in large-scale disordered 3D point cloud with high accuracy. In the real-scanned Livox Mid-40 Lidar dataset, our proposed method improves the detection accuracy by 31% compared with the traditional Euclidean clustering. © Published under licence by IOP Publishing Ltd.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

Robust optimization-based fusion of GNSS and Visual-Inertial-Wheel Odometry

Robust optimization-based fusion of GNSS and Visual-Inertial...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Jake Jie Hou Xinrui Wu Jiwei Shan Dun Li Hesheng Wang Department of Automation Shanghai Jiao Tong University China Shanghai Karlang Industrial Nantong Intelligent Technology Co. Ltd China Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781665481106

SLAM is significant to autonomous mobile robots. In order to realize drift-free state estimation and provide accurate localization results for the subsequent navigation, we develop an optimization-based framework consisting of a high-frequency Inertial-Wheel Odometry(IWO), Visual-Inertial-Wheel Odometry(VIWO) and a global fusion module. To fuse the local state with the position provided by GNSS, we perform ternary edge in factor graph optimization to estimate the transformation between the local frame and ENU coordinate. Thanks to the tightly-coupled VIWO, the localization property of the odometry presents more robustness, and improve the accuracy of global fusion. A noise repropagation strategy is introduced to ensure the consistency of the IMU and wheel odometer. We evaluate the proposed system on public datasets and test it in real-world scenario. The experimental results show that our system achieves accurate pose estimation in outdoor environments.

关键词： Location awareness Global navigation satellite system Simultaneous localization and mapping Robot kinematics Wheels Robustness Sensors

来源：评论

学校读者我要写书评

暂无评论

Densely activated self-attention for semantic segmentation

引用

Pattern Recognition 2025年

作者： Liwen Xiao Wenze Liu Zhicheng Wang Yiran Wang Zhiyu Pan Hao Lu Zhiguo Cao Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan 430074 China

In semantic segmentation, pixels often share the same mask labels across a vast region. However, in recent prevalent transformer-based models, predictions frequently suffer from incompleteness or discontinuities. The dilemma is caused by sparse activation of vanilla self-attention during feature extraction. During the vanilla self-attention, each query over-focuses on a small number of relevant keys but neglects numerous keys sharing the same category with it, restricting the capture of universal feature representation for its category. Such sparsely activated self-attention will further cause unignorable feature differences among tokens sharing the same class in feature maps, introducing noise on final predictions. To reduce such differences, we propose the Densely Activated self-attention Module (DAM), a novel pluggable module designed to generate densely activated self-attention. Inserted after the encoder, it encourages each query to attend to a broader range of keys, obtaining more consistent features. Experimental results on three widely used benchmarks with six different baselines demonstrate that DAM consistently improves performance with a negligible increase in parameters and FLOPs. Our work provides a new perspective on the behavior of self-attention in semantic segmentation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TSW-FD: A novel temporal and spatial domain weight analysis of feature difference for micro-expression spotting

TSW-FD: A novel temporal and spatial domain weight analysis ...

引用

2020 International Symposium on Automation, information and Computing, ISAIC 2020

作者： Zhang, Zhihao Mo, Fan Zhao, Ke Chen, Tong Fu, Xiaolan State Key Laboratory of Brain and Cognitive Science Institute of Psychology Chinese Academy of Sciences Beijing100101 China Department of Psychology University of Chinese Academy of Sciences Beijing100049 China Chongqing Key Laboratory of Non-linear Circuit and Intelligent Information Processing Southwest University Chongqing400715 China Chongqing Key Laboratory of Artificial Intelligence and Service Robot Control Technology Chongqing400715 China

The micro-expression spotting has recently attracted increasing attention from psychology and computer vision community, since embraced in the second facial Micro-Expression Grand Challenge (MEGC 2019). Different from the original feature difference (FD) analysis, in this paper, we proposed a novel temporal and spatial domain weight analysis of feature difference (TSW-FD) to achieve micro-expression spotting. The experimental results showed that TSW-FD improved 17.86% and 24.21% in F1-Score comparing to the FD in CASME Ⅱ and SMIC-E-HS. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Finite difference method

来源：评论

学校读者我要写书评

暂无评论

Sensor-based Multi-agent Coverage control with Spatial Separation in Unstructured Environments

arXiv

引用

arXiv 2024年

作者： Wang, Xinyi Xu, Jiwen Gao, Chuanxiang Chen, Yizhou Zhang, Jihan Wang, Chenggang Ding, Yulong Chen, Ben M. Department of Mechanical and Automation Engineering The Chinese University of Hong Kong N.T. Shatin Hong Kong Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University Shanghai200240 China Department of Control Science and Engineering Tongji University Shanghai China Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education China

Multi-robot systems have increasingly become instrumental in tackling coverage problems. However, the challenge of optimizing task efficiency without compromising task success still persists, particularly in expansive, unstructured scenarios with dense obstacles. This paper presents an innovative, decentralized Voronoi-based coverage control approach to reactively navigate these complexities while guaranteeing safety. This approach leverages the active sensing capabilities of multi-robot systems to supplement GIS (Geographic information System), offering a more comprehensive and real-time understanding of environments like post-disaster. Based on point cloud data, which is inherently non-convex and unstructured, this method efficiently generates collision-free Voronoi regions using only local sensing information through spatial decomposition and spherical mirroring techniques. Then, deadlock-aware guided map integrated with a gradient-optimized, centroid Voronoi-based coverage control policy, is constructed to improve efficiency by avoiding exhaustive searches and local sensing pitfalls. The effectiveness of our algorithm has been validated through extensive numerical simulations in high-fidelity environments, demonstrating significant improvements in task success rate, coverage ratio, and task execution time compared with others. Copyright © 2024, The Authors. All rights reserved.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Bionic Geomagnetic Navigation for Autonomous Underwater Vehicle with Temporal Attention-based Data-Driven Dead Reckoning

TechRxiv

引用

TechRxiv 2023年

作者： Yang, Songnan Zhang, Xiaohui Liu, Ding Bai, Wenqi Liu, Fan The School of Automation and Information Engineering Xi’an University of Technology Shaanxi 710048 China The Institute of Advanced Navigation and Electromagnetics Xi’an University of Technology Shaanxi 710048 China The State Key Laboratory of Eco-Hydraulics in the Northwest Arid Region of China Xi’an University of Technology Shaanxi 710048 China The Shaanxi Key Laboratory of Complex System Control with the Intelligent Information Processing Xi’an University of Technology Shaanxi 710048 China

Numerous studies have demonstrated that numerous animal species are capable of goal-directed navigation using environmental information for dead reckoning. The stable magnetic field of the earth provides important information for the migration of animals over long distances. Inspired by the goal-directed navigation of animals, a novel Geomagnetic Navigation with Temporal Attention-based Data-Driven Dead Reckoning (Attention-DR) method for Autonomous Underwater Vehicles (AUV) is presented in this article, which only utilizes the inclination angle (I) and the declination angle (D) of the Geomagnetic Field (GF) for underwater navigation without any prior knowledge of the geographical location or geographic map. This article proposes a Temporal Attention-based Long Short-Term Memory (TA-LSTM) neural network by combining history, GF information, and location in time series to achieve the optimization heading angle of underwater dead reckoning. Due to its ability to adjust the utilization weights of local and global temporal information in the path, TA-LSTM possesses the capability to continually update neural network model parameters through a data-driven process during the navigation process. This enables the Attention-DR to achieve efficient navigation in regions without prior magnetic maps and overcome navigation failures caused by magnetic field anomalies. The simulation outcomes confirm the efficiency, precision, and practicability of the proposed algorithm. © 2023, CC BY.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Dual-Band HRRP Fusion Recognition via Wavelet Decomposition Embedded Autoencoder

Dual-Band HRRP Fusion Recognition via Wavelet Decomposition ...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Weijia Wang Zhuchang Qi Lue Wang Wei Yang Liang Zhang Yanhua Wang Radar Technology Research Institute Beijing Institute of Technology Beijing China Xi'an Institute of Modern Control Technology Xi'an China Zhengzhou Academy of Intelligent Technology Beijing Institute of Technology Zhengzhou China Beijing Key Laboratory of Embedded Real-Time Information: Processing Technology Beijing China Chongqing Innovation Center Beijing Institute of Technology China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

High-resolution range profile (HRRP) is a crucial technique for radar target recognition. Due to the coupling of azimuthal scattering information and aspect sensitivity, fine target recognition using HRRP remains challenging. One way to mitigate HRRP aspect sensitivity is through enhancing the dimensionality of radar information acquisition. Therefore, this paper proposes a Dual-Band HRRP Fusion Recognition Model via Wavelet Decomposition Embedded Autoencoder (DF-WD-AENet). The method we proposed mainly comprises two modules. Firstly, the autoencoder model based on wavelet decomposition (WD-AEM) achieves constraint on feature information, making it better suited for dual-band fusion. Next is the dual-band information fusion module (DFM), in which we achieved the interaction and fusion of feature information through convolutional block attention module (CBAM) and omni-dimensional dynamic convolution (ODConv), and used a fusion loss function to train the model. Experiment shows that the recognition rate of our method is 7.73% higher than that of single-band, proving the effectiveness of the proposed method.

关键词： Sensitivity Target recognition Convolution Fuses Autoencoders Dual band Scattering Radar Radar signal processing Signal resolution

来源：评论

学校读者我要写书评

暂无评论

Autonomous inverse encoding guides 4D nanoprinting for highly programmable shape morphing

引用

International Journal of Extreme Manufacturing 2025年第3期 472-488页

作者： Shuaiqi Ren Zhiang Zhang Ruokun He Jiahao Fan Guangming Wang Hesheng Wang Bing Han Yong-Lai Zhang Zhuo-Chen Ma Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Department of Engineering University of Cambridge Institute of Medical Robotics School of Biomedical Engineering Shanghai Jiao Tong University State Key Laboratory of Integrated Optoelectronics College of Electronic Science and EngineeringJilin University

Highly programmable shape morphing of 4D-printed micro/nanostructures is urgently desired for applications in robotics and intelligent systems. However, due to the lack of autonomous holistic strategies throughout the target shape input, optimal material distribution generation,and fabrication program output, 4D nanoprinting that permits arbitrary shape morphing remains a challenging task for manual design. In this study, we report an autonomous inverse encoding strategy to decipher the genetic code for material property distributions that can guide the encoded modeling toward arbitrarily pre-programmed 4D shape morphing. By tuning the laser power of each voxel at the nanoscale, the genetic code can be spatially programmed and controllable shape morphing can be realized through the inverse encoding process. Using this strategy, the 4D-printed structures can be designed and accurately shift to the target morphing of arbitrarily hand-drawn lines under stimulation. Furthermore, as a proof-of-concept, a flexible fiber micromanipulator that can approach the target region through pre-programmed shape morphing is autonomously inversely encoded according to the localized spatial *** strategy may contribute to the modeling and arbitrary shape morphing of micro/nanostructures fabricated via 4D nanoprinting, leading to cutting-edge applications in microfluidics, micro-robotics, minimally invasive robotic surgery, and tissue engineering.

关键词：

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：