检索结果-内蒙古大学图书馆

5th International Conference on Artificial Intelligence Technologies and Applications, ICAITA 2023

作者： Wang, Gang Lian, Mingchang Ding, Wei Chen, Songhang Chen, Hao Quanzhou Institute of Equipment Manufacturing Haixi Institutes Chinese Academy of Sciences Quanzhou362200 China College of Computer and Cyber Security Fujian Normal University Fujian Fuzhou350001 China Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China Fujian Fuzhou350108 China Fujian Provincial Key Laboratory of Intelligent Identification and Control of Complex Dynamic System Quanzhou362200 China

ISBN: (纸本)9781643684840

This paper is based on the research background of block relocation in the automated warehouse and proposes a solution utilizing AGV to relocate goods within the warehouse. Building upon the automated warehouse layout and block relocation process, we formulate a mathematical model to minimize the the number of AGV moving goods and the total travel distance of the AGV. To solve the model, we develop an enhanced genetic algorithm, which zones the block relocation process into multiple stages. Each stage integrates conventional heuristic algorithms to enhance the efficiency of the solution process. The improved genetic algorithm can effectively solve the problem, significantly enhancing the automation level of the warehouse. © 2024 The Authors.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

TDCNet: Transparent Objects Depth Completion with CNN-Transformer Dual-Branch Parallel Network

arXiv

引用

arXiv 2024年

作者： Fan, Xianghui Ye, Chao Deng, Anping Wu, Xiaotian Pan, Mengyang Yang, Hang Changchun Institute of Optics Fine Mechanics and Physics Chinese Academy of Sciences Changchun130033 China University of Chinese Academy of Sciences Beijing101408 China Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin150001 China National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Harbin Institute of Technology Harbin150001 China College of Physics Northeast Normal University Changchun130024 China

The sensing and manipulation of transparent objects present a critical challenge in industrial and laboratory robotics. Conventional sensors face challenges in obtaining the full depth of transparent objects due to the refraction and reflection of light on their surfaces and their lack of visible texture. Previous research has attempted to obtain complete depth maps of transparent objects from RGB and damaged depth maps (collected by depth sensor) using deep learning models. However, existing methods fail to fully utilize the original depth map, resulting in limited accuracy for deep completion. To solve this problem, we propose TDCNet, a novel dual-branch CNN-Transformer parallel network for transparent object depth completion. The proposed framework consists of two different branches: one extracts features from partial depth maps, while the other processes RGB-D images. Experimental results demonstrate that our model achieves state-of-the-art performance across multiple public datasets. Our code and the pre-trained model are publicly available at https://***/XianghuiFan/TDCNet. Copyright © 2024, The Authors. All rights reserved.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

An Improved Task Planning Method for Unmanned Swarms with Coupled Physical and Logical Constraints

An Improved Task Planning Method for Unmanned Swarms with Co...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Xiubin Chen Lei Zhang Fang Xu Weiran Yao School of Astronautics Harbin Institude of Technology Harbin China Wuhan 2nd Ship Design and Research Institute Wuhan China Marine Military Intelligence Innovation Institute CSSC Systems Engineering Research Institute Beijing China National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Beijing China

ISBN: (数字)9798350384185

ISBN: (纸本)9798350384192

Traditional task allocation methods for unmanned swarm systems ignore the effects of actual paths, resulting in estimation accuracy reduction. This paper formulates task planning problem by incorporating physical and logical constraints, and establishes an integrated framework of task allocation and path planning. Conflict-based search method is used to address path planning with physical constraints. A genetic algorithm is employed to solve multi-traveling salesman allocation problem. A bounded suboptimal optimization, a data dictionary, and an island model are introduced to accelerate the convergence speed of the genetic algorithm. The experiments verify that compared to the decoupled task planning methods, the proposed method improves task execution efficiency and remains adaptability to various complex spatial maps.

关键词： Dictionaries Search methods Estimation Path planning Data models Planning Resource management Optimization Genetic algorithms Convergence

来源：评论

学校读者我要写书评

暂无评论

WATNet: A Wavelet-Aware Lightweight Hybrid Model for Fast Low-Light Enhancement

WATNet: A Wavelet-Aware Lightweight Hybrid Model for Fast Lo...

引用

Artificial Intelligence technology (ACAIT), Asian Conference on

作者： Qiangqiang Wang Peiliang Huang Lei Li Longfei Han AHU-IAI AI Joint Laboratory Anhui University Hefei China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China School of Automation Northwestern Polytechnical University Xi’an China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China Beijing Technology and Business University Beijing China School of Information Science and Technology University of Science and Technology of China Hefei China

ISBN: (数字)9798350359145

ISBN: (纸本)9798350359152

Low-light enhancement task is an essential component of computer low-level visual tasks, which involves processing images captured under dim lighting conditions to make them appear as if they were taken under normal illumination. Currently, deep neural networks have become the mainstream approach for image processing. However, recent works have devoted considerable efforts to designing high-performance models, which often come with high computational complexity and inference time, making real-time processing unfeasible. We observed that some convolutional methods are due to the need for deep layers which results in a large number of parameters. Moreover, enhancing details and removing noise in low-light images remains an open challenge. In order to solve the above problems, we propose a lightweight baseline that combines CNN and sparse grid attention transformer blocks to enable the model to capture a global receptive field at an early stage. Specifically, we propose a High-Frequency Wavelet-aware Block(HFWB) that focuses on processing high-frequency information in the wavelet domain to refine details and suppress noise. With a processing time of only 10.6ms, the performance of our model outperforms that of the current state-of-the-art lightweight models on benchmark low-light datasets. Compared to state-of-the-art models in the LOL dataset, our model achieves a reduction in inference time of over 90% and requires only about 1% of the FLOPS.

关键词： Wavelet transforms Visualization Wavelet domain Noise Lighting Benchmark testing Transformers

来源：评论

学校读者我要写书评

暂无评论

Zero-shot learning based on semantic embedding for ship detection 3

Zero-shot learning based on semantic embedding for ship dete...

引用

3rd International Conference on Unmanned systems, ICUS 2020

作者： Zhang, Zihan Zhoa, Jiajia Liang, Xinkai Northwestern Polytechnical University School of Electronics and Information Shaanxi Xi'an China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Bejing China

ISBN: (纸本)9781728180250

Zero-shot detection (ZSD) is a hot topic, which can detect unseen object without training on it. This new approach rises several challenges, e.g., the imbalance between positive and negative data, ambiguity between background and unseen classes, and how to align visual feature and semantic concept. In this paper, we apply an end-to-end zero-shot network to fulfil ZSD, where polarity loss is utilized to train detection model. polarity loss puts more importance on difficult data to reduce class imbalance and can maximize the difference between positive and negative predictions. Then, we use a semantic embedding method that use word vectors in both classification and regression subnets to better align visual features and semantic features. Finally, we use MS-COCO dataset as seen classes to train detection model, then we transfer the model for our own to detect warship object. Our model performs good on unseen classes and test accuracy of using polarity loss is apparently higher than that of using focal loss. © 2020 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Robust composite control of telescopic wing morphing aircraft with control allocation

Robust composite control of telescopic wing morphing aircraf...

引用

Chinese Automation Congress (CAC)

作者： Zijian Wang Mingzhe Hou Mingrui Hao Center for Control Theory and Guidance Technology Harbin Institute of Technology Harbin China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9781665426480

In this paper, the problem of anti-disturbance, anti-saturation and fixed-time control for a class of telescopic wing morphing aircraft is studied. The telescopic wing morphing aircraft treats the variable wingspan as an extra control input to construct the dynamic model of the morphing-aided maneuver. According to the model characteristics, the controller design is divided into two loops: the speed loop and the attitude loop. Through a fixed-time continuous feedback control scheme, fixed time of the tracking reference trajectory is ensured. By combining the integral sliding mode control (ISMC) method with super-twisting control (STC), the uncertainties of aerodynamic coefficients and external disturbances are overcome. In addition, the anti-saturation problem of the aircraft actuator is solved by the initial solution correction method based on Null-space augmented solutions. The simulation result shows that the designed algorithm has great tracking performance, while the robustness and anti-saturation performance are guaranteed.

关键词： Attitude control Atmospheric modeling Heuristic algorithms Aerodynamics Robustness Trajectory Feedback control

来源：评论

学校读者我要写书评

暂无评论

Tail Classes Matter: Long-Tailed Object Detection Revisited

Tail Classes Matter: Long-Tailed Object Detection Revisited

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yinglu Zhang Chenbo Zhang Lu Zhang Tianying Liu Jihong Guan Xinkai Liang Jiajia Zhao Shuigeng Zhou Shanghai Key Lab of Intelligent Information Processing and School of Computer Science Fudan University China Department of Computer Science & Technology Tongji University China Science and Technology on Complex System Conroland InelligentAgent Cooperation Laboratory Beijing Electro-Mechanical Engineering Institute China

Real-world data ubiquitously exhibit long-tailed distribution, which sparks the increasing interest in long-tailed object detection (LTOD). However, existing methods neglect that a lack of diverse data in tail classes will cause underrepresented tail class features, making their efforts for balancing foreground classes tend to over-fit tail classes and be less effective. In this paper, we propose a multi-class co-attention generation network to increase data diversity of tail classes by generating augmented samples. To alleviate imbalance, we develop a distribution-aware up-sampling strategy, performing differential up-sampling for different classes and design a bi-directional regulation loss to adjust both positive and negative gradients. Moreover, we construct a new dataset LVIS-X with more rare classes based on existing LTOD benchmark dataset LVIS. Experiments on LVIS and LVIS-X demonstrate the superiority of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Phase Unwrapping Based on CFAR Detection for Multi-baseline InISAR

Phase Unwrapping Based on CFAR Detection for Multi-baseline ...

引用

IEEE International Conference on Radar

作者： Meng Ma Guangzhou Qu Shuaishuai Liu Yanjiao Yang Hucheng Pei Qingxi Chi Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China Beijing Electro-Mechanical Engineering Institute Beijing China

ISBN: (纸本)9781665468893

A phase unwrapping method based on constant false alarm rate (CF AR) detection is proposed for multi-baseline interferometric inverse synthetic aperture radar (InISAR). Aiming at the problem of ambiguity number estimation error under the condition of phase noise, Chinese remainder theorem (CRT) and cluster analysis are utilized to acquire the probability distribution of phase noise. By introducing CFAR detection, the novel method reduced the error probability of ambiguity number estimation. Through simulation, it is verified that the novel method can effectively suppress phase noise and obtain accurate phase unwrapping results.

关键词： Phase noise Phase measurement Radar measurements Radar Radar scattering Radar imaging Cathode ray tubes

来源：评论

学校读者我要写书评

暂无评论

Rapid and Accurate Regional Star-Map Simulated Method

Rapid and Accurate Regional Star-Map Simulated Method

引用

Computer, control and Robotics (ICCCR), International Conference on

作者： Jian Han Jiahui Tong Cheng Tang Beijing Electro-Mechanical Engineering Institute Beijing China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

The following topics are dealt with: mobile robots; feature extraction; learning (artificial intelligence); motion control; neural nets; path planning; optimisation; object detection; fault diagnosis; design engineering.

ISBN: (数字)9781728190358

ISBN: (纸本)9781728190365

关键词： Strips Gray-scale Reconstruction algorithms Position measurement Image reconstruction Robots Next generation networking

来源：评论

学校读者我要写书评

暂无评论

Motion-Guided Spatial Perception for Enhanced Multi-Object Tracking: A Hierarchical Framework

SSRN

引用

SSRN 2023年

作者： Zheng, Yujin Qi, Hang Li, Lei Li, Shan Huang, Yan He, Chu Wang, Dingwen School of Computer Science Wuhan University Hubei Wuhan430000 China The Beijing Electro-Mechanical Engineering Institute Beijing100074 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China Zmvision Technology Hubei Wuhan430000 China School of Electronic Information Wuhan University Hubei Wuhan430000 China

Multi-object tracking (MOT) aims to associate objects of interest across sequences, which has rapidly progressed with the development of object detection and optimal matching techniques. However, spatio-temporal modeling complex variations, such as camera motion and occlusion in crowded scenes, have been relatively underexplored in recent years. In this work, a temporal concern through motion-guided feature aggregation module is proposed to capture multi-frame variations for instances. Additionally,an occlusion-aware head and hierarchical spatial association are proposed to handle the challenges of occlusion through spatial perception. The above approach, namely MSPNet addresses the challenges posed by occlusion effectively, resulting in improved tracking performance. Evaluation on benchmark datasets shows that MSPNet achieves the state-of-the-art performance. Specifically, MSPNet achieves 75.4% MOTA, and 72.4% IDF1 on the test set of MOT16, 74.6% MOTA, and 71.9% IDF1 on MOT17, 75.9% MOTA, and 74.4% IDF1 on MOT20, respectively. © 2023, The Authors. All rights reserved.

关键词： Object detection

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：