检索结果-内蒙古大学图书馆

2004 International Conference on Image processing, ICIP 2004

作者： Tianxu, Zhang Jin, Liu Institute for Pattern Recognition and Artifical Intelligence State Key Laboratory of Image Processing and Intelligent Control HuaZhong University of Science and Technology China Institute for Pattern Recognition and Artifical Intelligence HuaZhong University of Science and Technology China

ISBN: (纸本)0780385543

An important class of radiometric degradations we are faced with often in practice is image blurring. Special attention is paid to the recognition of the blurred image by moment invariant approach. Some important rules of complex moments for the blurred image are presented. Based on these rules, a useful subset of moment invariants is introduced, that are not affected by the blur, rotation, scale, and translation of the images. The experiments have shown that these invariants can be successfully used in recognition of the blurred image. ©2004 IEEE.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Prototype-guided Unsupervised Domain Adaptation for Semantic Segmentation

Prototype-guided Unsupervised Domain Adaptation for Semantic...

引用

2023 IEEE International Conference on Control, Electronics and Computer Technology, ICCECT 2023

作者： Xia, Shaoqi Huang, Hua Li, Qishen He, Yifan Nanchang Hangkong University Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition School of Information Engineering Jiangxi Nanchang China Nanchang Hangkong University School of Information Engineering Nanchang China Nanchang Hangkong University Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition School of Software Nanchang China

ISBN: (纸本)9798350399028

Semantic segmentation is one of the most important research directions in the field of computer vision, and has a wide range of applications for autonomous driving, medical imaging, intelligent security, etc. Unsupervised domain adaptation is the mainstream research topic in recent years, which can use a large number of labeled source samples to complete the segmentation task in target domain without labeled target samples. In this paper, we propose a prototype-guided unsupervised domain adaptation for semantic segmentation based on ProDA model. Due to lacking of labeled target samples and the prior probability, a prototype distance loss based on target domain is proposed to optimize the distribution of features by measuring the distance between features and the updated prototype and designing an adaptive threshold strategy. Meanwhile, a smoothing loss is proposed to alleviate the impact of source samples on our model and improve the prediction performance of the network. By conducting experiments on the GTA5 to Cityscapes scenarios, the results show that compared with the original model, the loss optimization improves mIoU by1.52. © 2023 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Motion Planning and Tracking Control Method Based on CoppeliaSim for UGV in Irregular Terrain 5

Motion Planning and Tracking Control Method Based on Coppeli...

引用

5th World Robot Conference Symposium on Advanced Robotics and Automation, WRC SARA 2023

作者： Huang, Jiale Chen, Zhihua Zhong, Yongbo Zeng, Wenrui Ji, Chuanmin Nanchang Hangkong University Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Moe Key Lab of Nondestructive Testing Technology Nanchang330063 China

ISBN: (纸本)9798350307320

Path planning and tracking algorithms are one of the cores of autonomous navigation technology for unmanned ground vehicle (UGV). In this paper, a local obstacle avoidance method based on event-triggered control is proposed to ensure that the UGV avoids obstacles in the tracking process. First, the path planning and tracking control problem of the UGV is modeled and formulated. Second, the improvement and logical correlation of the relevant algorithms are described in detail. Finally, ajoint simulation of MATLAB and V-rep is performed. The simulation results show that event-triggered control can largely improve the reliability of the UGV path planning and tracking process, and verify the effectiveness of the algorithm. © 2023 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Encapsulation strategies on 2D materials for field effect transistors and photodetectors

引用

Chinese Chemical Letters 2022年第5期33卷 2281-2290页

作者： Wenjuan Huang Yue Zhang Mengting Song Bugao Wang Huayi Hou Xiaozong Hu Xiangbai Chen Tianyou Zhai Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan Institute of TechnologyWuhan 430205China State Key Laboratory of Materials Processing and Die&Mould Technology School of Materials Science and EngineeringHuazhong University of Science and TechnologyWuhan 430074China Green Catalysis Center College of ChemistryZhengzhou UniversityZhengzhou 450001China

Two-dimensional(2D)layered materials provide a promising alternative solution for overcoming the scal-ing limits in conventional Si-based ***,practical applications of 2D materials are facing crucial bottlenecks,particularly that arising from the instability under ambient *** studies of degradation mechanisms and protecting strategies for overcoming the ambient instability of 2D materials have attracted extensive research attentions,both experimentally and *** review attempts to provide an overview on the recent progress of the encapsulation strategies for 2D *** en-capsulation strategies of mechanical transfer,polymer capping,atomic layer deposition,in-situ oxidation,and surface functionalization are systematically discussed for improving the ambient stability of 2D *** addition,the current advances in air-stable and high-performance 2D materials-based field effect transistors(FETs)and photodetectors assisted by the encapsulation strategies are ***,the future directions of encapsulation techniques of 2D materials for FETs and photodetectors applications are suggested.

关键词： Two-dimensional materials Encapsulation Degradation Stability Field effect transistors Photodetectors

来源：评论

学校读者我要写书评

暂无评论

Design of a High Performance Monolithic Current-Mode Boost DC-DC Converter

引用

电子学报(英文版) 2006年第4期15卷 599-603页

作者： YU Hua ZOU Xuecheng CHEN Chaoyang ZHANG Jing Department of Electronic Science and Technology Huazhong University of Science and Technology Wuhan 430074 China State Key Laboratory for Image Processing and Intelligence Control Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China

The work presented in this paper mainly focuses on designing a monolithic current-mode boost DC-DC converter with integrated 22V DMOS FET power switch and control circuits. The boost converter operating at fixed frequency of 1.6MHz has been fabricated with a 1.5μm Bipolar-CMOS-DMOS (BCD) process. The chip with features of wide input voltage range (2.7V to 14V), high efficiency over large load range (1mA to 500mA), low shutdown current, fast transient response and low power, was designed for mobile power management applications. Besides issues such as technology choice, power switch optimization and ramp compensation, the paper also copes with the monolithic switching noise in switching power IC circuits.

关键词： DC-DC转换器变速补偿电流控制脉冲调制

来源：评论

学校读者我要写书评

暂无评论

Adaptive tracking method for ground target of FLIR imaging

Adaptive tracking method for ground target of FLIR imaging

引用

MIPPR 2009 - Automatic Target recognition and Image Analysis: 6th International Symposium on Multispectral Image processing and pattern recognition

作者： Li, Yun Zhang, Tianxu Zuo, Zhengrong Wan, Meijun State Key Laboratory for Multispectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9780819478061

An adaptive tracking method for ground target in FLIR image including centric and eccentric tracking is presented in this paper. The eccentric tracking is adopted to assist ATR or manual target acquisition by stabilizing the light axis of the seeker. The tracking adaptability detection at the start of centric tracking avoids tracking bad locked point and decreases the shift, slide and jump in the subsequent tracking. Combination of periodic template-updating based on scale variance rate and interruptive template-updating based on supervision of tracking point enhances the adaptability of tracking template. Supervision, modification of current tracking point and the combination of direct and indirect tracking increase the stability of tracking system. The multi-scale and size-variable template is adopted to fit the variable target scale. The detection and adoption of occlusion mask increase the accuracy of the tracking system. The hardware system based on multi-DSP takes a real-time parallel processing. The trial results show that this method is efficient to reduce the possibility of shift, slide, and jump in ground target tracking comparing with the traditional correlation tracking method. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

A novel method concerning about image transition region extraction and segmentation

A novel method concerning about image transition region extr...

引用

2nd International Conference on Multimedia Technology, ICMT 2011

作者： Wang, Fang Zhang, Tianxu Deng, Jinpeng State Key Laboratory for Multispectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9781612847740

According to the feature that the gray distribution of the transition region (locating between the objects and the background) is more scattered than that of the regions of targets or background in an image, this paper proposes a novel method concerning about transition region extraction and segmentation, which is based on local variance of different areas of an image. The experiments indicate that the proposed approach can achieve better segmentation results than the local complexity method (one of the previous methods for extracting transition region).What's more, the novel approach outperforms the local complexity method about more complete and more accurate transition regions, less interference from backgrounds, more detail information of segmented targets, clearer and better segmented targets, easier calculation, and higher processing speed. © 2011 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A novel method of aerial image classification based on attention-based local descriptors

引用

Procedia Earth and Planetary Science 2009年第1期1卷 1133-1139页

作者： Xu, Sheng Fang, Tao Huo, Hong Li, Deren Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai 200240 China The State Key Laboratory for Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan 430072 China

This paper proposes a novel method for object-based classification in very high spatial resolution aerial image. It combines the saliency maps very closely to extract the conspicuous local regions for better description of object and classification. Unlike the previous work on detection of the local regions, a biologically motivated selective attention model is presented in this paper, since not all the local regions are important for describing the objects. In order to model the attention region, we propose a new attention-based local descriptor using the saliency map and relative local features to reflect the region of interest (ROI). The experimental results on the VHR aerial image dataset show that the proposed approach can obtain the state-of-the-art classifica-tion performance. © 2009.

关键词： Object recognition Image analysis Image classification Image segmentation Aerial images Bag of visual words Local descriptors Local feature Local region Novel methods Object based Region of interest Saliency map Selective attention model Very high spatial resolutions

来源：评论

学校读者我要写书评

暂无评论

A novel multiscale recursive recognition method for flying airplane objects

A novel multiscale recursive recognition method for flying a...

引用

2012 International Conference on Image processing, Computer Vision, and pattern recognition, IPCV 2012

作者： Zhang, Tianxu Zhou, Gang Yang, Ying Weng, Wenjie Sun, Xiangdong Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology State Key Laboratory for Multispectral Information Processing Technologies Wuhan Hubei China

ISBN: (纸本)9781601322258

In actual imaging process, the projection or silhouette of a three-dimensional moving object is variable in shape, scale and resolution to make its recognizability also unstable. A remedy is suggested on concepts defined in this paper as the dynamic feature space of the pattern. The necessity of developing feature models of multi-scale characteristic view for three-dimensional moving airplane objects and the rationality of using a usual constraint on airplane object moving characteristics are discussed. Thus, a novel multi-scale intelligent recursive recognizing (MUSIRR) method for image sequences is proposed. An intelligent recognizer composed of hybrid neural networks and logic decision-making modules is constructed with the BP neural networks and RBF networks as the building blocks of the recognizer. The rationality and effectiveness of the new method proposed in this paper have been verified by results of massive simulation and actual experiments on several types of airplane object.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Airborne target tracking algorithm against oppressive decoys in infrared imagery

Airborne target tracking algorithm against oppressive decoys...

引用

MIPPR 2009 - Automatic Target recognition and Image Analysis: 6th International Symposium on Multispectral Image processing and pattern recognition

作者： Sun, Xiechang Zhang, Tianxu State Key Laboratory for Multispectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9780819478061

This paper presents an approach for tracking airborne target against oppressive infrared decoys. Oppressive decoy lures infrared guided missile by its high infrared radiation. Traditional tracking algorithms have degraded stability even come to tracking failure when airborne target continuously throw out many decoys. The proposed approach first determines an adaptive tracking window. The center of the tracking window is set at a predicted target position which is computed based on uniform motion model. Different strategies are applied for determination of tracking window size according to target state. The image within tracking window is segmented and multi features of candidate targets are extracted. The most similar candidate target is associated to the tracking target by using a decision function, which calculates a weighted sum of normalized feature differences between two comparable targets. Integrated intensity ratio of association target and tracking target, and target centroid are examined to estimate target state in the presence of decoys. The tracking ability and robustness of proposed approach has been validated by processing available real-world and simulated infrared image sequences containing airborne targets and oppressive decoys. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Target 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：