检索结果-内蒙古大学图书馆

Autonomous Obstacle Avoidance Scheme Using Monocular Vision Applied to Mobile Robots

Autonomous Obstacle Avoidance Scheme Using Monocular Vision ...

2020 International Conference on intelligent Control, Measurement and Signal Processing and intelligent Oil Field, ICMSP 2020

作者： Song, Yun Yun Yang, Sheng Yi Liu, Chao Wu, Qing Gui School of Data Science and Information Engineering Key Laboratory of Pattern Recognition and Intelligent Systems of Guizhou Province Guizhou Minzu University Guiyang China School of Mechatronics Engineering Guizhou Minzu University Guiyang China

Mobile robots cannot move in an unknown environment with static or slow-moving obstacles effectively. We present an enhanced obstacle avoidance strategy using monocular vision to solve this problem. First, we combine Canny and Otsu to extract the barrier feature and find the critical pixel position of obstacles by the monocular vision. Then the image depth estimation algorithm is used to estimate the gaps. With these parameters of barriers, an improved bug algorithm is proposed to avoid the obstacles autonomously. The experiments show that the proposed obstacles avoidance strategy can effectively make a small mobile robot avoid different kinds of obstacles. © Published under licence by IOP Publishing Ltd.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Task Adaptive Parameter Fine-Tuning Based on Contribution Measure for Transfer Learning

SSRN

引用

SSRN 2023年

作者： Feng, Le Feng, Fujian Yang, Yuan Tan, Mian Wang, Lin Guizhou Key Laboratory of Pattern Recognition and Intelligent System Guizhou Minzu University Guiyang550025 China

Fine-tuning is an important transfer learning technique that has achieved significant success in various tasks lacking training data, and requires only a small number of training epochs to achieve satisfactory results. However, with the increasing complexity of the model scale and structure, designing appropriate fine-tuning schemes for specific target tasks becomes increasingly difficult. In this paper, a contribution measure criterion is used to quantify the importance of the pre-trained model parameters to the target task, providing a basis for selecting fine-tuning parameters. In addition, we found that the fine-tuning ratio vary depending on the specific target task. Therefore, we proposed an adaptive fine-tuning ratio search strategy to search the appropriate fine-tuning ratio for the given target task. Based on the above strategy, we propose an adaptive fine-tuning algorithm based on parameter contribution to customize the fine-tuning scheme for the target task. The experimental results show that the proposed algorithm can effectively quantify the contribution of model parameters, and our algorithm can adaptively adjust the fine-tuning ratio for the target task. Furthermore, our algorithm achieved state-of-the-art performance on seven publicly available visual classification datasets widely used in transfer learning. © 2023, The Authors. All rights reserved.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Geometric Numerical Integral Method in Compact Lie Group

Geometric Numerical Integral Method in Compact Lie Group

引用

6th International Conference on intelligent Computing and Signal Processing (ICSP)

作者： Chao Liu Shengyi Yang Key Laboratory of Pattern Recognition and Intelligent System of Guizhou Province Guizhou Minzu University Gui Yang China

ISBN: (纸本)9781665447300

Three dimensions special orthogonal group SO (3) is widely used to describe the rotation kinematics of the rigid body without local coordinates, which can avoid rotation singularity and unwinding in traditional methods. Propagating the rotation kinematics in SO (3) with a specific geometric integration method is not only to obtained numerical results with improved qualitative behavior, but also provided more accurate long-time integration results. While many studies have focused on geometric integration algorithms to preserve the geometric structure, this work has the additional objective of studying result accuracy. Integral curves on SO (3) obtained using the third-order Crouch-Grossman Lie group method are compared with numerical results using the third-order RKMK algorithms, the exponential coordinates method, and the simple projection method. Results show that the use of the Crouch-Grossman Lie group method better preserves the geometric structure of SO (3) for the larger time steps considered. It is also found that the third-order Crouch-Grossman algorithm is more accurate than the RKMK except for the smallest time step used.

关键词： Heuristic algorithms Signal processing algorithms Kinematics Signal processing

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Person Re-identification Combining Feature Concatenation and Attention

Cross-Domain Person Re-identification Combining Feature Conc...

引用

作者： Feng Pan Lin Wang Yansha Zhang Jie Wang College of Data Science and Information Engineering Guizhou Minzu University Key Laboratory of Pattern Recognition and Intelligent System of Guizhou Province

To improve the insufficient generalization and poor cross-domain capability of the existing direct cross-dataset person re-identification methods,a cross-domain person re-identification method combining feature concatenation and attention(FCANet) is *** deep features of the network are concatenated to complement the feature information and obtain discriminatively feature,and the position attention module is introduced to enhance the data feature representation capability of the cross-domain task,using the joint training network of label smooth cross-entropy loss and triplet loss,model training in the source domain,and directly deploy to the target domain for *** verify the performance of the proposed method,it was experimented on three public datasets of Market1501,DukeMTMC-reID and MSMT17,which mAP and Rank1can reach 51.4%and 62.7% on *** results show that the proposed method has good performance in improving the generalization of cross-domain tasks,and the recognition accuracy outperforms the domain generalization algorithms of comparison.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Smoke Image Segmentation Based on Color Model

Smoke Image Segmentation Based on Color Model

引用

第11届创新与管理国际学术会议（ICIM2014）

作者： Deng Xing Yu Zhongming Wang Lin Li Jinlan School of Science Guizhou Minzu University Guizhou provincial key laboratory of pattern recognition and intelligent system Liupanshui Normal University

Smoke is the most significant feature in the process of fire,so it's possible to rely on smoke detection to detect *** the smoke image segmentation is the most difficult and also indispensable step in the analysis of smoke image *** order to improve its accuracy and effectively exclude the disturbances of non-smoke image,and lower the false alarm rate,it puts forward a kind of smoke image segmentation based on color *** uses K-means clustering in Lab color space and threshold segmentation in HSV color space,then merges the two ***,it uses the method of shen filter and regional mark to denoise,Experimental results on segmentation of smoke image show that the proposed method is able to segment smoke from the background.

关键词： Image segmentation K-means algorithm Color space LAB HSV

来源：评论

学校读者我要写书评

暂无评论

Video matting based on local-global features fusion 4

Video matting based on local-global features fusion

引用

4th International Conference on Machine Learning and Computer Application, ICMLCA 2023

作者： Dong, Niuniu Liang, Yihui Zou, Kun Li, Wensheng Feng, Fujian School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Computer Science Zhongshan Institute University of Electronic Science and Technology of China Zhongshan China Guizhou Key Laboratory of Pattern Recognition and Intelligent System Guizhou Minzu University Guiyang China

ISBN: (数字)9781510680265

ISBN: (纸本)9781510680258

Video matting aims at accurately separating foreground from videos. Recent video matting researches pursue to eliminate auxiliary inputs. However, due to the limited ability of extracting global correlation features, these methods suffer from performance degradation when dealing with complex scenes or natural background videos. To address this challenge, we propose a video matting method called Video Matting Based on Local-Global Features Fusion (VMBLGFF) which can extract both comprehensive global correlation features and local subtle features. VMBLGFF contains two closely connected networks: a transformer network that utilizes window and global attention mechanisms to obtain global correlation features within and cross windows, and a fusion network that integrates local subtle features into the global correlation features to supplement the local detail information which may be overlooked by the attention mechanisms. VMBLGFF alleviates the issue of limiting global correlation features and has been benchmarked on both synthetic and real datasets, and the results demonstrate that VMBLGFF improves the quality of video matting and exhibits good generalization performance. © 2024 SPIE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

License Plate Character recognition Based on Gaussian-Hermite Moments

License Plate Character Recognition Based on Gaussian-Hermit...

引用

International Workshop on Education Technology and Computer Science, ETCS

作者： Xiaojuan Ma Renlong Pan Lin Wang Guizhou Key Laboratory of Pattern Recognition & Intelligent Control Guizhou University for Nationalities Guiyang China

ISBN: (纸本)9781424463886;9780769539874

Character recognition plays an important role in the automatic license plate recognition (ALPR) system. In this paper, we propose a new method to recognize the license plates characters by using 2D Gaussian-Hermite moments (GHMs) of different orders with 231 GHMs features as the input vector of BP neural network. The system worked under variable illumination, variable size of plate and dynamic backgrounds. The experimental results demonstrate robust and efficient of our method.

关键词： Licenses Character recognition Gaussian processes Neural networks pattern recognition Image segmentation intelligent transportation systems Robustness Image recognition pattern analysis

来源：评论

学校读者我要写书评

暂无评论

Segmentation-based Euler number with multi-levels for image feature description

引用

Procedia Computer Science 2017年 111卷 245-251页

作者： Qian Zhang Lin Wang Jiang-Hao Yu Minggui Zhang Academic Affairs Office Guizhou Minzu University GuiYang 550025 China Pattern Recognition & Intelligent System Key Laboratory of Gui Zhou Province GuiYang 550025 China

This paper proposes a new and efficient image feature descriptor using Euler Number with the help of segmentation according to given number of levelsest. The proposed Segmentation-based Euler Number for image description algorithm (SENA) works as the following steps. First, transforming the image into gray image if the image is color image; then, dividing the gray image into different sets using the given number of levelsets; next, decomposing the gray image into binary images with multi-thresh using the otsu algorithm; following, computing the Euler Number of each binary image; finally, combining the Euler Numbers, mean and variance to form the feature vector for an input image. The proposed SENA was employed to the image classification on three public available dataset (Stanford Dogs Dataset, 17 flower dataset, and Caltech 256 dataset). We compute SENA with LBP and Gabor on the Stanford Dogs Dataset, the detail classification results on 17 flower dataset is given as confusion matrix, and the result of SENA on the Caltech 256 dataset is compared with those of the recently reported. The experiments demonstrate a competitive performance of SENA for classification task.

关键词： Number image feature image segmentation image classification LevelSet

来源：评论

学校读者我要写书评

暂无评论

An Image Segmentation Algorithm Based on Gray Bit Plane for Flame

An Image Segmentation Algorithm Based on Gray Bit Plane for ...

引用

2016 4th International Conference on Electrical&Electronics Engineering and Computer Science(ICEEECS 2016)

作者： Xing Deng Jinlan Li Fujian Feng Lin Wang Zhongming Yu School of physics and electronic science Guizhou Normal University Guizhou provincial key laboratory of pattern recognition and intelligent system Liupanshui Normal University

ISBN: (纸本)9781510835429

Flame region judgment is an important part of fire detection system;meanwhile the flame of intelligent monitoring system also has important practical significance to national fire control safety. Therefore, this article puts forward the flame image segmentation method based on gray level bit plane. Firstly, by studying the distribution of flame image in OHTA color space, we found that it can accurately segment the flame area by using the method of the gray level bit plane for component image in OHTA color space. The experiments results show that the algorithm in different scenarios for segmenting flame has a good effectiveness and robustness.

关键词： Fire detect OHTA color space gray bit plane image segmentation

来源：评论

学校读者我要写书评

暂无评论

An Image Matching Evolutionary Algorithm Based on Hu Invariant Moments

An Image Matching Evolutionary Algorithm Based on Hu Invaria...

引用

2011 International Conference on Image Analysis and Signal Processing(2011第三届图像分析与信号处理国际会议 IASP 2011)

作者： Ruliang Zhang Lin Wang Key Laboratory of Pattern Recognition and Intelligent Control Guizhou University for NationalitiesGuiyang China

ISBN: (纸本)9781612848792

This paper presents an image matching evolutionary algorithm (called IMEA algorithm) based on Hu invariant moments. First, the population is initialized. A group of searched subgraphs is constructed. Second, the fitness function based on Hu invariant moments is designed. The seven Hu invariant moments of the template image and the searched subgraph are calculated. The Euclidean distance of Hu invariant moments is used to measure similarity between the template image and the searched subgraph. The template image and the searched subgraph are matched if these Euclidean distances are less than the set threshold. Finally, a new searched subgraph is constructed by means of a new evolutionary strategy. The new searched subgraph replaces the searched subgraph whose value of the fitness function is maximum. Experimental results demonstrate the great robustness and efficiency of the IMEA algorithm.

关键词： Hu invariant moments evolutionary algorithm euclidean distance image matching

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：