检索结果-内蒙古大学图书馆

Multiobjective optimization using an immunodominance and clonal selection inspired algorithm

Science in China(Series F) 2008年第8期51卷 1064-1082页

作者： GONG MaoGuo JIAO LiCheng MA WenPing DU HaiFeng Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information Processing Xidian University Xi'an 710071 China School of Public and Administration Xi'an Jiaotong University Xi'an 710049 China

Based on the mechanisms of immunodominance and clonal selection theory, we propose a new multiobjective optimization algorithm, immune dominance clonal multiobjective algorithm （IDCMA）. IDCMA is unique in that its fitness values of current dominated individuals are assigned as the values of a custom distance measure, termed as Ab-Ab affinity, between the dominated individuals and one of the nondominated individuals found so far. According to the values of Ab-Ab affinity, all dominated individuals （antibodies） are divided into two kinds, subdominant antibodies and cryptic antibodies. Moreover, local search only applies to the subdominant antibodies, while the cryptic antibodies are redundant and have no function during local search, but they can become subdominant （active） antibodies during the subsequent evolution. Furthermore, a new immune operation, clonal proliferation is provided to enhance local search. Using the clonal proliferation operation, IDCMA reproduces individuals and selects their improved maturated progenies after local search, so single individuals can exploit their surrounding space effectively and the newcomers yield a broader exploration of the search space. The performance comparison of IDCMA with MISA, NSGA-Ⅱ, SPEA, PAES, NSGA, VEGA, NPGA, and HLGA in solving six well-known multiobjective function optimization problems and nine multiobjective 0/1 knapsack problems shows that IDCMA has a good performance in converging to approximate Pareto-optimal fronts with a good distribution.

关键词： multiobjective optimization immunodominance clonal selection artificial immune systems evolutionaryalgorithms

来源：评论

学校读者我要写书评

暂无评论

DNN-based joint classification for multi-source image change detection 11th

DNN-based joint classification for multi-source image change...

引用

11th International Conference on Bio-inspired Computing – Theories and Applications, BIC-TA 2016

作者： Ma, Wenping Li, Zhizhou Zhang, Puzhao Hu, Tianyu Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian University Xi’anShaanxi Province710071 China

ISBN: (纸本)9789811036101

In this paper, we propose a novel joint classification framework for multi-source image change detection, the multi-source imagepair is generated by different sensors, such as optical sensor and synthetic aperture radar, respectively. This framework is established for feature learning, which is based on deep neural networks. Firstly, in order to segment the optical image, deep neural networks are essential to extract deep features for clustering segmentation. Then the stacked denoising autoencoders is trained to learn capability of classification via choosing part of reliable segmentation results of optical image as labels. Next, the other image of the image-pair is entered in the trained stacked denoising autoencoders to classification automatically. Afterwards, two images passed joint classification are obtained. Finally, the difference image is produced by comparing the two images passed joint classification. Experimental results illustrate that the method can be applied to multi-source image and outperforms the state-of-the-art methods. © Springer Nature Singapore Pte Ltd. 2016.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Block Pruning and Collaborative Distillation for image Classification of Remote Sensing

Block Pruning and Collaborative Distillation for Image Class...

引用

2024 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2024

作者： Wang, Xiaokai Wang, Rongfang Jiao, Changzhe Niu, Yi Mu, Caihong Xidian Univerisity The Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xi'an China

ISBN: (纸本)9798350360325

Convolutional Neural Networks (CNNs) have achieved remarkable performance in remote sensing image classification tasks. To address the issue of high model complexity, we propose a block-level pruning strategy based on the semantic similarity analysis that no fine-tuning is required during the pruning process. By employing this strategy, we effectively reduce the complexity of the model. Furthermore, to restore the overall performance of the pruned model, we propose a teacher-student collaborative distillation strategy that enables knowledge transfer through the collaboration of the original model and the dropped-blocks model to promote the performance of the compact pruned model. Experimental results demonstrate that our pruning and distillation strategies outperform other approaches, thereby achieving favorable performance while reducing model complexity. © 2024 IEEE.

关键词： blocks pruning image classification knowledge distillation light CNN remote sensing

来源：评论

学校读者我要写书评

暂无评论

SAR image despeckling based on edge detection and nonsubsampled second generation bandelets

引用

Journal of Systems Engineering and Electronics 2009年第3期20卷 519-526页

作者： Zhang Wenge~(1,2),Liu Fang~(1,2),Jiao Licheng~(2,3)& Gao Xinbo~(2,3) 1.School of Computer Science and Technology,Xidian Univ.,Xi’an 710071,P.R.China 2.key Lab.of intelligent perception and image understanding of Ministry of Education of China,Xi’an 710071,P.R.China 3.Inst,of intelligent Information Processing,Xidian Univ.,Xi’an 710071,P.R.China School of Computer Science and Technology Xidian Univ. Xi'an 710071 P. R. China Key Lab. of Intelligent Perception and Image Understanding of Ministry of Education of China Xi'an 710071 P. R. China Key Lab. of Intelligent Perception and Image Understanding of Ministry of Education of China Xi'an 710071 P. R. China Inst. of Intelligent Information Processing Xidian Univ. Xi'an 710071 P. R. China

To preserve the sharp features and details of the synthetic aperture radar （SAR） image effectively when despeckling, a despeckling algorithm with edge detection in nonsubsampled second generation bandelet transform （NSBT） domain is proposed. First, the Canny operator is utilized to detect and remove edges from the SAR image. Then the NSBT which has an optimal approximation to the edges of images and a hard thresholding rule are used to approximate the details while despeckling the edge-removed image. Finally, the removed edges are added to the reconstructed image. As the edges axe detected and protected, and the NSBT is used, the proposed algorithm reaches the state-of-the-art effect which realizes both despeckling and preserving edges and details simultaneously. Experimental results show that both the subjective visual effect and the mainly objective performance indexes of the proposed algorithm outperform that of both Bayesian wavelet shrinkage with edge detection and Bayesian least square-Gaussian scale mixture （BLS-GSM）.

关键词： computer image processing synthetic aperture radar speckle edge detection nonsubsampled second generation bandelet transform Canny operator threshold shrinkage.

来源：评论

学校读者我要写书评

暂无评论

A multiobjective immune clustering ensemble technique applied to unsupervised SAR image segmentation 10

A multiobjective immune clustering ensemble technique applie...

引用

ACM International Conference on image and Video Retrieval, ACM-CIVR 2010

作者： Liu, Ruochen Zhang, Wei Jiao, Licheng Liu, Fang Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information Processing Xidian University Xi'an China

ISBN: (纸本)9781450301176

In the past few years, multiobjective clustering has been one of the most successful techniques in the field of computer vision and data clustering. This paper proposes a novel unsupervised approach for synthetic aperture radar (SAR) image segmentation, namely, multiobjective immune clustering ensemble technique (MICET). The new technique first divides the image into several regions, and a certain number of pixels are picked out from these regions to form the clustering dataset. Second, artificial immune system (AIS) and multiobjective optimization (MOO) are introduced to generate multiple clustering results, which are then combined together for the following ensemble process. Multiple runs of the multiob-jective clustering method with different randomly selected image features are performed to ensure high quality components as well as necessary diversity for an efficient ensemble. Finally, each datum is assigned to one cluster according to the relationship with the clustering dataset. Experimental results show that interesting segmentation performances on SAR images can be achieved by the proposed technique despite its completely unsupervised nature. Copyright © 2010 ACM.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Filter for Visual Drone Single Object Tracking 16th

A Deep Learning Filter for Visual Drone Single Object Tracki...

引用

Workshops held at the 16th European Conference on Computer Vision, ECCV 2020

作者： Zhang, Xin Jiao, Licheng Liu, Xu Li, Xiaotong Zhang, Wenhua Zhu, Hao Zhang, Jie Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University Xi’an China

ISBN: (纸本)9783030668228

Object tracking is one of the most important topics in computer vision. In visual drone tracking, it is an extremely challenging due to various factors, such as camera motion, partial occlusion, and full occlusion. In this paper, we propose a deep learning filter method to relieve the above problems, which is to obtain a priori position of the object at the subsequent frame and predict its trajectory to follow up the object during occlusion. Our tracker adopts the geometric transformation of the surrounding of the object to prevent the bounding box of the object lost, and it uses context information to integrate its motion trend thereby tracking the object successfully when it reappears. Experiments on the VisDrone-SOT2018 test dataset and the VisDrone-SOT2020 val dataset illustrate the effectiveness of the proposed approach. © 2020, Springer Nature Switzerland AG.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Low bit-rate SAR image encoding using bandelets with adaptive quadtree partition

Low bit-rate SAR image encoding using bandelets with adaptiv...

引用

2009 Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2009

作者： Yang, Shuyuan Meng, Huixiao Wu, Ruixia Jiao, Licheng Key Laboratory of Intelligent Perception Image Understanding of Ministry of Education Institute of Intelligence Information Processing Xi'an 710071 China

ISBN: (纸本)9781424427314

Synthetic aperture radar (SAR) is an imaging system which provides high-resolution images of earth surface. Nowadays there is an ever-growing interest in the SAR data compression because of the huge resources which require for storage and transmission. In this paper, we address the problem of SAR image compression and apply the multiscale Bandelet with adaptive quadtree partition to solve it. Because Bandelet can provide an efficient representation of geometric structures existed in images, the Bandelet based method can capture abundant textures in SAR images. Moreover, the multiscale Bandelet with adaptive quadtree partition can approximate any piecewise Cα-regular functions when α is unknown, so Bandelet can represent the hierarchy textures of SAR images efficiently. Embedded Block Coding with Optimal Truncation (EBCOT) coding algorithm is employed in our proposed method. Experimental results show that our method outperforms JPEG2000 and the second generation Bandelet (2G-Bandelet) compression methods on SAR image encoding at low bit rates. ©2009 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

ICSA based projection pursuit clustering with LDA index and its application in SAR image segmentation

ICSA based projection pursuit clustering with LDA index and ...

引用

2009 Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2009

作者： Gou, Shuiping Feng, Jing Jiao, Licheng He, Xiao Key Laboratory of Intelligent Perception and Image Understanding for the Ministry of Education Institute of Intelligent Information Processing Xidian University Xi'an 710071 China

ISBN: (纸本)9781424427314

The performance of the traditional clustering algorithm is not always satisfied with the high-dimensional datasets, which make clustering method limited in many application. To solve this problem, Projection Pursuit with LDA index based on Immune Clonal Selection Algorithm is proposed in this paper. Projection pursuit strategy can maintain consistent Euclidean distances between points in the low-dimensional embeddings where the ICSA is used to search optimal projection direction. In the proposed algorithm, k-mean clustering algorithm is used to partition the reduced data and give labels to LDA index, and iterations have been done for several times can converge quickly to obtain a clustering result. The experimental results on UCI data show that the present method has better clustering accuracy compared with traditional linear dimension reduction method for principle component analysis (PCA). And the experiments on SAR image segmentation also have a good performance. ©2009 IEEE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Two-phase clustering algorithm with density exploring distance measure

引用

CAAI Transactions on Intelligence Technology 2018年第1期3卷 59-64页

作者： Jingjing Ma Xiangming Jiang Maoguo Gong Key Lab of Intelligent Perception and Image Understanding of Ministry of Education of China Xidian University PO Box 224 Xi'an 710071People's Republic of China

Here, the authors propose a novel two-phase clustering algorithm with a density exploring distance （DED） measure. In the first phase, the fast global K-means clustering algorithm is used to obtain the cluster number and the prototypes. Then, the prototypes of all these clusters and representatives of points belonging to these clusters are regarded as the input data set of the second phase. Afterwards, all the prototypes are clustered according to a DED measure which makes data points locating in the same structure to possess high similarity with each other. In experimental studies, the authors test the proposed algorithm on seven artificial as well as seven UCI data sets. The results demonstrate that the proposed algorithm is flexible to different data distributions and has a stronger ability in clustering data sets with complex non-convex distribution when compared with the comparison algorithms.

关键词：密度探索距离聚类算法计算方法人工智能

来源：评论

学校读者我要写书评

暂无评论

Synthetic aperture radar automatic target recognition based on curvelet transform

Synthetic aperture radar automatic target recognition based ...

引用

MIPPR 2009 - Automatic Target Recognition and image Analysis: 6th International Symposium on Multispectral image Processing and Pattern Recognition

作者： Wang, Shuang Liu, Zhuo Jiao, Licheng He, Jun Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China Institute of Intelligent Information Processing Xidian University Xi'an 710071 China

ISBN: (纸本)9780819478061

A novel synthetic aperture radar (SAR) automatic target recognition (ATR) approach based on Curvelet Transform is proposed. However, the existing approaches can not extract the more effective feature. In this paper, our method is concentrated on a new effective representation of the moving and stationary target acquisition and recognition (MSTAR) database to obtain a more accurate target region and reduce feature dimension. Firstly, MSTAR database can be extracted feature through the optimal sparse representation by curvelets to obtain a clear target region. However, considering the loss of part of edges of image. We extract coarse feature, which is to compensate fine feature error brought by segmentation. The final features consisting of fine and coarse feature are classified by SVM with Gaussian radial basis function (RBF) kernel. The experiments show that our proposed algorithm can achieve a better correct classification rate. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Automatic target recognition

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：