检索结果-内蒙古大学图书馆

High-Power Diode Laser Technology and Applications IV

作者： Wang, Xiangyang Yang, Jie Peng, Ningsong Teng, Xiaolong Inst. of Image Processing and Pattern Recognition Jiaotong University Shanghai 200030 China

ISBN: (纸本)0819461466

We propose a new algorithm to find minimal rough set reducts by using Particle Swarm Optimization (PSO). Like Genetic Algorithm, PSO is also a type of evolutionary algorithm. But compared with GA, PSO does not need complex operators as crossover and mutation that G A does, it requires only primitive and simple mathematical operators, and is computationally inexpensive in terms of both memory and times. The experiments on some UCI data compare our algorithm with GA-based, and other deterministic rough set reduction algorithms. The results show that PSO is efficient to minimal rough set reduction. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Rough set theory

来源：评论

学校读者我要写书评

暂无评论

Dominant Correlogram Based Particle Filter Tracking

引用

Journal of Shanghai Jiaotong university(Science) 2005年第1期10卷 12-15页

作者：毛燕芬施鹏飞 Inst.of Image Processing & Pattern Recognition Shanghai Jiaotong Univ. Shanghai 200030 China

A novel dominant correlogram based particle filter was proposed for an object tracking in visual surveillance. Particle filter outperforms the Kalman filter in non-linear and non-Gaussian estimation problem. This paper proposed incorporating spatial information into visual feature, and yields a reliable likelihood description of the observation and prediction. A similarity-ratio is defined to evaluate the effectivity of different similarity measurements in weighing samples. The experimental results demonstrate the effective and robust performance compared with the histogram based tracking in traffic scenes.

关键词： dominant correlogram particle filter (PF) visual probabilistic tracking similarity-ratio

来源：评论

学校读者我要写书评

暂无评论

Research on a novel restoration algorithm of turbulence-degraded images with alternant iterations

引用

Journal of Systems Engineering and Electronics 2006年第3期17卷 477-482页

作者： Liu Chunsheng Hong Hanyu Zhang Tianxu Inst. for Pattern Recognition and AI State Key Laboratory of Image Processing and Intelligent Control Huazhong Univ. of Science and Technology Wuhan 430074 P. R. China

A new restoration algorithm based on double loops and alternant iterations is proposed to restore the object image effectively from a few frames of turbulence-degraded images, Based on the double loops, the iterative relations for estimating the turbulent point spread function PSF and object image alternately are derived. The restoration experiments have been made on computers, showing that the proposed algorithm can obtain the optimal estimations of the object and the point spread function, with the feasibility and practicality of the proposed algorithm being convincing.

关键词： turbulence-degraded image image restoration double loops alternant iterations.

来源：评论

学校读者我要写书评

暂无评论

Neural Networks in image Pyramids

Neural Networks in Image Pyramids

引用

1992 International Joint Conference on Neural Networks, IJCNN 1992

作者： Bischof, Horst Pinz, Axel J. Inst. for Automation Dept. for Pattern Recognition and Image Processing Technical University Vienna Austria

ISBN: (纸本)0780305590

We present a novel neural network model for visual information processing. The model uses a hierarchical network with local connectivity (image pyramid) as a stem network. This network generates hypotheses about the expected image content, and then selectively uses small neural network modules on parts of the image to check these hypotheses. The resulting neural network is able to use different spatial resolutions, and is both modular and hierarchical. We demonstrate the application of this model to remotely sensed image (Landsat TM) classification. We achieve a slightly better classification accuracy at reduced computational cost, compared to classification without the model. © 1992 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Crowd Scene Analysis: Crowd Counting using MCNN based on Self-Supervised training with Attention Mechanism 25

Crowd Scene Analysis: Crowd Counting using MCNN based on Sel...

引用

25th International Multi Topic Conference, INMIC 2023

作者： Asif, Muhammad Junaid Asad, Mujtaba Imran, Shaheer University of Central Punjab Faculty of It & Cs Lahore Pakistan Inst. of Image Processing and Pattern Recognition Seiee Sjtu Shanghai China

ISBN: (纸本)9798350317701

Fully-supervised learning requires expensive and laborious annotations of labeled data for crowd-counting tasks. To alleviate this burden, it is desirable to explore methods that reduce the need for extensive labeling. Fortunately, there are a vast number of unlabeled images available in the world, making them easily accessible compared to labeled datasets. This paper proposes a self-supervised learning-based M-CNN framework with an attention mechanism that aims to leverage unlabeled data for pre-training the model. The framework consists of four sub-modules: a data augmentation framework, a self-supervised training network, a multi-column CNN, and an attention mechanism. These networks receive the images that undergo random processing using two defined augmentation transformations. Transformed images are then subjected to self-supervised learning and fed to a feature extraction network. FEN consists of M-CNN with five convolutional branches to extract features at a multi-scale level. These extracted features are then employed as an attention mechanism to focus on the head or shoulder location of people. To evaluate the effectiveness of our proposed model, experiments are conducted on two public datasets: ShanghaiTech Part A, Part B, and UCFQNRF. The experimental results demonstrate that our approach outperforms state-of-the-art semi-supervised methods, showcasing the effectiveness of our proposed approach in leveraging both unlabeled and limited labeled data for crowd counting tasks. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An object tracking algorithmbased on occlusion mesh model

An object tracking algorithmbased on occlusion mesh model

引用

Proceedings of 2002 International Conference on Machine Learning and Cybernetics

作者： Zhao, Jian-Wei Wang, Peng Liu, Chong-Qing Inst. Image Proc Pattern Recognition Shanghai Jiaotong University Shanghai China

ISBN: (纸本)0780375084

The concept of occlusion mesh model is introduced. A novel object tracking algorithm based on occlusion mesh model is proposed. A modified occlusion detection method is considered to improve the detection accuracy. Mesh nodes motion estimation method based on feature window matching is presented to achieve sub-pixel resolution and overcome block artifacts produced by block matching. Experiment results indicate that the proposed algorithm is practical and feasible, it can be used to object tracking effectively. Also it solves 2D motion estimation problem existed in occlusion regions and shows better visual performance.

关键词： Algorithms

来源：评论

学校读者我要写书评

暂无评论

A Model of Federated Evidence Fusion for Real-time Urban Traffic State Estimation

引用

Journal of Shanghai Jiaotong university(Science) 2007年第6期12卷 793-798,804页

作者：孔庆杰刘允才 Inst. of Image Processing and Pattern Recognition Shanghai Jiaotong Univ.

In order to make full use of heterogeneous multi-sensor data to serve urban intelligent transportation systems, a real-time urban traffic state fusion model was proposed, named federated evidence fusion model. The model improves conventional D-S evidence theory in temporal domain, such that it can satisfy the requirement of real-time processing and utilize traffic detection information more efficaciously. The model frame and computational procedures are given. In addition, a generalized reliability weight matrix of evidence is also presented to increase the accuracy of estimation. After that, a simulation test is presented to explain the advantage of the proposed method in comparison with conventional D-S evidence theory. Besides, the validity of the model is proven by the use of the data of loop detectors and GPS probe vehicles collected from an urban link in Shanghai. Results of the experiment show that the proposed approach can well embody and track traffic state at character level in real-time conditions.

关键词： traffic state estimation D-S evidence theory information fusion intelligent transportation systems

来源：评论

学校读者我要写书评

暂无评论

Multi-resolution LOD volume rendering in medicine

引用

5th International Conference on Computational Science - ICCS 2005

作者： Xie, Kai Yang, Jie Zhu, Yue Min Inst. of Image Processing and Pattern Recognition Shanghai Jiaotong Univ. 200030 Shanghai China CREATIS CNRS INSERM 69621 Villeurbanne France

ISBN: (纸本)9783540260325

This paper presents a level of detail (LOD) selection algorithm for multi-resolution volume rendering using 3D texture mapping. It uses an adaptive scheme that renders the volume in a region-of-interest at a high resolution and the volume away from this region at progressively lower resolutions. The algorithm is based on several important criteria, rendering is done adaptively by selecting high-resolution cells close to a center of attention and low-resolution cells away from this area. In addition, our hierarchical level-of-detail representation guarantees consistent interpolation between different resolution levels. Experiments have been applied to a number of large medical data and produced high quality images at interactive frame rates using standard PC hardware. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

Unsupervised multiscale image segmentation using wavelet domain hidden Markov tree

Unsupervised multiscale image segmentation using wavelet dom...

引用

8th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2004

作者： Qing, Xu Jie, Yang Siyi, Ding Inst. of Image Processing and Pattern Recognition Shanghai Jiao tong Univ Shanghai Box251 1954 Huashan Road Shanghai China

ISBN: (纸本)3540228179

In this paper, we have improved the supervised multi-scale texture segmentation (HMTseg), where wavelet domain hidden Markov model is applied to capture the texture feature and a contextual model is employed to fuse multi-scale segmentation. In order to extend supervised HMTseg to an unsupervised one, we perform a hierarchical clustering in the blocks on the starting scale. The dissimilarity between sub-mages is measured by the Kullback- Leibler distance (KLD) between corresponding WD HMT models. Experiments show that the performance of our proposed method is promising and needs less prior information on textures present in the given images. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

image ANALYSIS BASED ON EDGE DETECTION TECHNIQUES

引用

Journal of Shanghai Jiaotong university(Science) 2002年第2期7卷 198-203页

作者： NASSIR H.SALMAN(纳瑟) LIU Chong-qing(刘重庆) Inst. of Image Processing & Pattern Recognition Shanghai Jiaotong Univ. Shanghai 200030 China Inst. of Image Processing & Pattern Recognition Shanghai Jiaotong Univ. Shanghai 200030 China

A method that incorporates edge detection technique, Markov Random field (MRF), watershed segmentation and merging techniques was presented for performing image segmentation and edge detection tasks. It first applies edge detection technique to obtain a Difference In Strength (DIS) map. An initial segmented result is obtained based on K means clustering technique and the minimum distance. Then the region process is modeled by MRF to obtain an image that contains different intensity regions. The gradient values are calculated and then the watershed technique is used. DIS calculation is used for each pixel to define all the edges (weak or strong) in the image. The DIS map is obtained. This help as priority knowledge to know the possibility of the region segmentation by the next step (MRF), which gives an image that has all the edges and regions information. In MRF model, gray level l , at pixel location i , in an image X , depends on the gray levels of neighboring pixels. The segmentation results are improved by using watershed algorithm. After all pixels of the segmented regions are processed, a map of primitive region with edges is generated. The edge map is obtained using a merge process based on averaged intensity mean values. A common edge detectors that work on (MRF) segmented image are used and the results are compared. The segmentation and edge detection result is one closed boundary per actual region in the image.

关键词： Difference In Strength (DIS) Markov Random Field (MRF) watershed algorithm K-means edge detection image segmentation image analysis

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：