检索结果-内蒙古大学图书馆

IEEE International Conference on image processing

作者： Yu Zhao Lei Zhou Keren Fu Jie Yang Institution of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

ISBN: (纸本)9781467399623

In this paper, an approach using the spatio-temporal feature and nonnegative locality-constrained linear coding (NLLC) is proposed to detect abnormal events in videos. This approach utilizes position-based spatio-temporal descriptors as the low-level representations of a video clip. Each descriptor consists of the position information of a space-time interest point and an appearance feature vector. To obtain the high-level video representations, the nonnegative locality-constrained linear coding is adopted to encode each spatio-temporal descriptor. Then, the max pooling integrates all NLLC codes of a video clip to produce a feature vector. Finally, the support vector machine (SVM) is employed to classify the feature vector as abnormal or normal. Experimental results on two datasets have demonstrated the promising performance of the proposed approach in the detection of both global and local abnormal events.

关键词： Videos Encoding Feature extraction Event detection Support vector machines Computer vision image motion analysis Event detection Support Vector Network Videotapes image motion analysis abnormal event Eigenvector images computer vision Feature extraction video clips Nonnegative coding

来源：评论

学校读者我要写书评

暂无评论

Correlation filter tracking via bootstrap learning

Correlation filter tracking via bootstrap learning

引用

IEEE International Conference on image processing

作者： Kunqi Gu Tao Zhou Fanghui Liu Jie Yang Yu Qiao Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

In recent years, correlation filter based trackers outperform better than other trackers. Nevertheless, they only employ one feature and a single kernel, so they are usually not robust in complex scenes. In this paper, we derive a multi-feature and multi-kernel correlation filter based tracker which fully takes advantage of the invariance-discriminative power spectrums of various features and kernels to further improve the performance. A novel bootstrap learning method is utilized to obtain a strong classifier by fusing these weak kernel correlation filters (KCFs). Moreover, a new target scale estimation strategy is incorporated into our framework. The efficient and effective scale estimation method is based on target dictionary representation. The proposed method is tested on several videos and compared with seven state-of-the-art methods. Experimental results have provided further support to the effectiveness and robustness of the proposed method.

关键词： Kernel Target tracking Correlation Computational modeling Boosting Robustness Object tracking

来源：评论

学校读者我要写书评

暂无评论

Semantic Channels for Fast Pedestrian Detection

Semantic Channels for Fast Pedestrian Detection

引用

IEEE Conference on Computer Vision and pattern recognition

作者： Arthur Daniel Costea Sergiu Nedevschi Image Processing and Pattern Recognition Research Center Technical University of Cluj-Napoca

ISBN: (纸本)9781467388528

Pedestrian detection and semantic segmentation are high potential tasks for many real-time applications. However most of the top performing approaches provide state of art results at high computational costs. In this work we propose a fast solution for achieving state of art results for both pedestrian detection and semantic segmentation. As baseline for pedestrian detection we use sliding windows over cost efficient multiresolution filtered LUV+HOG channels. We use the same channels for classifying pixels into eight semantic classes. Using short range and long range multiresolution channel features we achieve more robust segmentation results compared to traditional codebook based approaches at much lower computational costs. The resulting segmentations are used as additional semantic channels in order to achieve a more powerful pedestrian detector. To also achieve fast pedestrian detection we employ a multiscale detection scheme based on a single flexible pedestrian model and a single image scale. The proposed solution provides competitive results on both pedestrian detection and semantic segmentation benchmarks at 8 FPS on CPU and at 15 FPS on GPU, being the fastest top performing approach.

关键词： Pedestrians Semantics Arts image scale short-distance central processing units segmentation Segmentation FES gene

来源：评论

学校读者我要写书评

暂无评论

Short text classification based on LDA topic model

Short text classification based on LDA topic model

引用

International Conference on Audio, Language and image processing, ICALIP

作者： Qiuxing Chen Lixiu Yao Jie Yang Institution of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

ISBN: (纸本)9781509006557

As the rapid development of computer technology and network communication, short text data has increased enormously. Classifying the short text snippets is a great challenge to due to its less semantic information and high sparseness. In this paper, we proposed an improved short text classification method based on Latent Dirichlet Allocation topic model and K-Nearest Neighbor algorithm. The generated probabilistic topics help both make the texts more semantic-focused and reduce the sparseness. In addition, we present a novel topic similarity measure method with the topic-word matrix and the relationship of the discriminative terms between two short texts. A short text dataset for experiment validation is constructed by crawling the posts from Sina News website. The extensive and comparable experimental results obtained show the effectiveness of our proposed method.

关键词： Training Text categorization Resource management Probabilistic logic Semantics Classification algorithms Search engines

来源：评论

学校读者我要写书评

暂无评论

Fault detection and isolation of sensor in Markov jump systems based on space geometry method

Fault detection and isolation of sensor in Markov jump syste...

引用

Chinese Control Conference (CCC)

作者： Yandong Hou Dianfeng Qiao Qianshuai Cheng Ruirui Huang Institute of Image Processing and Pattern Recognition Henan University Kaifeng Henan CN

This paper investigates sensor fault problems in Markov jump systems with uncertain disturbances. Using the measurement equation, the sensor faults can be translated into the state inputs. Subsequently, a cluster of residual generators is designed by employing the space geometric method. The corresponding filter parameters are obtained based on the space geometric approach, then using H ∞ optimization technique reduce the effects of disturbance inputs on the residuals, at the same time, the residual generator is designed so that the residual signals and sensor faults satisfy one to one correspondence, which can be used to detect and isolate the sensor faults in Markov jump systems with disturbance. Simulation results demonstrate the efficiency of the proposed method.

关键词： Hafnium Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Real-time multi-resolution digital elevation map creation using the sensor model of a stereovision sensor

Real-time multi-resolution digital elevation map creation us...

引用

International Conference on Intelligent Transportation

作者： Szilárd Mandici Sergiu Nedevschi Image Processing and Pattern Recognition Research Group Technical University of Cluj-Napoca Romania

ISBN: (纸本)9781509018901

This paper presents an approach for constructing high quality Digital Elevation Maps (DEMs) from dense stereo data. As opposed to classical DEM creation algorithms, the proposed solution uses the sensor models of the stereovision sensor to correct the raw data. The direct and inverse sensor models are found from experiments. The algorithm decomposes the 2D cells containing vertical objects or object boundaries in order to model the objects more precisely. The approach distinguishes between 2 types of cells: cells containing horizontal and vertical objects. For the vertical object cells, connected components in the histogram of heights are found while in the horizontal object cells, the most representative height is determined using a mode-seeking approach similar to mean shift. The 3D reconstructed points are assigned to the cells around it by considering the probability of correspondence based on the 2D Gaussian component of the direct sensor model. In order to eliminate the noise, a similarity measure is computed between each 3D point and cell based on the calculated DEM cell descriptor and is discarded if the similarity score is smaller than a predefined threshold. The algorithm is implemented on the GPU in order to achieve a real-time execution speed and it is evaluated extensively in comparison with other DEM creation algorithms using the latest KITTI stereo benchmark data. The obtained DEM is denser, more accurate and the object boundaries are modeled more precisely.

关键词： Three-dimensional displays Robot sensing systems image reconstruction Two dimensional displays Histograms Solid modeling Mathematical model

来源：评论

学校读者我要写书评

暂无评论

A MIL-based interactive approach for hotspot segmentation from bone scintigraphy

A MIL-based interactive approach for hotspot segmentation fr...

引用

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

作者： Shijie Geng Jingyang Ma Xiaoguang Niu Shaoyong Jia Yu Qiao Jie Yang Institute of Image Processing and Pattern Recognition The Key Laboratory of System Control and Information Processing Ministry of Education China

ISBN: (纸本)9781479999897

Bone scintigraphy is widely used to diagnose bone diseases. Accurate hotspot segmentation is a critical task for tumor metastasis diagnosis. In this paper, we propose an interactive approach to detect and extract hotspots in thoracic region based on a new multiple instance learning (MIL) method called EM-MILBoost. We convert the segmentation problem to a multiple instance learning task by constructing positive and negative bags according to the input bounding box. In order to be robust against noisy input, we train a region-level hotspot classifier with EM-MILBoost and develop several segmentation strategies based on it. The experimental results demonstrate that our method outperforms other methods and is robust against various noisy input.

关键词： image segmentation Noise measurement Bones Training Indexes Belts Standards

来源：评论

学校读者我要写书评

暂无评论

Unsupervised feature selection algorithm based on sparse representation 3

Unsupervised feature selection algorithm based on sparse rep...

引用

2016 3rd International Conference on Systems and Informatics, ICSAI 2016

作者： Cui, Guoqing Yang, Jie Zareapoor, Masoumeh Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Minhang District Shanghai China Jiechen Wang Complex Network and Control Lab Shanghai Jiao Tong University Minhang District Shanghai China

ISBN: (纸本)9781509055210

Feature selection, as a preprocessing step to machine learning, plays a pivotal role in removing irrelevant data, reducing dimensionality and improving performance evaluations. Recent years, sparse representation has become a useful tool for both supervised and unsupervised feature selection. So far, most of these algorithms still have many problems such as large computation load, performance with poor stability. Thus, this paper proposes a new unsupervised feature selection algorithm via sparse representation (UFSSR), with respect to efficiency and effectiveness. Firstly, this paper reconstructs part of data matrix via sparse representation, which makes the proposed algorithm be robust and independent of domain knowledge. Then, to reduce the reconstruction error, a new feature evaluation function is given to rank all features. Theoretical analysis and experiments compared with many popular algorithms on a set of datasets demonstrate the improvements brought by UFSSR. © 2016 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Robust Face recognition via Low-rank Sparse Representation-based Classification

引用

International Journal of Automation and computing 2015年第6期12卷 579-587页

作者： Hai-Shun Du Qing-Pu Hu Dian-Feng Qiao Ioannis Pitas Institute of Image Processing and Pattern Recognition Henan University Department of Informatics Aristotle University of Thessaloniki

Face recognition has attracted great interest due to its importance in many real-world applications. In this paper,we present a novel low-rank sparse representation-based classification(LRSRC) method for robust face recognition. Given a set of test samples, LRSRC seeks the lowest-rank and sparsest representation matrix over all training samples. Since low-rank model can reveal the subspace structures of data while sparsity helps to recognize the data class, the obtained test sample representations are both representative and discriminative. Using the representation vector of a test sample, LRSRC classifies the test sample into the class which generates minimal reconstruction error. Experimental results on several face image databases show the effectiveness and robustness of LRSRC in face image recognition.

关键词： Face recognition image classification sparse repre

来源：评论

学校读者我要写书评

暂无评论

Actuator Fault Detection and Isolation of Combined System Based on Space Geometry Theory 34

Actuator Fault Detection and Isolation of Combined System Ba...

引用

第三十四届中国控制会议

作者： CHENG Qianshuai QIAO Dianfeng HOU Yandong JIN Yong Institute of Image Processing and Pattern Recognition Henan University

ISBN: (纸本)9781467374439

In this paper, we propose an algorithm to solve the issue of actuator fault FDI of combined system. The algorithm is based on space geometry method. Firstly, we use space division theory and space projection operation of unobservability subspace to solve system matrix parameters. Then build a residual generator to realize decoupling corresponding relation of residuals and faults in combined system. Finally, the feasibility and effectiveness of the algorithm are shown for actuator FDI by simulations.

关键词： Combined System,Fault Detection and Isolation(FDI),Space Geometry Theory,Residual Generator

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：