检索结果-南通市图书馆

Real-time stereo matching on CUDA using Fourier descriptors and dynamic programming

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2019年第1期5卷 59-71页

作者： Mohamed Hallek Fethi Smach Mohamed Atri Faculty of Sciences of Monastir Technologies et services de l'information

Computation of stereoscopic depth and disparity map extraction are dynamic research topics.A large variety of algorithms has been developed,among which we cite feature matching, moment extraction, and image representation using descriptors to determine a disparity map. This paper proposes a new method for stereo matching based on Fourier descriptors. The robustness of these descriptors under photometric and geometric transformations provides a better representation of a template or a local region in the image. In our work, we specifically use generalized Fourier descriptors to compute a robust cost function.Then, a box filter is applied for cost aggregation to enforce a smoothness constraint between neighboring pixels. Optimization and disparity calculation are done using dynamic programming, with a cost based on similarity between generalized Fourier descriptors using Euclidean distance. This local cost function is used to optimize correspondences. Our stereo matching algorithm is evaluated using the Middlebury stereo benchmark; our approach has been implemented on parallel high-performance graphics hardware using CUDA to accelerate our algorithm, giving a real-time implementation.

关键词： generalized Fourier descriptors stereo matching dynamic programming CUDA

Saliency guided local and global descriptors for effective action recognition

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2016年第1期2卷 97-106页

作者： Ashwan Abdulmunem Yu-Kun Lai Xianfang Sun School of Computer Science and Informatics Cardiff University Department of Computer Science School of ScienceKerbala University

This paper presents a novel framework for human action recognition based on salient object detection and a new combination of local and global descriptors. We first detect salient objects in video frames and only extract features for such objects.We then use a simple strategy to identify and process only those video frames that contain salient objects. Processing salient objects instead of all frames not only makes the algorithm more efficient, but more importantly also suppresses the interference of background pixels. We combine this approach with a new combination of local and global descriptors, namely3D-SIFT and histograms of oriented optical flow(HOOF), respectively. The resulting saliency guided3D-SIFT–HOOF(SGSH) feature is used along with a multi-class support vector machine(SVM) classifier for human action recognition. Experiments conducted on the standard KTH and UCF-Sports action benchmarks show that our new method outperforms the competing state-of-the-art spatiotemporal feature-based human action recognition methods.

关键词： action recognition saliency detection local and global descriptors bag of visual words(Bo VWs) classification

Keypoints and descriptors Based on Cross-Modality Information Fusion for Camera Localization

在线全文

学校读者我要写书评

暂无评论

Wuhan University Journal of Natural Sciences 2021年第2期26卷 128-136页

作者： MA Shuo GAO Yongbin+ TIAN Fangzheng LU Junxin HUANG Bo GU Jia ZHOU Yilong College of Electronic and Electrical Engineering Shanghai University of Engineering ScienceShanghai 201620China

To address the problem that traditional keypoint detection methods are susceptible to complex backgrounds and local similarity of images resulting in inaccurate descriptor matching and bias in visual localization, keypoints and descriptors based on cross-modality fusion are proposed and applied to the study of camera motion estimation. A convolutional neural network is used to detect the positions of keypoints and generate the corresponding descriptors, and the pyramid convolution is used to extract multi-scale features in the network. The problem of local similarity of images is solved by capturing local and global feature information and fusing the geometric position information of keypoints to generate descriptors. According to our experiments, the repeatability of our method is improved by 3.7%, and the homography estimation is improved by 1.6%. To demonstrate the practicability of the method, the visual odometry part of simultaneous localization and mapping is constructed and our method is 35% higher positioning accuracy than the traditional method.

关键词： keypoints descriptors cross-modality information global feature visual odometry

Density Functional Theory for Electrocatalysis

在线全文

学校读者我要写书评

暂无评论

Energy & Environmental Materials 2022年第1期5卷 157-185页

作者： Xiaobin Liao Ruihu Lu Lixue Xia Qian Liu Huan Wang Kristin Zhao Zhaoyang Wang Yan Zhao State Key Laboratory of Silicate Materials for Architectures International School of Materials Science and EngineeringWuhan University of TechnologyWuhan 430070China Zhejiang University Hangzhou 310058China State Key Laboratory of Advanced Technology for Materials Synthesis and Processing Center of Smart Materials and DevicesSchool of Materials Science and EngineeringWuhan University of TechnologyWuhan 430070China Lynbrook High School San Jose CA 95129USA The Institute of Technological Sciences Wuhan UniversityWuhan 430072China

It is a considerably promising strategy to produce fuels and high-value chemicals through an electrochemical conversion process in the green and sustainable energy systems.Catalysts for electrocatalytic reactions,including hydrogen evolution reaction(HER),oxygen evolution reaction(OER),oxygen reduction reaction(ORR),nitrogen reduction reaction(NRR),carbon dioxide reduction reaction(CO_(2)RR),play a significant role in the advanced energy conversion technologies,such as water splitting devices,fuel cells,and rechargeable metal-air batteries.Developing low-cost and highly efficient electrocatalysts is closely related to establishing the composition-structure-activity relationships and fundamental understanding of catalytic mechanisms.Density functional theory(DFT)is emerging as an important computational tool that can provide insights into the relationship between the electrochemical performances and physical/chemical properties of catalysts.This article presents a review on the progress of the DFT,and the computational simulations,within the framework of DFT,for the electrocatalytic processes,as well as the computational designs and virtual screenings of new electrocatalysts.Some useful descriptors and analysis tools for evaluating the electrocatalytic performances are highlighted,including formation energies,d-band model,scaling relation,egorbital occupation,and free energies of adsorption.Furthermore,the remaining questions and perspectives for the development of DFT for electrocatalysis are also proposed.

关键词： analysis tools density functional theory descriptors electrocatalysis

Machine Learning for Organic Photovoltaic Polymers:A Minireview

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Polymer Science 2022年第8期40卷 870-876,I0006页

作者： Asif Mahmood Ahmad Irfan Jin-Liang Wang Beijing Key Laboratory of Photoelectronic/Electrophotonic Conversion Materials Key Laboratory of Medical Molecule Science and Pharmaceutics Engineering in Ministry of Industry and Information TechnologySchool of Chemistry and Chemical EngineeringBeijing Institute of TechnologyKey Laboratory of Cluster Science of Ministry of EducationBeijing100081China Department of Chemistry College of ScienceKing Khalid UniversityAbha61413Saudi Arabia

Machine learning is a powerful tool that can provide a way to revolutionize the material science.Its use for the designing and screening of materials for polymer solar cells is also increasing.Search of efficient polymeric materials for solar cells is really difficult task.Researchers have synthesized and fabricated so many materials.Sorting the results and get feedback for further research requires an innovative approach.In this minireview,we provides brief introduction of machine learning.The importance of machine learning is also mentioned,and the application of machine learning for polymeric material design is discussed.The key challenges that are hindering the wide spread use of machine are discussed.Suggestions are also given to improve the use of data science.The predictions using machine learning maybe not highly accurate but it definitely better than no prediction at all.

关键词： Machine learning Polymer solar cells Data science descriptors Polymers

Keypoint Description Using Statistical Descriptor with Similarity-Invariant Regions

在线全文

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2022年第7期42卷 407-421页

作者： Ibrahim El rube Sameer Alsharif Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityP.o.Box 11099Taif21944Saudi Arabia

This article presents a method for the description of key points using simple statistics for regions controlled by neighboring key points to remedy the gap in existing descriptors.Usually,the existent descriptors such as speeded up robust features(SURF),Kaze,binary robust invariant scalable keypoints(BRISK),features from accelerated segment test(FAST),and oriented FAST and rotated BRIEF(ORB)can competently detect,describe,and match images in the presence of some artifacts such as blur,compression,and illumination.However,the performance and reliability of these descriptors decrease for some imaging variations such as point of view,zoom(scale),and rotation.The intro-duced description method improves image matching in the event of such distor-tions.It utilizes a contourlet-based detector to detect the strongest key points within a speciﬁed window size.The selected key points and their neighbors con-trol the size and orientation of the surrounding regions,which are mapped on rec-tangular shapes using polar transformation.The resulting rectangular matrices are subjected to two-directional statistical operations that involve calculating the mean and standard deviation.Consequently,the descriptor obtained is invariant(translation,rotation,and scale)because of the two methods;the extraction of the region and the polar transformation techniques used in this paper.The descrip-tion method introduced in this article is tested against well-established and well-known descriptors,such as SURF,Kaze,BRISK,FAST,and ORB,techniques using the standard OXFORD dataset.The presented methodology demonstrated its ability to improve the match between distorted images compared to other descriptors in the literature.

关键词： Keypoint detection descriptors neighbor region similarity invariance

Extracting and smoothing contours in mammograms using Fourier descriptors

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Biomedical Science and Engineering 2014年第3期7卷 119-129页

作者： Cyrille K. Feudjio Alain Tiedeu Marie-Laure Noubeg Mihaela Gordan Aurel Vlaicu Samuel Domngang Centre Mère et Enfant Fondation Chantal Biya Yaoundé Cameroun CTMED Technical University of Cluj-Napoca Cluj-Napoca Romania Faculty of Science University of Yaoundé I Yaoundé Cameroon LETS GRETMAT National Advanced School of Engineering Yaoundé Cameroon

Contour is an important pattern descriptor in image processing and particularly in region description, registration and length estimation. In many applications where contour is used, a good segmentation and an efficient smoothing method are needed. In X-ray images, such as mammograms, where object edge is not clearly discernible, estimating the object’s contour may yield substantial shift along the boundary due to noise or segmentation drawbacks. An appropriate smoothing is therefore required to reduce these effects. In this paper, an approach based on local adaptive threshold segmentation to extract contour and a new smoothing approach founded on Fourier descriptors are introduced. The experimental results of extraction obtained from a set of mammograms and compared with the breast regions delineated by radiologists yielded a percent overlap area of 98.7% ± 0.9% with false positive and negative rates of 0.36 ± 0.74 and 0.93 ± 0.44 respectively. The proposed method was tested on a set of images and improved the accuracy, leading to an average error of less than one pixel.

关键词： Mammogram Segmentation Breast Contour Smoothing Fourier descriptors

Facial Expression Recognition Based on Local Fourier Coefficients and Facial Fourier descriptors

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Signal and Information Processing 2017年第3期8卷 132-151页

作者： Gibran Benitez-Garcia Tomoaki Nakamura Masahide Kaneko Department of Mechanical Engineering and Intelligent Systems The University of Electro-Communications Tokyo Japan

The recent boom of mass media communication (such as social media and mobiles) has boosted more applications of automatic facial expression recognition (FER). Thus, human facial expressions have to be encoded and recognized through digital devices. However, this process has to be done under recurrent problems of image illumination changes and partial occlusions. Therefore, in this paper, we propose a fully automated FER system based on Local Fourier Coefficients and Facial Fourier descriptors. The combined power of appearance and geometric features is used for describing the specific facial regions of eyes-eyebrows, nose and mouth. All based on the attributes of the Fourier Transform and Support Vector Machines. Hence, our proposal overcomes FER problems such as illumination changes, partial occlusion, image rotation, redundancy and dimensionality reduction. Several tests were performed in order to demonstrate the efficiency of our proposal, which were evaluated using three standard databases: CK+, MUG and TFEID. In addition, evaluation results showed that the average recognition rate of each database reaches higher performance than most of the state-of-the-art techniques surveyed in this paper.

关键词： Facial Expression Recognition Fourier Coefficients Fourier descriptors Facial Region Segmentation Partial Occlusion

DFT-Based Prediction of Bioconcentration Factors of Polychlorinated Biphenyls in Fish Species Using Molecular descriptors

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Advances in Biological Chemistry 2020年第1期10卷 1-15页

作者： Anil Kumar Soni Pratibha Singh Vishnu Kumar Sahu Department of Chemistry Shia Post Graduate College Lucknow India Department of Chemistry Saket Post Graduate College Ayodhya India Department of Chemistry Maharani Lal Kunwari Post Graduate College Balrampur India.

Experimental determination of BCFs is expensive and demanding if performed correctly. Because of this, measuring the BCFs of many thousands of chemical substances that are potential regulatory interest is simply not possible. Hence, prediction of BCFs of the PCBs based on QSAR were made time to time to increase the probability of success and reduce the time and cost in exploring the toxicological and ecological characteristics of molecules. DFT methods are, in general, capable of generating a variety of isolated molecular descriptors as well as local reactivity descriptors quite accurately. In this work, prediction of BCFs of the fifty seven PCBs based on quantum chemical descriptors derived from DFT method using the B88-PW91 GGA energy function with the DZVP basis set have been made. The study concluded that dipole moment and ionization potential are reliable descriptors for correlation of bioconcentration factors of polychlorinated biphenyls with their electronic structures. The resulted QSAR model (r2 = 0.9139, ?= 0.8986, k = 2, SE = 0.2668) can be useful for predicting the BCFs of compounds prior to their synthesis.

关键词： PCBs QSAR DFT Quantum Chemical descriptors