DOCSLIB.ORG

Intelligent Video Surveillance Dmitry Kangin

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text

Load more

Intelligent Video Surveillance Dmitry Kangin Supervisors: Prof. Plamen P. Angelov, PhD, DSc, FIEEE, FIET Prof. Garegin Markarian, PhD, DSc, FIET A thesis presented for the degree of Doctor of Philosophy Data Science Group School of Computing and Communications Lancaster University England February 2016 Abstract In the focus of this thesis are the new and modified algorithms for object detection, recognition and tracking within the context of video analytics. The manual video surveillance has been proven to have low effectiveness and, at the same time, high expense because of the need in manual labour of operators, which are additionally prone to erroneous decisions. Along with increase of the number of surveillance cameras, there is a strong need to push for automatisation of the video analytics. The benefits of this approach can be found both in military and civilian applications. For military applications, it can help in localisation and tracking of objects of interest. For civilian applications, the similar object localisation procedures can make the criminal investigations more effective, extracting the meaningful data from the massive video footage. Recently, the wide accessibility of consumer unmanned aerial vehicles has become a new threat as even the simplest and cheapest airborne vessels can carry some cargo that means they can be upgraded to a serious weapon. Additionally they can be used for spying that imposes a threat to a private life. The autonomous car driving systems are now impossible without applying machine vision methods. The industrial applications require automatic quality control, including non-destructive methods and particularly methods based on the video analysis. All these applications give a strong evidence in a practical need in machine vision algorithms for object detection, tracking and classification and gave a reason for writing this thesis. The contributions to knowledge of the thesis consist of two main parts: video tracking and object detection and recognition, unified by the common idea of its applicability to video analytics problems. The novel algorithms for object detection and tracking, described in this thesis, are unsupervised and have only a small number of parameters. The approach is based on rigid motion segmentation by Bayesian filtering. The Bayesian filter, which was proposed specially for this method and contributes to its novelty, is formulated as a generic approach, and then applied to the video analytics problems. The method is augmented with optional object co- ordinate estimation using plain two-dimensional terrain assumption which gives a basis for the algorithm usage inside larger sensor data fusion models. The proposed approach for object detection and classification is based on the evolving systems concept and the new Typicality-Eccentricity Data Analytics (TEDA) framework. The methods are capable of solving classical problems of data mining: clustering, classification, and regression. The methods are proposed in a domain-independent way and are capable of 1 addressing shift and drift of the data streams. Examples are given for the clustering and classification of the imagery data. For all the developed algorithms, the experiments have shown sustainable results on the testing data. The practical applications of the proposed algorithms are carefully examined and tested. 2 Statement of Originality I, Dmitry Kangin, confirm that the work presented in this thesis is my own. Where information has been derived from other sources, I confirm that this has been indicated in the thesis. 3 Acknowledgements The author is pleased to thank Denis Kolev and Mikhail Suvorov, discussions with whom, as well the co-operation on the articles and book chapter, have contributed significantly to this thesis. The discussions, article co-operation and various help and assistance of my supervisors, Professor Plamen Angelov and Professor Garik Markarian, helped me enormously. Also I need to praise Professor George Kolev for all discussions and help. Also, many appreciation go to my colleagues in Rinicom, to fellows of the EU FP7 TRAX project for object tracking, in which I am happy to participate, and to my parents, Nikolay and Lyudmila, and my sister Evgenia. 4 Contents Abstract............................................................................................................................. 1 Statement of Originality ................................................................................................... 3 Acknowledgements .......................................................................................................... 4 List of Figures................................................................................................................... 8 List of Tables .................................................................................................................. 10 Acronyms & Abbreviations ............................................................................................ 11 1 Research Overview ................................................................................................ 13 1.1 Motivation .......................................................................................................... 13 1.2 Research Contribution ....................................................................................... 14 1.3 Methodology ...................................................................................................... 15 1.4 Publication Summary ......................................................................................... 15 1.5 Thesis Outline .................................................................................................... 16 2 Existing tracking, detection and recognition techniques ....................................... 18 2.1 Tracking methods survey ................................................................................... 18 2.1.1 Brief review of the state-of-the-art tracking methods ................................ 18 2.1.2 Technical description of the state-of-the-art methods ................................ 21 2.1.3 Optical flow: the necessary supplement to video object tracking .............. 28 2.2 Detection and recognition methods survey ........................................................ 29 2.2.1 Object detection methods review ............................................................... 32 2.2.2 Neural networks review .............................................................................. 33 2.2.3 Decision trees ............................................................................................. 35 2.2.4 Support Vector Machines ........................................................................... 37 2.2.5 Evolving fuzzy classifiers ........................................................................... 41 2.2.6 Clustering techniques ................................................................................. 44 2.2.7 Image segmentation techniques .................................................................. 49 2.2.8 Template matching techniques ................................................................... 52 5 2.2.9 Feature extraction survey ............................................................................ 54 2.3 Conclusion ......................................................................................................... 59 3 Proposed object tracking techniques ..................................................................... 61 3.1 Practical motivation of the method .................................................................... 61 3.2 Bayesian filter based algorithm for Gaussian mixture propagation ................... 62 3.2.1 System initialisation ................................................................................... 64 3.2.2 Prediction .................................................................................................... 64 3.2.3 Update ......................................................................................................... 66 3.2.4 EM algorithm for the proposed model ....................................................... 67 3.3 Bayesian filter based algorithm with variational inference ............................... 71 3.3.1 Variational inference for the Bayesian filter approximation ...................... 71 3.4 Feature points detection and tracking ................................................................ 77 3.5 Object detection ................................................................................................. 78 3.6 Object co-ordinates estimation combined with Bayesian filter based algorithm 78 3.7 Final formulation of the proposed tracking algorithm ....................................... 80 3.8 Conclusion ......................................................................................................... 81 4 Proposed object detection and recognition techniques .......................................... 83 4.1 Clustering techniques ......................................................................................... 83 4.1.1 TEDA approach overview .......................................................................... 84 4.1.2 Recursive calculation of typicality and eccentricity ................................... 85 4.1.3 Covariance matrix update ........................................................................... 89 4.1.4 TEDACluster .............................................................................................
Recommended publications
  • Edge Detection of an Image Based on Extended Difference of Gaussian

    Edge Detection of an Image Based on Extended Difference of Gaussian

    American Journal of Computer Science and Technology 2019; 2(3): 35-47 http://www.sciencepublishinggroup.com/j/ajcst doi: 10.11648/j.ajcst.20190203.11 ISSN: 2640-0111 (Print); ISSN: 2640-012X (Online) Edge Detection of an Image Based on Extended Difference of Gaussian Hameda Abd El-Fattah El-Sennary1, *, Mohamed Eid Hussien1, Abd El-Mgeid Amin Ali2 1Faculty of Science, Aswan University, Aswan, Egypt 2Faculty of Computers and Information, Minia University, Minia, Egypt Email address: *Corresponding author To cite this article: Hameda Abd El-Fattah El-Sennary, Abd El-Mgeid Amin Ali, Mohamed Eid Hussien. Edge Detection of an Image Based on Extended Difference of Gaussian. American Journal of Computer Science and Technology. Vol. 2, No. 3, 2019, pp. 35-47. doi: 10.11648/j.ajcst.20190203.11 Received: November 24, 2019; Accepted: December 9, 2019; Published: December 20, 2019 Abstract: Edge detection includes a variety of mathematical methods that aim at identifying points in a digital image at which the image brightness changes sharply or, more formally, has discontinuities. The points at which image brightness changes sharply are typically organized into a set of curved line segments termed edges. The same problem of finding discontinuities in one-dimensional signals is known as step detection and the problem of finding signal discontinuities over time is known as change detection. Edge detection is a fundamental tool in image processing, machine vision and computer vision, particularly in the areas of feature detection and feature extraction. It's also the most important parts of image processing, especially in determining the image quality.
  • Multiscale Computation and Dynamic Attention in Biological and Artificial

    Multiscale Computation and Dynamic Attention in Biological and Artificial

    brain sciences Review Multiscale Computation and Dynamic Attention in Biological and Artificial Intelligence Ryan Paul Badman 1,* , Thomas Trenholm Hills 2 and Rei Akaishi 1,* 1 Center for Brain Science, RIKEN, Saitama 351-0198, Japan 2 Department of Psychology, University of Warwick, Coventry CV4 7AL, UK; [email protected] * Correspondence: [email protected] (R.P.B.); [email protected] (R.A.) Received: 4 March 2020; Accepted: 17 June 2020; Published: 20 June 2020 Abstract: Biological and artificial intelligence (AI) are often defined by their capacity to achieve a hierarchy of short-term and long-term goals that require incorporating information over time and space at both local and global scales. More advanced forms of this capacity involve the adaptive modulation of integration across scales, which resolve computational inefficiency and explore-exploit dilemmas at the same time. Research in neuroscience and AI have both made progress towards understanding architectures that achieve this. Insight into biological computations come from phenomena such as decision inertia, habit formation, information search, risky choices and foraging. Across these domains, the brain is equipped with mechanisms (such as the dorsal anterior cingulate and dorsolateral prefrontal cortex) that can represent and modulate across scales, both with top-down control processes and by local to global consolidation as information progresses from sensory to prefrontal areas. Paralleling these biological architectures, progress in AI is marked by innovations in dynamic multiscale modulation, moving from recurrent and convolutional neural networks—with fixed scalings—to attention, transformers, dynamic convolutions, and consciousness priors—which modulate scale to input and increase scale breadth.
  • Deep Neural Network Models for Sequence Labeling and Coreference Tasks

    Deep Neural Network Models for Sequence Labeling and Coreference Tasks

    Federal state autonomous educational institution for higher education ¾Moscow institute of physics and technology (national research university)¿ On the rights of a manuscript Le The Anh DEEP NEURAL NETWORK MODELS FOR SEQUENCE LABELING AND COREFERENCE TASKS Specialty 05.13.01 - ¾System analysis, control theory, and information processing (information and technical systems)¿ A dissertation submitted in requirements for the degree of candidate of technical sciences Supervisor: PhD of physical and mathematical sciences Burtsev Mikhail Sergeevich Dolgoprudny - 2020 Федеральное государственное автономное образовательное учреждение высшего образования ¾Московский физико-технический институт (национальный исследовательский университет)¿ На правах рукописи Ле Тхе Ань ГЛУБОКИЕ НЕЙРОСЕТЕВЫЕ МОДЕЛИ ДЛЯ ЗАДАЧ РАЗМЕТКИ ПОСЛЕДОВАТЕЛЬНОСТИ И РАЗРЕШЕНИЯ КОРЕФЕРЕНЦИИ Специальность 05.13.01 – ¾Системный анализ, управление и обработка информации (информационные и технические системы)¿ Диссертация на соискание учёной степени кандидата технических наук Научный руководитель: кандидат физико-математических наук Бурцев Михаил Сергеевич Долгопрудный - 2020 Contents Abstract 4 Acknowledgments 6 Abbreviations 7 List of Figures 11 List of Tables 13 1 Introduction 14 1.1 Overview of Deep Learning . 14 1.1.1 Artificial Intelligence, Machine Learning, and Deep Learning . 14 1.1.2 Milestones in Deep Learning History . 16 1.1.3 Types of Machine Learning Models . 16 1.2 Brief Overview of Natural Language Processing . 18 1.3 Dissertation Overview . 20 1.3.1 Scientific Actuality of the Research . 20 1.3.2 The Goal and Task of the Dissertation . 20 1.3.3 Scientific Novelty . 21 1.3.4 Theoretical and Practical Value of the Work in the Dissertation . 21 1.3.5 Statements to be Defended . 22 1.3.6 Presentations and Validation of the Research Results .
  • Scale Invariant Feature Transform - Scholarpedia 2015-04-21 15:04

    Scale Invariant Feature Transform - Scholarpedia 2015-04-21 15:04

    Scale Invariant Feature Transform - Scholarpedia 2015-04-21 15:04 Scale Invariant Feature Transform +11 Recommend this on Google Tony Lindeberg (2012), Scholarpedia, 7(5):10491. doi:10.4249/scholarpedia.10491 revision #149777 [link to/cite this article] Prof. Tony Lindeberg, KTH Royal Institute of Technology, Stockholm, Sweden Scale Invariant Feature Transform (SIFT) is an image descriptor for image-based matching and recognition developed by David Lowe (1999, 2004). This descriptor as well as related image descriptors are used for a large number of purposes in computer vision related to point matching between different views of a 3-D scene and view-based object recognition. The SIFT descriptor is invariant to translations, rotations and scaling transformations in the image domain and robust to moderate perspective transformations and illumination variations. Experimentally, the SIFT descriptor has been proven to be very useful in practice for image matching and object recognition under real-world conditions. In its original formulation, the SIFT descriptor comprised a method for detecting interest points from a grey- level image at which statistics of local gradient directions of image intensities were accumulated to give a summarizing description of the local image structures in a local neighbourhood around each interest point, with the intention that this descriptor should be used for matching corresponding interest points between different images. Later, the SIFT descriptor has also been applied at dense grids (dense SIFT) which have been shown to lead to better performance for tasks such as object categorization, texture classification, image alignment and biometrics . The SIFT descriptor has also been extended from grey-level to colour images and from 2-D spatial images to 2+1-D spatio-temporal video.
  • Convolutional Neural Network Model Layers Improvement for Segmentation and Classification on Kidney Stone Images Using Keras and Tensorflow

    Convolutional Neural Network Model Layers Improvement for Segmentation and Classification on Kidney Stone Images Using Keras and Tensorflow

    Journal of Multidisciplinary Engineering Science and Technology (JMEST) ISSN: 2458-9403 Vol. 8 Issue 6, June - 2021 Convolutional Neural Network Model Layers Improvement For Segmentation And Classification On Kidney Stone Images Using Keras And Tensorflow Orobosa Libert Joseph Waliu Olalekan Apena Department of Computer / Electrical and (1) Department of Computer / Electrical and Electronics Engineering, The Federal University of Electronics Engineering, The Federal University of Technology, Akure. Nigeria. Technology, Akure. Nigeria. [email protected] (2) Biomedical Computing and Engineering Technology, Applied Research Group, Coventry University, Coventry, United Kingdom [email protected], [email protected] Abstract—Convolutional neural network (CNN) and analysis, by automatic or semiautomatic means, of models are beneficial to image classification large quantities of data in order to discover meaningful algorithms training for highly abstract features patterns [1,2]. The domains of data mining include: and work with less parameter. Over-fitting, image mining, opinion mining, web mining, text mining, exploding gradient, and class imbalance are CNN and graph mining and so on. Some of its applications major challenges during training; with appropriate include anomaly detection, financial data analysis, management training, these issues can be medical data analysis, social network analysis, market diminished and enhance model performance. The analysis [3]. Recent progress in deep learning using models are 128 by 128 CNN-ML and 256 by 256 CNN machine learning (CNN-ML) has been helpful in CNN-ML training (or learning) and classification. decision support and contributed to positive outcome, The results were compared for each model significantly. The application of CNN-ML to diverse classifier. The study of 128 by 128 CNN-ML model areas of soft computing is adapted diagnosis has the following evaluation results consideration procedure to enhance time and accuracy [4].
  • Edge Detection Low Level

    Edge Detection Low Level

    Image Processing - Lesson 10 Image Processing - Computer Vision Edge Detection Low Level • Edge detection masks Image Processing representation, compression,transmission • Gradient Detectors • Compass Detectors image enhancement • Second Derivative - Laplace detectors • Edge Linking edge/feature finding • Hough Transform image "understanding" Computer Vision High Level UFO - Unidentified Flying Object Point Detection -1 -1 -1 Convolution with: -1 8 -1 -1 -1 -1 Large Positive values = light point on dark surround Large Negative values = dark point on light surround Example: 5 5 5 5 5 -1 -1 -1 5 5 5 100 5 * -1 8 -1 5 5 5 5 5 -1 -1 -1 0 0 -95 -95 -95 = 0 0 -95 760 -95 0 0 -95 -95 -95 Edge Definition Edge Detection Line Edge Line Edge Detectors -1 -1 -1 -1 -1 2 -1 2 -1 2 -1 -1 2 2 2 -1 2 -1 -1 2 -1 -1 2 -1 -1 -1 -1 2 -1 -1 -1 2 -1 -1 -1 2 gray value gray x edge edge Step Edge Step Edge Detectors -1 1 -1 -1 1 1 -1 -1 -1 -1 -1 -1 -1 -1 -1 1 -1 -1 1 1 -1 -1 -1 -1 1 1 1 1 -1 1 -1 -1 1 1 1 1 1 1 gray value gray -1 -1 1 1 1 -1 1 1 x edge edge Example Edge Detection by Differentiation Step Edge detection by differentiation: 1D image f(x) gray value gray x 1st derivative f'(x) threshold |f'(x)| - threshold Pixels that passed the threshold are -1 -1 1 1 -1 -1 -1 -1 Edge Pixels -1 -1 1 1 -1 -1 -1 -1 -1 -1 1 1 1 1 1 1 -1 -1 1 1 1 -1 1 1 Gradient Edge Detection Gradient Edge - Examples ∂f ∂x ∇ f((x,y) = Gradient ∂f ∂y ∂f ∇ f((x,y) = ∂x , 0 f 2 f 2 Gradient Magnitude ∂ + ∂ √( ∂ x ) ( ∂ y ) ∂f ∂f Gradient Direction tg-1 ( / ) ∂y ∂x ∂f ∇ f((x,y) = 0 , ∂y Differentiation in Digital Images Example Edge horizontal - differentiation approximation: ∂f(x,y) Original FA = ∂x = f(x,y) - f(x-1,y) convolution with [ 1 -1 ] Gradient-X Gradient-Y vertical - differentiation approximation: ∂f(x,y) FB = ∂y = f(x,y) - f(x,y-1) convolution with 1 -1 Gradient-Magnitude Gradient-Direction Gradient (FA , FB) 2 2 1/2 Magnitude ((FA ) + (FB) ) Approx.
  • A PRAGMATIC ANALYSIS of REFUSAL EXPRESSIONS USED by the FAMILY CHARACTERS in ORPHAN MOVIE a THESIS Presented As a Partial Fulfil

    A PRAGMATIC ANALYSIS of REFUSAL EXPRESSIONS USED by the FAMILY CHARACTERS in ORPHAN MOVIE a THESIS Presented As a Partial Fulfil

    A PRAGMATIC ANALYSIS OF REFUSAL EXPRESSIONS USED BY THE FAMILY CHARACTERS IN ORPHAN MOVIE A THESIS Presented as a Partial Fulfillment of the Requirements for the Attainment of the Degree of Sarjana Sastra in English Language and Literature By Arum Sari 07211144028 STUDY PROGRAM OF ENGLISH LANGUAGE AND LITERATURE DEPARTMENT OF ENGLISH EDUCATION FACULTY OF LANGUAGES AND ARTS STATE UNIVERSITY OF YOGYAKARTA 2012 MOTTOS “The only way to do great work is to love what you do.” (Steve Jobs) “Never try, never know” (Topik) v DEDICATION I dedicate this thesis to people whom I love most in the world: Bapak Bambang Setyawan and Ibu Rika Rostika Ningsih vi ACKNOWLEDGMENTS Alhamdulilah, all praise to be Allah SWT, the Almighty, and the Most Merciful without which I would have never finished this thesis completely. I would also like to give my deepest thank to: 1. Suhaini, M. Saleh, M.A as my first consultant and Paulus Kurnianta, M.Hum as my second consultant, without their advice, care and patience, this thesis would not have been finished; 2. my Pembimbing Akademik, Paulus Kurnianta, M.Hum. for his guidance; 3. all lectures in study program Language and Literature in Yogyakarta State University; 4. my parents, Bambang Setyawan and Rika Rostika Ningsih who have given me endless love, support and pray, so that I could finish this thesis; 5. my beloved sister, Sekar Galuh who always supports and prays for me; 6. my aunt Mama Enny Ratna Dewi who always gives me inspiration and supports me; 7. my kind-hearted cousin, Cubi Abi who always reminds me about this thesis; 8.
  • Fast Almost-Gaussian Filtering

    Fast Almost-Gaussian Filtering

    Fast Almost-Gaussian Filtering Peter Kovesi Centre for Exploration Targeting School of Earth and Environment The University of Western Australia 35 Stirling Highway Crawley WA 6009 Email: [email protected] Abstract—Image averaging can be performed very efficiently paper describes how the fixed low cost of averaging achieved using either separable moving average filters or by using summed through separable moving average filters, or via summed area area tables, also known as integral images. Both these methods tables, can be exploited to achieve a good approximation allow averaging to be performed at a small fixed cost per pixel, independent of the averaging filter size. Repeated filtering with to Gaussian filtering also at a small fixed cost per pixel, averaging filters can be used to approximate Gaussian filtering. independent of filter size. Thus a good approximation to Gaussian filtering can be achieved Summed area tables were devised by Crow in 1984 [12] but at a fixed cost per pixel independent of filter size. This paper only recently introduced to the computer vision community by describes how to determine the averaging filters that one needs Viola and Jones [13]. A summed area table, or integral image, to approximate a Gaussian with a specified standard deviation. The design of bandpass filters from the difference of Gaussians can be generated by computing the cumulative sums along the is also analysed. It is shown that difference of Gaussian bandpass rows of an image and then computing the cumulative sums filters share some of the attributes of log-Gabor filters in that down the columns.
  • The History Began from Alexnet: a Comprehensive Survey on Deep Learning Approaches

    The History Began from Alexnet: a Comprehensive Survey on Deep Learning Approaches

    > REPLACE THIS LINE WITH YOUR PAPER IDENTIFICATION NUMBER (DOUBLE-CLICK HERE TO EDIT) < 1 The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches Md Zahangir Alom1, Tarek M. Taha1, Chris Yakopcic1, Stefan Westberg1, Paheding Sidike2, Mst Shamima Nasrin1, Brian C Van Essen3, Abdul A S. Awwal3, and Vijayan K. Asari1 Abstract—In recent years, deep learning has garnered I. INTRODUCTION tremendous success in a variety of application domains. This new ince the 1950s, a small subset of Artificial Intelligence (AI), field of machine learning has been growing rapidly, and has been applied to most traditional application domains, as well as some S often called Machine Learning (ML), has revolutionized new areas that present more opportunities. Different methods several fields in the last few decades. Neural Networks have been proposed based on different categories of learning, (NN) are a subfield of ML, and it was this subfield that spawned including supervised, semi-supervised, and un-supervised Deep Learning (DL). Since its inception DL has been creating learning. Experimental results show state-of-the-art performance ever larger disruptions, showing outstanding success in almost using deep learning when compared to traditional machine every application domain. Fig. 1 shows, the taxonomy of AI. learning approaches in the fields of image processing, computer DL (using either deep architecture of learning or hierarchical vision, speech recognition, machine translation, art, medical learning approaches) is a class of ML developed largely from imaging, medical information processing, robotics and control, 2006 onward. Learning is a procedure consisting of estimating bio-informatics, natural language processing (NLP), cybersecurity, and many others.
  • “Graph Cut Based Image Segmentation Using Statistical Priors and Its

    “Graph Cut Based Image Segmentation Using Statistical Priors and Its

    “GRAPH CUT BASED IMAGE SEGMENTATION USING STATISTICAL PRIORS AND ITS APPLICATION TO OBJECT DETECTION AND THIGH CT TISSUE IDENTIFICATION ANALYSIS” by TAPOSH BISWAS A THESIS Submitted in partial fulfillment of the requirements for the degree of Master of Science in the Natural Resources Graduate Program of Delaware State University DOVER, DELAWARE May 2018 This thesis is approved by the following members of the Final Oral Review Committee: Dr. Sokratis Makrogiannis, Committee Chairperson, Department of Mathematical Science, Delaware State University Dr. Thomas A. Planchon, Committee Member, Department of Physics and Engineering, Delaware State University Dr. Qi Lu, Committee Member, Department of Physics and Engineering, Delaware State University Dr. Matthew Tanzy, External Committee Member, Department of Mathematical Science, Delaware State University COPYRIGHT Copyright ©2018 by Taposh Biswas. All rights reserved. DEDICATION This thesis is dedicated to my parents Monoranjan Biswas and Dipti Biswas who have supported curiosity throughout my life. Without their persistent guidance, support, and advice, the successes I have achieved till now would never have come to fruition. ii ACKNOWLEDGEMENTS First, I would like to thank Dr. Sokratis Makrogiannis for giving me the opportunity to be a part of his research group (MIVIC) and supporting me through my thesis. It is an honor to work with him; he was always there for helping me improve my programming skills and assisting me with my research. I really appreciate his contributions of time, ideas and funding to complete my master’s degree. His door was always to discuss about any problem. I would like to thank the Federal Research and Development Matching Grant Program of the Delaware Economic Development Office (DEDO) for the funding and giving me the opportunity to complete my degree.
  • The Understanding of Convolutional Neuron Network Family

    The Understanding of Convolutional Neuron Network Family

    2017 2nd International Conference on Computer Engineering, Information Science and Internet Technology (CII 2017) ISBN: 978-1-60595-504-9 The Understanding of Convolutional Neuron Network Family XINGQUN QI ABSTRACT Along with the development of the computing speed and Artificial Intelligence, more and more jobs have been done by computers. Convolutional Neural Network (CNN) is one of the most popular algorithms in the field of Deep Learning. It is mainly used in computer identification, especially in voice, text recognition and other aspects of the application. CNNs have been developed for decades. In theory, Convolutional Neural Network has gradually become more mature. However, in practical applications, it is limited by various conditions. This paper will introduce the course of Convolutional Neural Network’s development today, as well as the current more mature and popular architecture and related applications of it, to help readers have more macro and comprehensive understanding of Convolutional Neural Networks. KEYWORDS Convolutional Neuron Network, Architecture, CNN family, Application INTRODUCTION With the continuous improvements of technology, there are more and more multi- disciplinary applications achieved with computer technology. And Machine Learning, especially Deep Learning is one of the most indispensable and important parts of that technology. Deep learning has the great advantage of acquiring features and modeling from data [1]. The Convolutional Neural Network (CNN) algorithm is one of the best and foremost algorithms in the Deep Learning algorithms. It is mainly used for image recognition and computer vision. In today’s living conditions, the impact and significance of CNN is becoming more and more important. In computer vision, CNN has an important position.
  • Random Fields for Image Registration

    Random Fields for Image Registration

    Computer Aided Medical Procedures Prof. Dr. Nassir Navab Dissertation Random Fields for Image Registration Benjamin M. Glocker Fakultät für Informatik Technische Universität München TECHNISCHE UNIVERSITÄT MÜNCHEN Computer Aided Medical Procedures & Augmented Reality / I16 Random Fields for Image Registration Benjamin M. Glocker Vollständiger Abdruck der von der Fakultät für Informatik der Technischen Universität München zur Erlangung des akademischen Grades eines Doktors der Naturwissenschaften (Dr. rer. nat.) genehmigten Dissertation. Vorsitzender: Univ.-Prof. Dr. Peter O. A. Struss Prüfer der Dissertation: 1. Univ.-Prof. Dr. Nassir Navab 2. Prof. Dr. Nikos Paragios, Ecole Centrale de Paris / Frankreich Die Dissertation wurde am 09.09.2010 bei der Technischen Universität München eingereicht und durch die Fakultät für Informatik am 16.05.2011 angenommen. Abstract Image registration is one of the key components in computer vision and medical image analysis. Motion compensation, multi-modal fusion, atlas matching, image stitching, or optical flow estimation are only some of the applications where efficient registration methods are needed. The task of registration is to recover a spatial transformation which aligns corresponding structures visible in the images. This is commonly formulated as an optimization problem based on an objective function which evaluates the quality of a transformation with respect to the image data and some prior information. So far, mainly classical continuous methods have been considered for the critical part of optimization. In this thesis, discrete labeling of random fields is introduced as a novel promising and powerful alternative. A general framework is derived which allows to represent both linear and non-linear image registration as labeling problems where random variables play the role of transformation parameters.