检索结果-内蒙古大学图书馆

Indoor Staircase Detection for Supporting Security Systems in Autonomous Smart Wheelchairs Based on Deep Analysis of the Co-Occurrence Matrix

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Utaminingrum, Fitri Wahyudi, Slamet Karim, Corina Johan, Ahmad Wali Satria Bahari Shih, Timothy K. Lin, Chih-Yang Computer Vision Research Groups Faculty of Computer Science Brawijaya University Malang65145 Indonesia Mechanical Department Brawijaya University Malang65145 Indonesia Mathematics Department Brawijaya University Malang65145 Indonesia Department of Informatics Institut Teknologi Telkom Purwokerto Surabaya65145 Indonesia Department of Computer Science and Information Engineering National Central University Taoyuan City32001 Taiwan Computer Vision and Interactive Technology Department of Electrical Engineering Yuan-Ze University Taoyuan City32003 Taiwan

Detection of descending stairs and floors is important in implementing autonomous systems in smart wheelchairs. Suppose the obstacle detection system applied to wheelchairs cannot properly detect the descending stairs. In that case, it will have fatal consequences for its users, one of which is an injury or even the worst impact can result in death. Hence, we need an algorithm that has good accuracy in detecting obstacles in descending stairs and a fast-computing time so that the system's response for braking on a wheelchair can be made immediately. In this study, we use the Gray Level Co-Occurrence Matrix (GLCM) method for the basis of feature ***, we analyzed the performance of several types of binary classification methods, including Naive Bayes, Decision Tree, Logistic Regression, k-Nearest Neighbors (k-NN), and Support Vector Machines (SVM). Based on the results obtained, the Decision Tree has the highest accuracy value compared to the others. The Accuracy value is 94%, and the computing time is 0.01299 seconds. These results were obtained in a combination of the GLCM method, the distance is equal to 2, and the angle is 45o. © 2023, The Authors. All rights reserved.

关键词： Stairs

Deep interactive Segmentation of Medical Images: A Systematic Review and Taxonomy

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Marinov, Zdravko Jäger, Paul F. Egger, Jan Kleesiek, Jens Stiefelhagen, Rainer The Computer Vision for Human-Computer Interaction Lab Department of Informatics Karlsruhe Institute of Technology Adenauerring 10 Karlsruhe76131 Germany Girardetstraße 2 Essen45131 Germany Heidelberg Interactive Machine Learning Group Im Neuenheimer Feld 223 Heidelberg69120 Germany The Helmholtz Imaging DKFZ Im Neuenheimer Feld 223 Heidelberg69120 Germany

interactive segmentation is a crucial research area in medical image analysis aiming to boost the efficiency of costly annotations by incorporating human feedback. This feedback takes the form of clicks, scribbles, or masks and allows for iterative refinement of the model output so as to efficiently guide the system towards the desired behavior. In recent years, deep learning-based approaches have propelled results to a new level causing a rapid growth in the field with 121 methods proposed in the medical imaging domain alone. In this review, we provide a structured overview of this emerging field featuring a comprehensive taxonomy, a systematic review of existing methods, and an in-depth analysis of current practices. Based on these contributions, we discuss the challenges and opportunities in the field. For instance, we find that there is a severe lack of comparison across methods which needs to be tackled by standardized baselines and benchmarks. Appendixes are here. © 2023, CC BY.

关键词： Medical imaging

MultiAR: A Multi-User Augmented Reality Platform for Biomedical Education

学校读者我要写书评

暂无评论

MultiAR: A Multi-User Augmented Reality Platform for Biomedi...

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Markus Perz Gijs Luijten Jens Kleesiek Dieter Schmalstieg Jan Egger Christina Gsaxner Institute of Computer Graphics and Vision Graz University of Technology Graz Austria Institute for Artificial Intelligence in Medicine University Medicine Essen Essen Germany Cancer Research Center Cologne Essen West German Cancer Center Essen Germany Institute for Visualization and Interactive Systems University of Stuttgart Stuttgart Germany Virtual and Extended Reality in Medicine (ZvRM) University Hospital Essen Essen Germany

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

This paper addresses the growing integration of Augmented Reality (AR) in biomedical sciences, emphasizing collaborative learning experiences. We present MultiAR, a versatile, domain-specific platform enabling multi-user interactions in AR for biomedical education. Unlike platform-specific solutions, MultiAR supports various AR devices, including handheld and head-mounted options. The framework extends across domains, augmenting biomedical education applications with collaborative capabilities. We define essential requirements for a multi-user AR framework in education, detail MultiAR’s design and implementation, and comprehensively evaluate it using anatomy education examples. Quantitative and qualitative analyses, covering system performance, accuracy metrics, and a user study with 20 participants, highlight the urgent need for a tailored collaborative AR platform in biomedical education. Results underscore enthusiasm for collaborative AR technology, endorsing MultiAR as an accessible, versatile solution for developers and end-users in biomedical education.

关键词： Measurement Accuracy Federated learning System performance Education Collaboration Anatomy Engineering in medicine and biology Augmented reality

Efficient Deep Models for Real-Time 4K Image Super-Resolution. NTIRE 2023 Benchmark and Report

学校读者我要写书评

暂无评论

Efficient Deep Models for Real-Time 4K Image Super-Resolutio...

2023 IEEE/CVF Conference on computer vision and Pattern Recognition Workshops, CVPRW 2023

作者： Conde, Marcos V. Zamfir, Eduard Timofte, Radu Motilla, Daniel Liu, Cen Zhang, Zexin Peng, Yunbo Lin, Yue Guo, Jiaming Zou, Xueyi Chen, Yuyi Liu, Yi Hao, Jia Yan, Youliang Zhang, Yuanfan Li, Gen Sun, Lei Kong, Lingshun Bai, Haoran Pan, Jinshan Dong, Jiangxin Tang, Jinhui Ayazoglu, Mustafa Bilecen, Bahri Batuhan Li, Mingxi Zhang, Yuhang Fan, Xianjun Sheng, Yankai Sun, Long Liu, Zibin Gou, Weiran Li, Shaoqing Yi, Ziyao Xiang, Yan Kong, Dehui Xu, Ke Gankhuyag, Ganzorig Yoon, Kihwan Zhang, Jin Yu, Gaocheng Zhang, Feng Wang, Hongbin Zhou, Zhou Chao, Jiahao Gao, Hongfan Gong, Jiali Yang, Zhengfeng Zeng, Zhenbing Chen, Chengpeng Guo, Zichao Park, Anjin Liu, Yuqing Jia, Qi Yu, Hongyuan Yin, Xuanwu Zuo, Kunlong Zhang, Dongyang Fu, Ting Cheng, Zhengxue Zhu, Shiai Zhou, Dajiang Yu, Weichen Ge, Lin Dong, Jiahua Zou, Yajun Wu, Zhuoyuan Han, Binnan Zhang, Xiaolin Zhang, Heng Shao, Ben Zheng, Shaolong Yin, Daheng Chen, Baijun Liu, Mengyang Nistor, Marian-Sergiu Chen, Yi-Chung Huang, Zhi-Kai Chiang, Yuan-Chun Chen, Wei-Ting Yang, Hao-Hsiang Chang, Hua-En Chen, I-Hsiang Hsieh, Chia-Hsuan Kuo, Sy-Yen Vo, Tu Yan, Qingsen Zhu, Yun Su, Jinqiu Zhang, Yanning Zhang, Cheng Luo, Jiaying Cho, Youngsun Lee, Nakyung Computer Vision Lab CAIDAS IFI University of Würzburg Germany Sony Interactive Entertainment CA United States Huawei Technologies Co. Ltd. China NetEase Games AI Lab Nanjing University of Science and Technology China Tencent China Attrsense Korea Republic of Sanechips Co Ltd Ant Group China East China Normal University China Shopee Dalian University of Technology Xiaomi Inc. China China Zhejiang Dahua Technology Co. Ltd. China Multimedia Department Xiaomi Inc. China Korea Photonic Technology Institute Korea Republic of School of Computer Science and Engineering Southeast University China University Al. I. Cuza Iasi Romania Graduate Institute of Electronics Engineering National Taiwan University Taiwan Department of Electrical Engineering National Taiwan University Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan ServiceNow United States Northwestern Polytechnical University China KC Machine Learning Lab CJ OliveNetworks AI Research

ISBN: (纸本)9798350302493

This paper introduces a novel benchmark for efficient up-scaling as part of the NTIRE 2023 Real-Time Image Super-Resolution (RTSR) Challenge, which aimed to upscale images from 720p and 1080p resolution to native 4K (×2 and ×3 factors) in real-time on commercial GPUs. For this, we use a new test set containing diverse 4K images ranging from digital art to gaming and photography. We assessed the methods devised for 4K SR by measuring their runtime, parameters, and FLOPs, while ensuring a minimum PSNR fidelity over Bicubic interpolation. Out of the 170 participants, 25 teams contributed to this report, making it the most comprehensive benchmark to date and showcasing the latest advancements in real-time SR. © 2023 IEEE.

关键词： Program processors

Deep learning - A first meta-survey of selected reviews across scientific disciplines, their commonalities, challenges and research impact

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Egger, Jan Pepe, Antonio Gsaxner, Christina Jin, Yuan Li, Jianning Kern, Roman Institute of Computer Graphics and Vision Faculty of Computer Science and Biomedical Engineering Graz University of Technology Graz Austria Computer Algorithms for Medicine Laboratory Graz Austria Department of Oral and Maxillofacial Surgery Medical University of Graz Graz Austria University Medicine Essen Essen Germany Research Center for Connected Healthcare Big Data Zhejiang Lab Zhejiang Hangzhou China Research Unit Experimental Neurotraumatology Department of Neurosurgery Medical University of Graz Graz Austria Knowledge Discovery Know-Center Graz Austria Institute of Interactive Systems and Data Science Graz University of Technology Graz Austria

Deep learning belongs to the field of artificial intelligence, where machines perform tasks that typically require some kind of human intelligence. Deep learning tries to achieve this by drawing inspiration from the learning of a human brain. Similar to the basic structure of a brain, which consists of (billions of) neurons and connections between them, a deep learning algorithm consists of an artificial neural network, which resembles the biological brain structure. Mimicking the learning process of humans with their senses, deep learning networks are fed with (sensory) data, like texts, images, videos or sounds. These networks outperform the state-of-the-art methods in different tasks and, because of this, the whole field saw an exponential growth during the last years. This growth resulted in way over 10,000 publications per year in the last years. For example, the search engine PubMed alone, which covers only a sub-set of all publications in the medical field, provides already over 11,000 results in Q3 2020 for the search term 'deep learning', and around 90% of these results are from the last three years. Consequently, a complete overview over the field of deep learning is already impossible to obtain and, in the near future, it will potentially become difficult to obtain an overview over a subfield. However, there are several review articles about deep learning, which are focused on specific scientific fields or applications, for example deep learning advances in computer vision or in specific tasks like object detection. With these surveys as a foundation, the aim of this contribution is to provide a first high-level, categorized meta-survey of selected reviews on deep learning across different scientific disciplines and outline the research impact that they already have during a short period of time. The categories (computer vision, language processing, medical informatics and additional works) have been chosen according to the underlying data sources (image,

关键词： Surveys

Using phase instead of optical flow for action recognition

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Hommos, Omar Pintea, Silvia L. Mettes, Pascal S.M. van Gemert, Jan C. Computer Vision Lab Delft University of Technology Netherlands Intelligent Sensory Interactive Systems University of Amsterdam Netherlands

Currently, the most common motion representation for action recognition is optical flow. Optical flow is based on particle tracking which adheres to a Lagrangian perspective on dynamics. In contrast to the Lagrangian perspective, the Eulerian model of dynamics does not track, but describes local changes. For video, an Eulerian phase-based motion representation, using complex steerable filters, has been successfully employed recently for motion magnification and video frame interpolation. Inspired by these previous works, here, we proposes learning Eulerian motion representations in a deep architecture for action recognition. We learn filters in the complex domain in an end-to-end manner. We design these complex filters to resemble complex Gabor filters, typically employed for phase-information extraction. We propose a phase-information extraction module, based on these complex filters, that can be used in any network architecture for extracting Eulerian representations. We experimentally analyze the added value of Eulerian motion representations, as extracted by our proposed phase extraction module, and compare with existing motion representations based on optical flow, on the UCF101 dataset. Copyright © 2018, The Authors. All rights reserved.

关键词： Optical flows

Why is the Winner the Best?

学校读者我要写书评

暂无评论

Why is the Winner the Best?

Conference on computer vision and Pattern Recognition (CVPR)

作者： M. Eisenmann A. Reinke V. Weru M. D. Tizabi F. Isensee T. J. Adler S. Ali V. Andrearczyk M. Aubreville U. Baid S. Bakas N. Balu S. Bano J. Bernal S. Bodenstedt A. Casella V. Cheplygina M. Daum M. De Bruijne A. Depeursinge R. Dorent J. Egger D. G. Ellis S. Engelhardt M. Ganz N. Ghatwary G. Girard P. Godau A. Gupta L. Hansen K. Harada M. Heinrich N. Heller A. Hering A. Huaulmé P. Jannin A. E. Kavur O. Kodym M. Kozubek J. Li H. Li J. Ma C. Martín-Isla B. Menze A. Noble V. Oreiller N. Padoy S. Pati K. Payette T. Rädsch J. Rafael-Patiño V. Singh Bawa S. Speidel C. H. Sudre K. Van Wijnen M. Wagner D. Wei A. Yamlahi M. H. Yap C. Yuan M. Zenk A. Zia D. Zimmerer D. Aydogan B. Bhattarai L. Bloch R. Brüngel J. Cho C. Choi Q. Dou I. Ezhov C. M. Friedrich C. Fuller R. R. Gaire A. Galdran Á. García Faura M. Grammatikopoulou S. Hong M. Jahanifar I. Jang A. Kadkhodamohammadi I. Kang F. Kofler S. Kondo H. Kuijf M. Li M. Luu T. Martinčič P. Morais M. A. Naser B. Oliveira D. Owen S. Pang J. Park S. Park S. Płotka E. Puybareau N. Rajpoot K. Ryu N. Saeed A. Shephard P. Shi D. Štepec R. Subedi G. Tochon H. R. Torres H. Urien J. L. Vilaça K. A. Wahid H. Wang J. Wang L. Wang X. Wang B. Wiestler M. Wodzinski F. Xia J. Xie Z. Xiong S. Yang Y. Yang Z. Zhao K. Maier-Hein P. F. Jäger A. Kopp-Schneider L. Maier-Hein Division of Intelligent Medical Systems German Cancer Research Center (DKFZ) Heidelberg Germany Helmholtz Imaging German Cancer Research Center (DKFZ) Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany Division of Biostatistics German Cancer Research Center (DKFZ) Heidelberg Germany Division of Medical Image Computing German Cancer Research Center (DKFZ) Heidelberg Germany Faculty of Engineering and Physical Sciences School of Computing University of Leeds Leeds UK Institute of Informatics School of Management HES-SO Valais-Wallis University of Applied Sciences and Arts Western Switzerland Sierre Switzerland Department of Nuclear Medicine and Molecular Imaging Lausanne University Hospital Lausanne Switzerland Technische Hochschule Ingolstadt Ingolstadt Germany Center for Artificial Intelligence and Data Science for Integrated Diagnostics (AI2D) and Center for Biomedical Image Computing and Analytics (CBICA) University of Pennsylvania Philadelphia PA USA Department of Pathology and Laboratory Medicine Perelman School of Medicine University of Pennsylvania Philadelphia PA USA Department of Radiology Perelman School of Medicine University of Pennsylvania Philadelphia PA USA Department of Radiology University of Washington Seattle WA USA Department of Computer Science Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS) University College London London UK Universitat Autònoma de Barcelona & Computer Vision Center Barcelona Spain Division of Translational Surgical Oncology National Center for Tumor Diseases (NCT/UCC) Dresden Dresden Germany Department of Advanced Robotics Istituto Italiano di Tecnologia Italy Department of Electronics Information and Bioengineering Politecnico di Milano Milan Italy IT University of Copenhagen Copenhagen Denmark Department of General Visceral and Transplantation Surgery Heidelberg University Hospital Heidelberg Germany Department of Radiology and Nuc

International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from these competitions. Do they really generate scientific progress? What are common and successful participation strategies? What makes a solution superior to a competing method? To address this gap in the literature, we performed a multicenter study with all 80 competitions that were conducted in the scope of IEEE ISBI 2021 and MICCAI 2021. Statistical analyses performed based on comprehensive descriptions of the submitted algorithms linked to their rank as well as the underlying participation strategies revealed common characteristics of winning solutions. These typically include the use of multi-task learning (63%) and/or multi-stage pipelines (61%), and a focus on augmentation (100%), image preprocessing (97%), data curation (79%), and post-processing (66%). The “typical” lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning. Two core general development strategies stood out for highly-ranked teams: the reflection of the metrics in the method design and the focus on analyzing and handling failure cases. According to the organizers, 43% of the winning algorithms exceeded the state of the art but only 11% completely solved the respective domain problem. The insights of our study could help researchers (1) improve algorithm development strategies when approaching new problems, and (2) focus on open research questions revealed by this work.

关键词：

Biomedical image analysis competitions: The state of current participation practice

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Eisenmann, Matthias Reinke, Annika Weru, Vivienn Tizabi, Minu Dietlinde Isensee, Fabian Adler, Tim J. Godau, Patrick Cheplygina, Veronika Kozubek, Michal Maier-Hein, Klaus Jäger, Paul F. Kopp-Schneider, Annette Maier-Hein, Lena Ali, Sharib Gupta, Anubha Kybic, Jan Noble, Alison de Solórzano, Carlos Ortiz Pachade, Samiksha Petitjean, Caroline Sage, Daniel Wei, Donglai Wilden, Elizabeth Alapatt, Deepak Andrearczyk, Vincent Baid, Ujjwal Bakas, Spyridon Balu, Niranjan Bano, Sophia Bawa, Vivek Singh Bernal, Jorge Bodenstedt, Sebastian Casella, Alessandro Choi, Jinwook Commowick, Olivier Daum, Marie Depeursinge, Adrien Dorent, Reuben Egger, Jan Eichhorn, Hannah Engelhardt, Sandy Ganz, Melanie Girard, Gabriel Hansen, Lasse Heinrich, Mattias Heller, Nicholas Hering, Alessa Huaulmé, Arnaud Kim, Hyunjeong Li, Hongwei Bran Landman, Bennett Li, Jianning Ma, Jun Martel, Anne Martín-Isla, Carlos Menze, Bjoern Nwoye, Chinedu Innocent Oreiller, Valentin Padoy, Nicolas Pati, Sarthak Payette, Kelly Sudre, Carole van Wijnen, Kimberlin Vardazaryan, Armine Vercauteren, Tom Wagner, Martin Wang, Chuanbo Yap, Moi Hoon Yu, Zeyun Yuan, Chun Zenk, Maximilian Zia, Aneeq Zimmerer, David Bao, Rina Choi, Chanyeol Cohen, Andrew Dzyubachyk, Oleh Galdran, Adrian Gan, Tianyuan Guo, Tianqi Gupta, Pradyumna Haithami, Mahmood Ho, Edward Jang, Ikbeom Li, Zhili Luo, Zhengbo Lux, Filip Makrogiannis, Sokratis Müller, Dominik Oh, Young-Tack Pang, Subeen Pape, Constantin Polat, Gorkem Reed, Charlotte Rosalie Ryu, Kanghyun Scherr, Tim Thambawita, Vajira Wang, Haoyu Wang, Xinliang Xu, Kele Yeh, Hung Yeo, Doyeob Yuan, Yixuan Zeng, Yan Zhao, Xin Abbing, Julian Adam, Jannes Adluru, Nagesh Agethen, Niklas Ahmed, Salman Al Khalil, Yasmina Alenyà, Mireia Alhoniemi, Esa An, Chengyang Arega, Tewodros Weldebirhan Avisdris, Netanell Aydogan, Dogu Baran Bai, Yingbin Calisto, Maria Baldeon Basaran, Berke Doga Beetz, Marcel Bian, Hao Blansit, Kevin Bloch, Louise Bohnsack, Robert Bosticardo, Sara Breen, Jack Brudfors, Mikael Brüngel, Raphael Cabezas, Mariano Cacciola, Alb Heidelberg Division of Intelligent Medical Systems Germany Heidelberg HI Helmholtz Imaging Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany Heidelberg Division of Biostatistics Germany Heidelberg Division of Medical Image Computing Germany Heidelberg HI Applied Vision Lab Germany IT University of Copenhagen Copenhagen Denmark Centre for Biomedical Image Analysis Masaryk University Brno Czech Republic Heidelberg Interactive Machine Learning Group Germany Faculty of Mathematics and Computer Science and Medical Faculty Heidelberg University Heidelberg Germany NCT Heidelberg DKFZ University Hospital Heidelberg Germany School of Computing University of Leeds Leeds United Kingdom SBILab Department of ECE IIIT-Delhi India Faculty of Electrical Engineering Czech Technical University Prague Czech Republic Institute of Biomedical Engineering University of Oxford United Kingdom Center for Applied Medical Research Pamplona Spain Shri Guru Gobind Singhji Institute of Engineering and Technology Maharashtra Nanded India Université de Rouen Normandie France Lausanne Switzerland School of Engineering and Applied Science Harvard University United States ICube University of Strasbourg CNRS France Institute of Informatics School of Management HES-SO Valais-Wallis University of Applied Sciences and Arts Western Switzerland Techno-Pôle 3 Sierre3960 Switzerland Department of Nuclear Medicine and Molecular Imaging Lausanne University Hospital Rue du Bugnon 46 LausanneCH-1011 Switzerland University of Pennsylvania PhiladelphiaPA United States Department of Radiology University of Washington United States Wellcome EPSRC Centre for Interventional and Surgical Sciences University College London London United Kingdom Visual Artificial Intelligence Lab Oxford Brookes University Oxford United Kingdom Universitat Autònoma de Barcelona & Computer Vision Center Spain Dresden Fetscherstraße 74 PF 64 Dresden01307 Germany

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps. © 2022, CC BY.

关键词： Benchmarking

Learning to Match Aerial Images with Deep Attentive Architectures

学校读者我要写书评

暂无评论

Learning to Match Aerial Images with Deep Attentive Architec...

IEEE Conference on computer vision and Pattern Recognition

作者： Hani Altwaijry Eduard Trulls James Hays Pascal Fua Serge Belongie Department of Computer Science Cornell University Computer Vision Laboratory Ecole Polytechnique Federale de Lausanne (EPFL) School of Interactive Computing College of Computing Georgia Institute of Technology

ISBN: (纸本)9781467388528

Image matching is a fundamental problem in computer vision. In the context of feature-based matching, SIFT and its variants have long excelled in a wide array of applications. However, for ultra-wide baselines, as in the case of aerial images captured under large camera rotations, the appearance variation goes beyond the reach of SIFT and RANSAC. In this paper we propose a data-driven, deep learning-based approach that sidesteps local correspondence by framing the problem as a classification task. Furthermore, we demonstrate that local correspondences can still be useful. To do so we incorporate an attention mechanism to produce a set of probable matches, which allows us to further increase performance. We train our models on a dataset of urban aerial imagery consisting of 'same' and 'different' pairs, collected for this purpose, and characterize the problem via a human study with annotations from Amazon Mechanical Turk. We demonstrate that our models outperform the state-of-the-art on ultra-wide baseline matching and approach human accuracy.

关键词： Neural networks computer vision computer architecture Training Feature extraction Cameras Distortion