scispace - formally typeset
Search or ask a question
Author

Sebastian Thrun

Other affiliations: University of Pittsburgh, ETH Zurich, Carnegie Mellon University  ...read more
Bio: Sebastian Thrun is an academic researcher from Stanford University. The author has contributed to research in topics: Mobile robot & Robot. The author has an hindex of 146, co-authored 434 publications receiving 98124 citations. Previous affiliations of Sebastian Thrun include University of Pittsburgh & ETH Zurich.


Papers
More filters
Proceedings ArticleDOI
13 Oct 1998
TL;DR: An approach to tracking planar surface patches over time using a technique from computer graphics, known as texture mapping, as the measurement model in an extended Kalman filter, which produces a super-resolved estimate of the texture present on the patch.
Abstract: We present an approach to tracking planar surface patches over time. In addition to tracking a patch with full six degrees of freedom, the algorithm also produces a super-resolved estimate of the texture present on the patch. This texture estimate is kept as an explicit model texture image which is refined over time. We then use it to infer the 3D motion of the patch from the image sequence. The main idea behind the approach is to use a technique from computer graphics, known as texture mapping, as the measurement model in an extended Kalman filter. We also calculate the partial derivative of this image formation process with respect to the 3D pose of the patch, which functions as the measurement Jacobian. The super-resolved estimate of the texture is obtained using the standard extended Kalman filter measurement update, with one essential approximation that makes this computationally feasible. The resulting equations are remarkably simple, yet lead to estimates that are properly super-resolved. In addition to developing the theory behind the approach, we also demonstrate both the tracking and the super-resolution aspect of the algorithm on real image sequences.

44 citations

Book ChapterDOI
01 Jan 2010
TL;DR: This chapter describes a new mesh-based performance capture algorithm that uses a combination of deformable surface and volume models for high-quality reconstruction of people in general apparel, i.e. also wide dresses and skirts.
Abstract: Nowadays, increasing performance of computing hardware makes it feasible to simulate ever more realistic humans even in real-time applications for the end-user. To fully capitalize on these computational resources, all aspects of the human, including textural appearance and lighting, and, most importantly, dynamic shape and motion have to be simulated at high fidelity in order to convey the impression of a realistic human being. In consequence, the increase in computing power is flanked by increasing requirements to the skills of the animators. In this chapter, we describe several recently developed performance capture techniques that enable animators to measure detailed animations from real world subjects recorded on multi-view video. In contrast to classical motion capture, performance capture approaches don’t only measure motion parameters without the use of optical markers, but also measure detailed spatio-temporally coherent dynamic geometry and surface texture of a performing subject. This chapter gives an overview of recent state-of-the-art performance capture approaches from the literature. The core of the chapter describes a new mesh-based performance capture algorithm that uses a combination of deformable surface and volume models for high-quality reconstruction of people in general apparel, i.e. also wide dresses and skirts. The chapter concludes with a discussion of the different approaches, pointers to additional literature and a brief outline of open research questions for the future.

44 citations

Patent
14 Dec 2007
TL;DR: In this paper, a location of a currently received image relative to a set of previously received images is indicated with reference to the indicated location, and adjustment information is indicated relative to an indicated position.
Abstract: Mosaicing methods and devices are implementing in a variety of manners. One such method is implemented for generation of a continuous image representation of an area from multiple images consecutively received from an image sensor. A location of a currently received image is indicated relative to the image sensor. A position of a currently received image relative to a set of previously received images is indicated with reference to the indicated location. The currently received image is compared to the set of previously received images as a function of the indicated position. Responsive to the comparison, adjustment information is indicated relative to the indicated position. The currently received image is merged with the set of previously received images to generate data representing a new set of images.

43 citations

Proceedings Article
01 Jul 1998
TL;DR: A gesture-based interface for human robot interaction is described, which enables people to instruct robots through easy-to-perform arm gestures, using a hybrid approach that integrates neural networks and template matching.
Abstract: For mobile robots to assist people in everyday life, they must be easy to instruct. This paper describes a gesture-based interface for human robot interaction, which enables people to instruct robots through easy-to-perform arm gestures. Such gestures might be static pose gestures, which involve only a specific configuration of the person's arm, or they might be dynamic motion gestures (such as waving). Gestures are recognized in real-time at approximate frame rate, using a hybrid approach that integrates neural networks and template matching. A fast, color-based tracking algorithm enables the robot to track and follow a person reliably through office environments with drastically changing lighting conditions. Results are reported in the context of an interactive clean-up task, where a person guides the robot to specific locations that need to be cleaned, and the robot picks up trash which it then delivers to the nearest trash-bin.

43 citations

Book ChapterDOI
18 Sep 2006
TL;DR: Insight is provided in the software architecture of Stanford's winning robot, which massively relied on machine learning and probabilistic modeling for sensor interpretation, and robot motion planning algorithms for vehicle guidance and control.
Abstract: The DARPA Grand Challenge has been the most significant challenge to the mobile robotics community in more than a decade. The challenge was to build an autonomous robot capable of traversing 132 miles of unrehearsed desert terrain in less than 10 hours. In 2004, the best robot only made 7.3 miles. In 2005, Stanford won the challenge and the $2M prize money by successfully traversing the course in less than 7 hours. This talk, delivered by the leader of the Stanford Racing Team, will provide insights in the software architecture of Stanford's winning robot. The robot massively relied on machine learning and probabilistic modeling for sensor interpretation, and robot motion planning algorithms for vehicle guidance and control. The speaker will explain some of the basic algorithms and share some of the excitement characterizing this historic event. He will also discuss the implications of this work for the future of the transportation.

41 citations


Cited by
More filters
Book
18 Nov 2016
TL;DR: Deep learning as mentioned in this paper is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts, and it is used in many applications such as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames.
Abstract: Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

38,208 citations

Journal ArticleDOI
TL;DR: This work proposes a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams, and Hofmann's aspect model.
Abstract: We describe latent Dirichlet allocation (LDA), a generative probabilistic model for collections of discrete data such as text corpora. LDA is a three-level hierarchical Bayesian model, in which each item of a collection is modeled as a finite mixture over an underlying set of topics. Each topic is, in turn, modeled as an infinite mixture over an underlying set of topic probabilities. In the context of text modeling, the topic probabilities provide an explicit representation of a document. We present efficient approximate inference techniques based on variational methods and an EM algorithm for empirical Bayes parameter estimation. We report results in document modeling, text classification, and collaborative filtering, comparing to a mixture of unigrams model and the probabilistic LSI model.

30,570 citations

Proceedings Article
03 Jan 2001
TL;DR: This paper proposed a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams, and Hof-mann's aspect model, also known as probabilistic latent semantic indexing (pLSI).
Abstract: We propose a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams [6], and Hof-mann's aspect model, also known as probabilistic latent semantic indexing (pLSI) [3]. In the context of text modeling, our model posits that each document is generated as a mixture of topics, where the continuous-valued mixture proportions are distributed as a latent Dirichlet random variable. Inference and learning are carried out efficiently via variational algorithms. We present empirical results on applications of this model to problems in text modeling, collaborative filtering, and text classification.

25,546 citations

Book
25 Oct 1999
TL;DR: This highly anticipated third edition of the most acclaimed work on data mining and machine learning will teach you everything you need to know about preparing inputs, interpreting outputs, evaluating results, and the algorithmic methods at the heart of successful data mining.
Abstract: Data Mining: Practical Machine Learning Tools and Techniques offers a thorough grounding in machine learning concepts as well as practical advice on applying machine learning tools and techniques in real-world data mining situations. This highly anticipated third edition of the most acclaimed work on data mining and machine learning will teach you everything you need to know about preparing inputs, interpreting outputs, evaluating results, and the algorithmic methods at the heart of successful data mining. Thorough updates reflect the technical changes and modernizations that have taken place in the field since the last edition, including new material on Data Transformations, Ensemble Learning, Massive Data Sets, Multi-instance Learning, plus a new version of the popular Weka machine learning software developed by the authors. Witten, Frank, and Hall include both tried-and-true techniques of today as well as methods at the leading edge of contemporary research. *Provides a thorough grounding in machine learning concepts as well as practical advice on applying the tools and techniques to your data mining projects *Offers concrete tips and techniques for performance improvement that work by transforming the input or output in machine learning methods *Includes downloadable Weka software toolkit, a collection of machine learning algorithms for data mining tasks-in an updated, interactive interface. Algorithms in toolkit cover: data pre-processing, classification, regression, clustering, association rules, visualization

20,196 citations

28 Jul 2005
TL;DR: PfPMP1)与感染红细胞、树突状组胞以及胎盘的单个或多个受体作用,在黏附及免疫逃避中起关键的作�ly.
Abstract: 抗原变异可使得多种致病微生物易于逃避宿主免疫应答。表达在感染红细胞表面的恶性疟原虫红细胞表面蛋白1(PfPMP1)与感染红细胞、内皮细胞、树突状细胞以及胎盘的单个或多个受体作用,在黏附及免疫逃避中起关键的作用。每个单倍体基因组var基因家族编码约60种成员,通过启动转录不同的var基因变异体为抗原变异提供了分子基础。

18,940 citations