How can robots perceive the world and their own movements so that they accomplish navigation and manipulation tasks? In this module, we will study how images and videos acquired by cameras mounted on robots are transformed into representations like features and optical flow. Such 2D representations allow us then to extract 3D information about where the camera is and in which direction the robot moves. You will come to understand how grasping objects is facilitated by the computation of 3D posing of objects and navigation can be accomplished by visual odometry and landmark-based localization.
oferecido por
Programa de cursos integrados RobóticaUniversidade da PensilvâniaInformações sobre o curso
30,619 visualizações recentes
Resultados de carreira do aprendiz
40%
comecei uma nova carreira após concluir estes cursos
29%
consegui um benefício significativo de carreira com este curso
Certificados compartilháveis
Tenha o certificado após a conclusão
100% on-line
Comece imediatamente e aprenda em seu próprio cronograma.
Curso 4 de 6 no
Prazos flexíveis
Redefinir os prazos de acordo com sua programação.
Nível intermediário
Aprox. 33 horas para completar
Inglês
Legendas: Francês, Português (Brasil), Russo, Inglês, Espanhol
Habilidades que você terá
Computer VisionEstimationRandom Sample Consensus (Ransac)Geometry
Resultados de carreira do aprendiz
40%
comecei uma nova carreira após concluir estes cursos
29%
consegui um benefício significativo de carreira com este curso
Certificados compartilháveis
Tenha o certificado após a conclusão
100% on-line
Comece imediatamente e aprenda em seu próprio cronograma.
Curso 4 de 6 no
Prazos flexíveis
Redefinir os prazos de acordo com sua programação.
Nível intermediário
Aprox. 33 horas para completar
Inglês
Legendas: Francês, Português (Brasil), Russo, Inglês, Espanhol
oferecido por
Universidade da Pensilvânia
The University of Pennsylvania (commonly referred to as Penn) is a private university, located in Philadelphia, Pennsylvania, United States. A member of the Ivy League, Penn is the fourth-oldest institution of higher education in the United States, and considers itself to be the first university in the United States with both undergraduate and graduate studies.
Programa - O que você aprenderá com este curso
10 horas para concluir
Geometry of Image Formation
Welcome to Robotics: Perception! We will begin this course with a tutorial on the standard camera models used in computer vision. These models allow us to understand, in a geometric fashion, how light from a scene enters a camera and projects onto a 2D image. By defining these models mathematically, we will be able understand exactly how a point in 3D corresponds to a point in the image and how an image will change as we move a camera in a 3D environment. In the later modules, we will be able to use this information to perform complex perception tasks such as reconstructing 3D scenes from video.
10 horas para concluir
15 vídeos (Total 180 mín.), 1 leitura, 9 testes
15 videos
Introduction10min
Camera Modeling10min
Single View Geometry14min
More on Perspective Projection8min
Glimpse on Vanishing Points10min
Perspective Projection I14min
Perspective Projection II14min
Point-Line Duality8min
Rotations and Translations18min
Pinhole Camera Model10min
Focal Length and Dolly Zoom Effect8min
Intrinsic Camera Parameter13min
3D World to First Person Transformation13min
How to Compute Intrinsics from Vanishing Points12min
Camera Calibration11min
1 leituras
Setting up MATLAB10min
8 exercícios práticos
Introduction30min
Vanishing Points30min
Perspective Projection30min
Rotations and Translations30min
Dolly Zoom30min
Feeling of Camera Motion30min
How to Compute Intrinsics from Vanishing Points30min
Camera Calibration30min
6 horas para concluir
Projective Transformations
Now that we have a good camera model, we will explore the geometry of perspective projections in depth. We will find that this projection is the cause of the main challenge in perception, as we lose a dimension that we can no longer directly observe. In this module, we will learn about several properties of projective transformations in depth, such as vanishing points, which allow us to infer complex information beyond our basic camera model.
6 horas para concluir
5 vídeos (Total 69 mín.)
5 videos
Compute Projective Transformations13min
Projective Transformations and Vanishing Points6min
Cross Ratios and Single View Metrology13min
Two View Soccer Metrology11min
4 exercícios práticos
Homogeneous Coordinates30min
Projective Transformations30min
Vanishing Points30min
Cross Ratios and Single View Metrology30min
8 horas para concluir
Pose Estimation
In this module we will be learning about feature extraction and pose estimation from two images. We will learn how to find the most salient parts of an image and track them across multiple frames (i.e. in a video sequence). We will then learn how to use features to find the position of the camera with respect to another reference frame on a plane using Homographies. We will also learn about how to make these techniques more robust, using least squares to hand noisy feature points or RANSAC to remove completely erroneous feature points.
8 horas para concluir
8 vídeos (Total 126 mín.)
8 videos
Visual Features23min
Singular Value Decomposition30min
RANSAC: Random Sample Consensus I13min
Where am I? Part 116min
Where am I? Part 213min
Pose from 3D Point Correspondences: The Procrustes Problem9min
Pose from Projective Transformations8min
Pose from Point Correspondences P3P10min
5 exercícios práticos
Visual Features30min
Singular Value Decomposition30min
RANSAC30min
3D-3D Pose30min
Pose Estimation30min
9 horas para concluir
Multi-View Geometry
Now we will use what we learned from two view geometry and extend it to sequences of images, such as a video. We will explain the fundamental geometric constraints between point features in images, the Epipolar constraint, and learn how to use it to extract the relative poses between multiple frames. We will finish by combining all this information together for the application of Structure from Motion, where we will compute the trajectory of a camera and a map throughout many frames and refine our estimates using Bundle adjustment.
9 horas para concluir
14 vídeos (Total 221 mín.)
14 videos
Epipolar Geometry I23min
Epipolar Geometry II14min
Epipolar Geometry III24min
RANSAC: Random Sample Consensus II6min
Nonlinear Least Squares I3min
Nonlinear Least Squares II6min
Nonlinear Least Squares III13min
Optical Flow: 2D Point Correspondences19min
3D Velocities from Optical Flow16min
3D Motion and Structure from Multiple Views18min
Visual Odometry19min
Bundle Adjustment I17min
Bundle Adjustment II18min
Bundle Adjustment III17min
4 exercícios práticos
Epipolar Geometry30min
Nonlinear Least Squares30min
3D Velocities from Optical Flow30min
Bundle Adjustment30min
Avaliações
Principais avaliações do ROBOTICS: PERCEPTION
por AS8 de Nov de 2019
The content is quite useful but the teaching can be improved upon through shorter videos and more animations instead of hand gestures (or static images) to explain mathematical derivations.
por SG16 de Jun de 2017
The content is not very easy to understand because the lecture speaks very fast and the document is not very sufficient. But in all, the content is good, help me with my research.
por DY27 de Mar de 2020
The concepts were explained very well and clearly. The last week content seemed a bit complicated to follow, but it was not unsolvable. I enjoyed the course. Thank you!
por SK31 de Mar de 2018
Outstanding Course! I could always count on Prof.Jianbo to crunch some of the most complex and confusing parts of the course into a much easier understandable language.
Sobre Programa de cursos integrados Robótica
The Introduction to Robotics Specialization introduces you to the concepts of robot flight and movement, how robots perceive their environment, and how they adjust their movements to avoid obstacles, navigate difficult terrains and accomplish complex tasks such as construction and disaster recovery. You will be exposed to real world examples of how robots have been applied in disaster situations, how they have made advances in human health care and what their future capabilities will be. The courses build towards a capstone in which you will learn how to program a robot to perform a variety of movements such as flying and grasping objects.
Perguntas Frequentes – FAQ
Quando terei acesso às palestras e às tarefas?
O que recebo ao me inscrever nesta Especialização?
Is financial aid available?
Ganharei créditos universitários por concluir o curso?
Mais dúvidas? Visite o Central de Ajuda ao Aprendiz.
