|
所在平台: Coursera |
课程主页: https://www.coursera.org/learn/robotics-perception
课程评论：没有评论
课程名称：机器人学：感知 概述：机器人如何感知世界及自身运动，以完成导航和操控任务？本模块将研究如何将安装在机器人上的摄像头获取的图像和视频转换为特征和光流等表示。这些二维表示使我们能够提取出关于相机位置及机器人运动方向的三维信息。您将了解到，计算物体的三维姿态可以促进物体的抓取，而通过视觉里程计和基于地标的定位可以实现导航。 课程大纲： 1. **图像形成的几何**：欢迎来到《机器人学：感知》！课程将从计算机视觉中标准相机模型的教程开始。借助这些模型，我们能够以几何方式理解场景中的光是如何进入相机并投影到二维图像上的。通过数学定义这些模型，我们将准确理解三维点与图像点的对应关系，以及在三维环境中移动相机时图像的变化。稍后的模块将利用这些信息执行复杂的感知任务，如从视频重建三维场景。 2. **投影变换**：在掌握了相机模型后，我们将深入探讨透视投影的几何。我们将发现，这一投影是感知中的主要挑战，因为我们失去了一维无法直接观察。本模块将详细介绍投影变换的几个特性，如消失点，它们使我们能够推断超出基本相机模型的复杂信息。 3. **姿态估计**：在本模块中，我们将学习如何从两幅图像中提取特征及姿态估计。我们将学习如何找到图像中最显著的部分，并在多个帧（即视频序列）中跟踪这些部分。我们还将学习如何使用特征找到相机相对于另一个参考平面的位置信息，运用单应性技术。同时，我们将探索如何利用最小二乘法处理噪声特征点或使用RANSAC去除完全错误的特征点，从而提升技术的鲁棒性。 4. **多视图几何**：现在我们将利用从两视图几何中学到的知识，扩展到图像序列（如视频）。我们将解释图像中特征点之间的基本几何约束，即极几何约束，并学习如何使用它提取多个帧之间的相对姿态。最后，我们将整合这些信息，应用于运动结构（Structure from Motion），计算相机在多个帧中的轨迹和地图，并利用束调整（Bundle adjustment）优化我们的估计。
Name:Geometry of Image Formation
Description: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.
Name:Projective Transformations
Description: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.
Name:Pose Estimation
Description: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.
Name:Multi-View Geometry
Description: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.
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.
