weixin_40763755的博客

Depth cameras have been exploited in computer vision for several years, but the high price and poor quality of such devices have limited their applicability. With the invention of the low-cost depth sensors such as Kinect and Time-of-Flight (TOF) cameras, high-resolution depth and visual (RGB) sensing have become available for widespread use as an off-the-shelf technology. The complementary nature of the synchronized depth and RGB information opens up new opportu- nities to solve fundamental problems in computer vision, including human pose estimation, activity recognition, object and people tracking, 3D mapping and localization, etc. Furthermore, the robustness gained with depth cameras allow us to take computer vision out of the lab and into real environments (e.g., people’s homes).

Robot Programming: A Guide to Controlling Autonomous Robots: Covers both ARM9 and ARM7 micro-controllers, including the newest LEGO Mindstorms EV3 and Wowee RS Media Robots.

welcome to Scientific Python and its community. If you’re a scientist who programs with Python, this practical guide, Elegant SciPy not only teaches you the fundamental parts of SciPy and libraries related to it, but also gives you a taste for beautiful, easy-to-read code that you can use in practice. You’ll learn how to write elegant code that’s clear, concise, and efficient at executing the task at hand. Explore the NumPy array, the data structure that underlies numerical scientific computation Use quantile normalization to ensure that measurements fit a specific distribution Represent separate regions in an image with a Region Adjacency Graph Convert temporal or spatial data into frequency domain data with the Fast Fourier Transform Solve sparse matrix problems, including image segmentations, with SciPy’s sparse module Perform linear algebra by using SciPy packages Explore image alignment (registration) with SciPy’s optimize module Process large datasets with Python data streaming primitives and the Toolz library Throughout the book, you’ll work with examples from the wider scientific Python ecosystem, using code that illustrates principles outlined in the book. Using actual scientific data, you’ll work on real-world problems with SciPy, NumPy, Pandas, scikit-image, and other Python libraries.