Free Trial

Safari Books Online is a digital library providing on-demand subscription access to thousands of learning resources.

  • Create BookmarkCreate Bookmark
  • Create Note or TagCreate Note or Tag
  • PrintPrint
Share this Page URL
Help

CHAPTER 8: Point Clouds, Part 2

C H A P T E R  8

Point Clouds, Part 2

This chapter builds on what you learned about point clouds and the Kinect to explore more advanced 3-D concepts. We will extend our methods to handle more than one image at the time. There are many things we could do with a point cloud, and in this chapter, we will explore three areas:

  • Registration
  • Simultaneous localization and mapping (SLAM)
  • Surface reconstruction

Constructing a point cloud from the depth and color images of the Kinect is only the first step. For most applications, we must still do some processing to be able to use the point cloud. So far, the point clouds we’ve constructed from each frame are independent from each other. It would be very useful if we could relate the different point clouds. For example, if one frame sees the front and left walls of a room and another frame sees the front and right walls, it would be nice to merge the two point clouds and have a single point cloud with all three walls. Finding the transformation that aligns the two point clouds is known as registration.


  

You are currently reading a PREVIEW of this book.

                                                                                                                    

Get instant access to over $1 million worth of books and videos.

  

Start a Free 10-Day Trial


  
  • Safari Books Online
  • Create BookmarkCreate Bookmark
  • Create Note or TagCreate Note or Tag
  • PrintPrint