Método genérico para estimação e modelagem do erro RMS em dados de profundidade de sensores para visão 3D
In the artificial vision are used several devices like MS Kinect v1 / v2, the stereo cameras PG Bumblebee XB3 and Stereolabs ZED, among others. Because they are all devices that estimate depth data, they may contain errors. In this work, we present the design and implementation of a generic metho...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | masterThesis |
| Language: | por |
| Published: |
Brasil
|
| Subjects: | |
| Online Access: | https://repositorio.ufrn.br/jspui/handle/123456789/24331 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In the artificial vision are used several devices like MS Kinect v1 / v2, the stereo
cameras PG Bumblebee XB3 and Stereolabs ZED, among others. Because they are all
devices that estimate depth data, they may contain errors. In this work, we present the
design and implementation of a generic method for estimating the RMS error in depth
data provided by any device, capable of generating data of type RGB-D, that is, an image
and a depth map Same time. To verify the method was built an embedded system based
on the NVIDIA Jetson TK1 and three sensors, the two versions of MS Kinect and the
ZED stereo camera. At the moment of the data collection, the mathematical models of
the RMS error were established for each device and, at the end, an analysis was made of
the accuracy of each one. |
|---|