kinect中的新手问题 [英] newbie questions in kinect

问题描述

我参与了一个与为视障人士使用kinect相关的项目，我有一些问题

i'm involved in a project related to using kinect for visiually impaired people and i have some questions

1 - 使用RGB相机加入红外线的价值是多少传感器相机？我们不能单独使用红外热像仪或RGB吗？

1-what is the value added by using RGB camera to IR sensors camera ? can't we only use IR camera or RGB alone ?

2 - 如何重建3D模型？

2-how is the 3D model reconstructed ?

3 - 我可以使用几个现成的相机和声纳传感器来处理上面所述的应用吗？

3-can i just use couple of off the shelf cameras and sonar sensors for the application i'm working on stated above ?

4 - 以下术语如何相关（深度图 - 点云）？

4-how does the following terms are related (depth map - point cloud) ?

推荐答案

你的一些问题可能不是Kinect特定的，你会有向你的团队询问他们使用Kinect的原因。

some of your questions may not be Kinect specific and you will have to ask your team as to why they are using Kinect.

1。 Kinect可配置为提供红外或彩色图像。 IR数据被转换为基于该图像中的数据成像的深度。

1. Kinect can be configured to provide ir or color images. The IR data is converted into a depth imaged based in the data in that image.

2。 Kinect本身不会创建3D模型。有一个名为Kinect Fusion的工具包功能，它集成了深度数据，并使用体素构建了重建的内部表示。您可以在文档或白皮书中阅读有关Fusion的更多信息。

2. The Kinect itself does not create 3D models. There is a toolkit feature called Kinect Fusion that integrates the depth data and builds an internal representation of the reconstructed using voxels. You can read more on Fusion in the docs or the whitepapers.

3。问你的团队

4。点云由深度数据生成。是在空间中绘制的点x，y&n，z，表示在3d空间中的深度图像 

4. point clouds are generated by the depth data. The are points x,y plotted in space, z, that represent the depth image in 3d space 

这篇关于kinect中的新手问题的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！