4.2 B. EuRoC Dataset | EuRoC 数据集


table_2

image copy right belongs to Raúl Mur-Artal and Juan D. Tardós. ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras. ArXiv preprint arXiv:1610.06475

图像摘录自ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras. ArXiv preprint arXiv:1610.06475

表2 EuRoC数据集。平移的最小均方误差比较(米)。


4.2.1 paragraph

The recent EuRoC dataset [21] contains 11 stereo sequences recorded from a micro aerial vehicle (MAV) flying around two different rooms and a large industrial environment.

EuRoC数据集包含了11个双目的序列,通过一个微型飞行器(MAV)采集到的数据,飞行在两个不同的房间和大量的工业环境。

The stereo sensor has a 11\sim 11 cm baseline and provides WVGA images at 20Hz.

这个双目传感器有一个小于11cm的基线和能够提供20HZ的WVGA格式的图像,

The sequences are classified as easyeasy , mediummedium and difficultdifficult depending on MAV’s speed, illumination and scene texture.

这个序列分成,简单中等、和困难,这取决于MAV(微型飞行器)的速度,照明和场景的纹理。

In all sequences the MAV revisits the environment and ORB-SLAM2 is able to reuse its map, closing loops when necessary.

在所有的序列当中,MAV(微型飞行器)再次访问这个环境的时候,ORB-SLAM2能够重用地图,回环检测。

Table II shows absolute translation RMSE of ORB-SLAM2 for all sequences, comparing to Stereo LSD-SLAM, for the results provided in [11].

这个表格2显示的是ORB-SLAM2的最小均方误差的绝对值变换,对于所有序列而言。

ORB-SLAM2 achieves a localization precision of a few centimeters and is more accurate than Stereo LSD-SLAM.

相比较对双目的LSD-SLAM的结果。ORB-SLAM2能够实现一个厘米级精准的定位,并且比双目的LSD-SLAM更加的精确。

Our tracking get lost in some parts of V2 03 difficult due to severe motion blur.

跟踪部分可能会在V2 03 difficul,序列当中跟丢,由于一些运动模糊。

As shown in [22], this sequence can be processed using IMU information.

在第22篇论文解释的情况,这个序列在处理的过程中是使用IMU信息,

Fig. 5 shows examples of computed trajectories compared to the ground-truth.

如图5所示,显示的一些估计轨迹对真实的世界相比的例子。


fig_5

image copy right belongs to Raúl Mur-Artal and Juan D. Tardós. ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras. ArXiv preprint arXiv:1610.06475

图像摘录自ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras. ArXiv preprint arXiv:1610.06475

Fig. 5. Estimated trajectory (black) and groundtruth (red) in EuRoC V1 02 medium, V2 02 medium, MH 03 medium and MH 05 difficutlt.

图5 在EuRoC V102_medium,V2_02_medium,MH_03_medium和MH_05数据集测试结果,其中估计轨迹(黑色)实际运动轨迹(红色)。


全篇仅提供学习,请勿用于商业用途,翻译版权【泡泡机器人】 all right reserved,powered by Gitbook修订时间: 2017-04

results matching ""

    No results matching ""