审稿中...

4. Evaluation 评估

We have evaluated ORB-SLAM2 in three popular datasets and compared to other state-of-the-art SLAM systems, using always results published by the original authors.

我们使用三个著名的数据集来评估ORB-SLAM2的算法的性能。

We have run ORB-SLAM2 in an Intel Core i7-4790 desktop computer with 16Gb RAM, being the average processing time of the tracking always below the sensor’s frame-rate.

我们在一台16G的RAM，Intel Core i7-4790的台式机运行，以低于传感器的帧率，对处理跟踪时间求平均。

We have run each sequence 5 times and show always median results, to account for the non-deterministic nature of the multithreading system.

我们运行数据集5次，取中间值，来消除多线程系统的不确定性。

Our open-source implementation includes calibration and instructions to run the system in all these datasets.

我们开源了在运行这几个系统的数据集的方法包括标定具体操作实现。