2.2 B. RGB-D SLAM
2.2.1 paragraph
One of the earliest and most famed RGB-D SLAM systems was the KinectFusion of Newcombe et al. [4].
最早和最著名的RGB-D SLAM系统是有Newcombe等人[4]提出的KinectFusion，
This method fused all depth data from the sensor into a volumetric dense model that is used to track the camera pose using ICP.
这种方法将深度数据进行融合，深度数据来源于传感器到深度模型，常常使用ICP算法来跟踪相机的位姿。
This system was limited to small workspaces due to its volumetric representation and the lack of loop closing.
由于体积的表现形式和缺乏回环检测，这种算法只能工作在小的工作空间。
Kintinuous by Whelan et al. [12] was able to operate in large environments by using a rolling cyclical buffer and included loop closing using place recognition and pose graph optimization.
Whelan 等人[12]提出的Kintinuous能够在大环境中运行。它通过使用一个滚动循环缓冲器和包括使用位置定位和位姿优化来达到回环检测的目的。
2.2.2 paragraph
Probably the first popular open-source system was the RGB-D SLAM of Endres et al. [13].
第一个开源的RGB-D SLAM方案是由Endres[13]提出的，
This is a feature-based system, whose fronted computes frame-to-frame motion by feature matching and ICP.
这是一种基于特征点提取的系统，他的前端采用提取和匹配特征点和ICP来计算帧与帧之间的运动。
The backend performs posegraph optimization with loop closure constraints from an heuristic search.
后端采用位姿图优化的方式，回环检测约束条件来源于一个启发式搜索。
Similarly the backed of DVO-SLAM of Kerl et al. [14] optimizes a pose-graph where keyframe-tokeyframe constraints are computed from a visual odometry that minimizes both photometric and depth error.
相似的是，Kerl 等人[14]提出的DVO-SLAM，是在关键帧与关键帧之间的优化位姿图，视觉里程计通过计算最小化光度和深度误差来计算约束条件。
DVO-SLAM also searches for loop candidates in an heuristic fashion over all previous frames, instead of relying on place recognition.
DVO-SLAM同时在以前的所有帧当中，搜索回环的候选者，而不依赖于位置识别。
2.2.3 paragraph
The recent ElasticFusion of Whelan et al. [15] builds a surfel-based map of the environment.
Whelan等人[15]提出的邻近ElasticFusion算法，是建立在基于确定环境的地图。
This is a map-centric approach that forget poses and performs loop closing applying a non-rigid deformation to the map, instead of a standard pose-graph optimization.
这是一种以地图为中心的方法。这种方法忽略了非刚性形变地图的位姿和回环检测的性能，也是不是一个标准的位姿图优化。
The detailed reconstruction and localization accuracy of this system is impressive, but the current implementation is limited to room-size maps as the complexity scales with the number of surfels in the map.
这种方法在重建和定位的精度都是十分优秀的，但是目前的应用十分有限对于一个房间大小的地图，由于在地图当中面元的数量影响计算的复杂程度。
2.2.4 paragraph
As proposed by Strasdat et al. [8] our ORB-SLAM2 uses depth information to synthesize a stereo coordinate for extracted features on the image.
Strasdat等人[8]提出ORB-SLAM2这种方法，这个方法使用深度信息去合成一个三维坐标，能够精确的提取到一副图像的信息。
This way our system is agnostic of the input being stereo or RGB-D.
ORB-SLAM2能够处理来自双目和RGB-D的图像，
Differently to all above methods our backend is based on bundle adjustment and builds a globally consistent sparse reconstruction.
与上述方法不同的是，我们的后端是用的BA算法，来建立一个全局的稀疏的地图重建，
Therefore our method is lightweight and works with standard CPUs.
因此我们的方法更加轻量级并且能够在标准的CPU上面运行。
Our goal is long-term and globally consistent localization instead of building the most detailed dense reconstruction.
我们的目标是长时间并且全局精准定位，而不是建立一个有很多细节的稠密地图。
However from the highly accurate keyframe poses one could fuse depth maps and get accurate reconstruction on-the-fly in a local area or post-process the depth maps from all keyframes after a full BA and get an accurate 3D model of the whole scene.
然而，高精度的关键帧的位姿，能够融合深度图像以及在计算中得到精准的重建，或者能够处理所有的关键帧和深度图，以及所有的BA并且得到一个精准的3D模型。