2.1 A. Stereo SLAM 双目SLAM
2.1.1 paragraph
A remarkable early stereo SLAM system was the work of Paz et al. [5].
最早研究双目SLAM方案的是Paz 等人[5]，
Based on Conditionally Independent Divide and Conquer EKF-SLAM it was able to operate in larger environments than other approaches at that time.
基于条件独立分割和扩展SLAM，其显著特点是能够在大场景中运行。
Most importantly, it was the first stereo SLAM exploiting both close and far points (i.e. points whose depth cannot be reliably estimated due to little disparity in the stereo camera), using an inverse depth parametrization [6] for the latter.
更重要的是，这是第一个使用近特征点和远特征点（例如，由于双目相机差异较小，导致点的深度不能准确的估计）的双目SLAM系统，使用一个逆深度参数进行估计。
They empirically showed that points can be reliably triangulated if their depth is less than ~40 times the stereo baseline.
经验值表明如果深度小于40倍双目的基线，那么这个点就能被三角测量化。
In this work we follow this strategy of treating in a different way and points, as explained in Section III-A.
我们就是跟随的这样思想来处理远近不同的特征点，具体解释放在第三部分。
2.1.2 paragraph
Most modern stereo SLAM systems are keyframe-based [7] and perform BA optimization in a local area to achieve scalability.
目前大多数双目系统都是基于特征匹配和局部BA优化的方式，来获得尺度。
The work of Strasdat et al. [8] performs a joint optimization of BA (point-pose constraints) in an inner window of keyframes and pose-graph (pose-pose constraints) in an outer window.
Strasdat等人[8]采用在一个输出窗口的关键帧[7]和位姿的BA联合优化算法。
By limiting the size of these windows the method achieves constant time complexity, at the expense of not guaranteeing global consistency.
在全局不一致性的情况下，通过限制窗口的大小的方式，实现了约束了时间的复杂程度的目的。
The RSLAM of Mei et al. [9] uses a relative representation of landmarks and poses and performs relative BA in an active area which can be constrained for constant-time.
Mei等人[9]在限定时间复杂度的条件下，使用路标和位姿相关性的方式的实现了RSLAM解决方案，并且提出和实现了在活动的区域的BA优化算法。
RSLAM is able to close loops which allow to expand active areas at both sides of a loop, but global consistency is not enforced.
即使在全局不一致的条件下，RSLAM也能够进行闭环，同时会扩大回环两侧的活动区域。
The recent S-PTAM by Pire et al. [10] performs local BA, however it lacks large loop closing.
Pire等人[10]把局部的BA运用到了邻近S-PTAM上面来，但是，这种方法缺少大量的回环检测。
Similar to this approaches we perform BA in a local set of keyframes so that the complexity is independent of the map size and we can operate in large environments.
与此相似的是，我们对局部关键帧采用BA优化，因此，这个地图的大小和复杂程度的大小是独立的，进而，我们可以在一个大场景当中运行。
However our goal is to build a globally consistent map.
然而，我们目标是建立一个全局不变的地图。
Our system aligns first both sides of the loop, similar to RSLAM, so that the tracking is able to continue localizing using the old map and then performs a pose-graph optimization that minimizes the drift accumulated in the loop, followed by full BA.
因此，我们的系统首先在回环的两端执行。这与RSLAM很相似，以便于能够使用旧的地图进行定位，之后进行位姿估计，即将回环产生的累积漂移最小化。
2.1.3 paragraph
The recent Stereo LSD-SLAM of Engel et al. [11] is a semi-dense direct approach that minimizes photometric error in image regions with high gradient.
Engel等人[11]提出邻近双目LSD-SLAM方案，采用的是一种直接的半稠密方法，最小化高梯度的图像区域中的光度误差。
Not relying on features, the method is expected to be more robust to motion blur or poorly-textured environments.
这种方法希望能够在不依赖特征提取的条件下，能够在纹理不清或者模糊运动的过程中获得更高的鲁棒性。
However as a direct method its performance can be severely degraded by unmodeled effects like rolling shutter or non-lambertian reflectance.
然而，直接法的性能会由于滚动（卷帘）快门，或者非朗伯反射的未建模的因素影响而下降。