slam 同时被 2 个专栏收录
8 篇文章 0 订阅
8 篇文章 25 订阅

# lsd-slam源码解读第三篇:算法解析

## Depth Map Estimation

tracking成功之后，就进入深度估计过程，首先是判断，是不是新建关键帧，论文中如此写道：

If the camera moves too far away from the existing map, a new keyframe is created from the most recent tracked image.

1. 用立体视觉方法来从先前的帧得到新的深度估计
2. 深度图帧与帧之间的传播
3. 部分规范化已知深度

#### 基于立体视觉对深度的更新

We use the oldest frame the pixel was observed in, where the disparity search range and the observation angle do not exceed a certain threshold (see Fig. 4). If a disparity search is unsuccessful (i.e., no good match is found), the pixel’s “age” is increased, such that subsequent disparity searches use newer frames where the pixel is likely to be still visible.

,

1. 参考帧上极线的计算
2. 极线上得到最好的匹配位置
3. 通过匹配位置计算出最佳的深度

g0表示等值线上的某个点，g=(gx,gy)^T表示图像的梯度方向

#### 深度的前向传播

tz表示相机的平移，sigmod_p表示预测的不确定度

### 创建KeyFrame

Once a new frame is chosen to become a keyframe, its depth map is initialized by projecting points from the previous keyframe into it, followed by one iteration of spatial regularization and outlier removal as proposed in 9. Afterwards, the depth map is scaled to have a mean inverse depth of one - this scaling factor is directly incorporated into the sim(3) camera pose. Finally, it replaces the previous keyframe and is used for tracking subsequent new frames

### refine Depth Map

A high number of very efficient small- baseline stereo comparisons is performed for image regions where the expected stereo accuracy is sufficiently large, as described in 9. The result is incorporated into the existing depth map, thereby refining it and potentially adding new pixels – this is done using the filtering approach proposed in 9.

## Map Optimization

01-09

12-16
07-26
11-25 1万+
07-08 1434
04-10
04-21 7270
11-28 7314
08-05 4578
05-21 2412
07-13 1610
12-30 5万+
04-30 851
07-17 791

lancelot_vim

¥2 ¥4 ¥6 ¥10 ¥20

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、C币套餐、付费专栏及课程。