简体   繁体   English

如何从 KITTI 数据集计算相机的焦距

[英]How to compute focal lenght of a camera from KITTI dataset

I work on the Kitti dataset of stereo images.我研究立体图像的 Kitti 数据集。 I have the intrinsic matrix given:我有给定的内在矩阵:

K_l = np.array([9.597910e+02, 0.000000e+00, 6.960217e+02, 0.000000e+00,
                9.569251e+02, 2.241806e+02, 0.000000e+00, 0.000000e+00, 1.000000e+00])

How can I compute the focal length from this matrix?如何从这个矩阵计算焦距?

We know that this matrix has the expression:我们知道这个矩阵有表达式:

cam.K =     [ -f/d   0    Cx;
                0  -f/d   Cy;
                0    0     1];

Thanks.谢谢。

In the camera matrix f is normally expressed in pixels, so you must multiply it by a coefficient to retrieve real world coordinates:在相机矩阵中f通常以像素表示,因此您必须将其乘以一个系数来检索真实世界坐标:

Fx = fx * W / w Fx = fx * W / w

with:和:

  • W: sensor width in world coordinates (meters) W:世界坐标中的传感器宽度(米)
  • w: sensor width in pixels (number of pixels in a row) w:以像素为单位的传感器宽度(一行中的像素数)

Those informations are available on the camera specs.这些信息可在相机规格中找到。

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

相关问题 如何从Kitti数据集计算基本矩阵? - How do I compute the fundamental matrix from Kitti dataset? 如何从立体图获取深度图 - KITTI 数据集 - How to acquire depth map from stereo - KITTI dataset 从 gps 位置计算姿势/变换矩阵(旋转和平移)和 KITTI 原始数据集的(滚动、俯仰、偏航) - Compute pose / transformation matrix (rotation and translation) from gps location and (roll, pitch, yaw) for KITTI raw dataset 具有不同焦距的立体相机的深度 - Depth from stereo camera with different focal length kitti数据集中的训练标签 - The training labels in kitti dataset 如何使用 KITTI 里程计数据集评估单目视觉里程计结果 - How to evaluate Monocular Visual Odometry results used the KITTI odometry dataset 如何通过投影矩阵从 KITTI 获得鸟瞰图? - How to get Bird's Eye View from KITTI by Projection Matrix? 如何计算描述性统计; 从数据集中选择特征的偏度和峰度? - how to compute descriptive statistics; Skewness and Kurtosis for slected feature from dataset? 如何在Kitti数据集中的每个点上标记Velodyen点? - How can I label velodyen points in Kitti dataset point per point? 如何在 PyTorch 中使用具有焦点损失的类权重用于多类分类的不平衡数据集 - How to Use Class Weights with Focal Loss in PyTorch for Imbalanced dataset for MultiClass Classification
 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM