立体视觉
立体视觉通过比较同一场景的两个视图来估计深度。这种计算的输出是三维点云，其中每个点都对应于其中一个图像中的一个匹配像素。工作流从立体相机标定开始，使用立体相机标定器估计内参和外参。标定完成后，立体图像矫正会将图像对对齐到一个公共平面上，从而简化视差估计中的对应点匹配。有关介绍，请参阅Using the Stereo Camera Calibrator App。要对未标定的图像执行立体矫正，请参阅Uncalibrated Stereo Image Rectification。
您可以使用分块匹配或半全局匹配等经典算法来计算视差图。然后，您可以应用三角剖分和对极几何等几何原理，使用视差图来执行稠密三维场景重建。有关详细信息，请参阅Reconstruct 3-D Scene from Stereo Image Pair Using Semi-Global Matching和Compare RAFT Optical Flow and Semi-Global Matching for Stereo Reconstruction。
立体视觉还支持视觉 SLAM 和真实世界距离测量等高级应用。有关详细信息，请参阅Stereo Visual SLAM for UAV Navigation in 3D Simulation和Measure Real-World Distances to Objects Using a Stereo-Camera。
App
| 立体相机标定器 | 估计立体相机的几何参数 |
函数
主题
- What Is Stereo Reconstruction?
Reconstruct 3-D scene using stereo vision.
- 什么是相机标定？
估计图像或视频相机的镜头与图像传感器的参数。
- 坐标系
指定像素索引、空间坐标和三维坐标系。
- Using the Stereo Camera Calibrator App
Calibrate a stereo camera, which you can then use to recover depth from images.
精选示例
Reconstruct 3-D Scene from Stereo Image Pair Using Semi-Global Matching
Reconstruct the 3-D world coordinates of points corresponding to each pixel from a disparity map.
Compare RAFT Optical Flow and Semi-Global Matching for Stereo Reconstruction
Compare deep learning based RAFT optical flow model and classical semi-global matching algorithm for disparity estimation and stereo reconstruction applications.
Measure Real-World Distances to Objects Using a Stereo-Camera
Detect a face and compute the distance between it in a camera scene and the camera.
Uncalibrated Stereo Image Rectification
Compute rectification of two uncalibrated images.
立体鱼眼镜头标定
通过确定每台相机的内参并估算它们之间的基线，对立体鱼眼镜头相机进行标定。
Performant and Deployable Stereo Visual SLAM with Fisheye Images
Use fisheye image data from a stereo camera to perform VSLAM and generate multi-threaded C/C++ code.
Stereo Visual SLAM for UAV Navigation in 3D Simulation
Develop a visual SLAM algorithm for a UAV equipped with a stereo camera.
Stereo Visual Simultaneous Localization and Mapping
Process image data from a stereo camera to build a map of an outdoor environment and estimate the trajectory of the camera.
基于立体视频的深度估计
检测由经过标定的立体相机拍摄的视频中的人员，并确定其与相机的距离。
Code Generation for Depth Estimation from Stereo Video
Use the MATLAB® Coder™ to generate C code for a MATLAB function, which uses the stereoParameters object produced by Stereo Camera Calibrator app or the estimateCameraParameters function. The example explains how to modify the MATLAB code in the 基于立体视频的深度估计 example to support code generation.
