4

You are right about the sameness of SLAM and 3D reconstruction. At the same time I don't think the author is misclassifying. The english is a little non-standard. The author could have better said it as: ...ranging from SLAM to 3D reconstruction to realtime face and hand tracking to ... I think the paper lists both separately to better organize their ...


4

Each camera needs to be defined by 6 variables (3 position, 3 orientation). This would mean that during the calibration process, a solver needs to find 12 variables. As this is done usually with an nonlinear optimization process, the solutions are quite sensitive to the initial guess. By making them parallel and giving them a fixed width, you can give the ...


2

I think the function you're looking for is TransformPoint(Vector3 position). You can describe something in coordinates that are local to the camera and use the TransformPoint() method to convert from local camera coordinates to world coordinates. It sounds like you're trying to make a scene to generate some test data, in which case you'll have to have a ...


2

Creating 3D models with this method is very compute intensive, 123d uses many pictures (at least 20), and examines them for feature points that are common in several pictures and by examining how they change between pictures it can help build up a 3ds point cloud which is then textured using the pictures, this is very resource intensive, and could be done by ...


2

SLAM is jointly estimating the sensor pose and a map, based on a sensor model and sometimes a model for the pose change. The map can be represented in many different ways (e.g. landmark positions, occupancy grids, pointclouds). 3D reconstruction is used to estimate a 3D representation of the environment based on sensor data. There are many different ways to ...


2

The difference is largely intent. SLAM is largely used to describe the mapping procedure used when navigating an unknown environment. This is done online so the most recent state estimates are available to the navigator. 3D reconstruction is often a post processing procedure to create a 3D map of some environment. Or put another way: slam is an iterative ...


2

Since you only have 4 points, you should use the P3P algorithm. 3 points give you up to 4 solutions, and you need a fourth point to decide which one is correct. So 4 is the minimum number of points you need solve for the pose. Unfortunately, the P3P algorithm does not generalize to more points, which is why all those other algorithms you mentioned were ...


2

In Stereo Vision, image rectification is used to "warp" (remap the pixels using the translation, rotation, fundamental matrices computed from camera calibration) the image to remove distortions introduced in camera lenses and horizontally align pixels in the left and the right images to satisfy the epipolar constraint so that when stereo matching is ...


1

This is the basic slam problem. You have to find out (model) how the uncertainty of the robot affects the uncertainty of the landmarks, and visa-versa. This is done using the cross-correlation terms of the uncertainty. Or, the covariance. Those four things you referred to as covariances are actually variances. The covariance describes how the uncertainties ...


1

Most packages utilize stereo images to calculate distances. StereoVision is a python package that can be used to generate 3d point clouds. Also, this will require the use of odometry information. In order to utilize information from more than two sequential images, an implementation of extended kalman filter can be utilized. Successive point clouds can be ...


1

Not sure if I understood the problem correctly, but I understood that you wish to estimate the height of the observed objects hanging from the ceiling. You have a mono camera but you can take two images from different positions and use them as a stereo pair. You can use OpenCV to do this more easily: http://docs.opencv.org/modules/calib3d/doc/...


1

In your case I would suggest using the stereo version because: - You already said Kinect is technically not a possible solution because of the sun's IR light - A reasonable good lidar sensors costs a fortune even for a 2D version - Stereo vision is not expensive. You get 2 webcams for 100$, which is even less then a Kinect. The major problem with the ...


1

Sounds good to me but there are some missing stages. camera to the projector extrinsic calibration projector intrinsic calibration -> don't need this stage if you are not interested in the accuracy of your result. Also, you need to make sure to calibrate camera after adjusting focus. Extrinsic as well if you have made a change in camera-to-projector ...


1

I will assume, similar to OpenCV, that each camera is a pinhole camera, so you already corrected for things like lens distortion. In this case each visible point in 3D space $(x,y,z)$ gets projected into camera coordinates using $$ \begin{bmatrix} x'_i \\ y'_i \\ z'_i \end{bmatrix} = R_i \, \begin{bmatrix} x \\ y \\ z \end{bmatrix} + \vec{t}_i, \\ u_i = \...


1

I'm not sure if this is the paper where the method was first proposed, but the 1992 paper A Method for Registration of 3-D Shapes by Best and McKay (published in IEEE Transactions on Pattern Analysis and Machine Intelligence 14(2):239-256 ยท March 1992) does describe a method of the kind you are looking for. More importantly from your perspective, it ...


1

Have you reviewed this article? An Explicit Loop Closing Technique for 6D SLAM It consists of building the 3D model of environment with heuristic loop closure using ICP and reliable feature extraction.


1

The answer simply is, it does not really matter because you're using the norm. The scale is determined by the actual translation and rotation between two cameras (which in case of monocular odometry are two views from the same calibrated camera). This rotation and translation information is contained in the essential matrix (or fundamental matrix) which has ...


1

It turns out this can easily be done with OpenCV - just find image features (FAST etc.) in first image, track them to the second image (get a set of corresponding features between two images) and then use triangulatePoints function to get the 3D scene. triangulatePoints accepts two projection matrices - one for each image. Each projection matrix defines ...


1

For Kinect Fusion, and mostly all other point cloud fusion algorithms, ICP is used for aligning the clouds and creating the mesh. In a feature-less scene, ICP does not work, as there is no easy way to calculate local minimum errors to align the clouds so the stitching is almost impossible over a larger space. There is additional research work available ...


1

Making them parallel is beneficial for reducing distortion after a rectification. We usually rectify two images for a fast matching. If speed is not your concern you can skip the rectification stage.


Only top voted, non community-wiki answers of a minimum length are eligible