# Questions tagged [computer-vision]

Questions about algorithms for processing and analyzing images and videos.

235 questions
Filter by
Sorted by
Tagged with
16 views

### Machine learning methods

In terms of a deep neural network, which activation will perform better between ReLU and sigmoid? Does it depend on the data or is one always better than the other? Are there any associated costs?
8 views

If bilinear interpolation is faster (uses 4 data points) but less accurate than bicubic interpolation, which uses 16 data points, why is there no "bi-quadratic" interpolation, which would use 9 data ...
11 views

### Measuring distance in arbitrary scale point cloud

I have one point cloud(point cloud of human feet) of arbitrary scale. If I have another point cloud(of human feet) with dimensions known, can I get the dimensions of a first point cloud? How will ...
8 views

### Using stereo vision for obstacle avoidance on quadcopter?

I am basically an electrical engineer. I plan to use stereo vision for obstacle avoidance (and possible further development of object recognition). Any efficient libraries for depth mapping from ...
25 views

48 views

### Why is sparsity useful in dictionary learning?

What is the particular reason for which we use sparse matrix X in dictionary learning equation Y=DX where Y is the signal matrix, D is dictionary and X is the coefficient matrix?
39 views

### identify abrupt frame changes in a video

The frames of live streams or videos, in general, do not flow smoothly. A sports game would have multiple cameras recording the game and hence, there will be camera switches in the stream. I am ...
29 views

### Finding the linear mapping between homogeneous coordinates of affine camera

If I have an affine camera with a projection relationship governed by: \begin{bmatrix} x & y \end{bmatrix}^T = A \begin{bmatrix} X & Y & Z \end{bmatrix}^T + b \end{...
78 views

### Camera calibration without grid

Ususally a grid pattern (circles or squares) is used for camera calibration. Features (circles or corners) are detected in a function (e.g. findCirclesGrid in OpenCV) and passed to the a camera ...
62 views

### what the mean and median filters with an n x n kernel (neighborhood) do to the grey-levels of the image? [closed]

sorry i haven't found a good title for these three questions i'm wondering if someone could give me explaination with proof (if possible ) of these three questions : Given a grey-level image stored ...
31 views

### How do we fix area of detectors in object detection?

I have gone through various articles on medium and also some from other sites trying to understand SSD. I am able to figure out most of the things from articles except this one. They always say that ...
20 views

### 3D registration for reconstructed surface

I use Meshroom (based on the framework AliceVision) to reconstruct a scene based on photographs (e.g. a bottle on a table in a room). The software captures the bottle, but also the table and the whole ...
45 views

### Algorithm to determine paths that define shape of connected rectangles

Say you have a bunch of rectangles like these: They get organized into 3 distinct final shapes like this: As you can see, there are a few "complete contours", as in here: The way you figure out the ...
76 views

### What is the practical limit to how many object classes you can detect with Faster RCNN?

I am trying to follow this tutorial where the Faster-RCNN-Inception-V2-COCO model from TensorFlow's model zoo is used to detect playing cards. I was wondering what is the practical limit to the number ...
102 views

### When estimating camera motion from the fundamental matrix, why can translation only be recovered up to scale using epipolar geometry?

I was wondering once you have recovered the fundamental matrix F such that xFx' = 0. If you try to recover translation and rotation from F, I am told that this is possible only up to scale? Why so?
37 views

### Stereo-Camera: How do Bundle Adjustment and projective ambiguity fit together?

In the book Multiple View Geometry in Computer Vision Hartley and Zisserman write that given a stereo image pair, the viewed scene can only be reconstructed under projective ambiguity, i.e. is a ...
66 views

### Transform Image Point to Azimuth and Elevation

I'm working on an object tracker where I need to report the azimuth and elevation of targets. Both values should be scaled from degrees to unsigned 32-bit integers. For now I can ignore lens ...
49 views

### How to find corresponding points between two photos when there's a repeated pattern?

Suppose that I have two photos, I1 and I2 and I want to find a set of corresponding points between the two photos to define a homography between them. There are many algorithms for this purpose, ...
28 views

### Removing fish-eye effect

The DNG specification (page 87) describes a simple algorithm for converting a "fish-eye" photo into a regular photo (just several lines of basic geometry). The transformation is configured using six ...
92 views

### Do white box methods for feature extraction exist for facial recognition?

Part of something I'm working on (or rather begin working on) involves white box approaches to facial recognition. I previously worked on something for character recognition using scene segmentation ...
15 views

### Plenoptic function meaning of dx

I'm trying to understand this paper on computer vision (http://persci.mit.edu/pub_pdfs/elements91.pdf) and it talks about building a periodic table of things we can get from the plenoptic function. It ...
63 views

### Image selection for Object detection

I'm relatively new and am still learning the basics. I've used NVIDIA DIGITS in the past, and am now looking at Tensorflow. While I've been able to fumble my way around creating some models for a few ...
45 views

### After stereo image rectification, why does the relation between disparity and depth still apply?

The relation between disparity and depth is derived based on the assumption that the two cameras are parallel. Image rectification does not make this assumption valid. But I see in many university ...
43 views

### Is there ongoing research on Markov Chain Monte Carlo algorithms (other than Metropolis-Hastings) for use in ray tracing? [closed]

Metropolis Light Transport is an application of the Metropolis-Hastings algorithm. Its variants differ only in the used "mutation strategy". Is there ongoing research on other Markov Chain Monte ...