Questions tagged [computer-vision]

Questions about algorithms for processing and analyzing images and videos.

1
vote
0answers
8 views

Does the illumination color (red/blue/green) has any effect over the disparity map generated from a stereo image?

I have a working model that creates a disparity map using stereoscopic image processing using opencv. I am thinking of improving the disparity map by using illumination and stuck with different ...
1
vote
1answer
16 views

How to calculate point in 3D space from multiple perspective

I have multiple camera in different points. I have their position and rotation as $(x,y,z)$ , $(\alpha,\beta,\gamma)$ or $( roll, pitch, yaw)$ . And I have output like this : Feed from camera-1, I ...
0
votes
0answers
15 views

maximum tensor rank for computer vision tasks

Most computer vision tasks do not require 4+ ranked tensors. Are there any use cases for tensors with ranks more than 4 in computer vision? Are there any use cases for deep learning in general?
1
vote
0answers
30 views

What is the common way to approximate contour with quad?

I'm trying to find quads on stream from my webcam. cv2.HoughLinesP sometimes returns more lines then needed. How can I approximate them to contour of exactly 4 points that fits returned result best? I'...
3
votes
0answers
29 views

How to detect facial landmarks - using haar and other way?

I have done some projects using haar cascade(Ex.- Face-detection,Eye inside face detection,shoe detection etc), I also have some knowledge about it. I have trained my own models learning from youtube, ...
3
votes
0answers
45 views

Calculating depth mask from different lighting

I have a object which is static, the camera is static and light source is moving. How can the depth mask be calculated ? Concept is to use - calculate height from shadow length Lets imagine a have ...
3
votes
0answers
14 views

impact of the single pixel in disparity

Disparity essentially means the distance of a corresponding pixel in another image ( in pixels). This is clear and understood. When I looked after how the depth is related to disparity, then I found ...
1
vote
1answer
35 views

Triangulation algorithm for an arbitary amount of points?

I have multiple cameras that records the 2D pixel coordinates of the features each camera sees. After some searching, I came across this paper with a method to calculate the 3D coordinates of the ...
2
votes
2answers
67 views

Computer Vision algorithm to tell if camera is moving?

I'm looking for a computer vision algorithm or method that can tell if the camera is moving in a video. Or maybe an alternate way of telling if the background is moving. I have a lot of videos and ...
0
votes
0answers
14 views

Confused between different Structure from Motion pipelines

What is the difference between Global SfM, Incremental SfM, Sequential SfM, Progressive SfM and VSLAM (Visual Simultaneous Localization and Mapping). Is sequential SfM the same as VSLAM ? I have tried ...
1
vote
1answer
48 views

Image registration using gradient descent

I have a target image $f(x,y)$ (where $x \in [0, 250]$ and $y \in [0,300]$), and a source image $g(x,y)$ I want to align $g$ to $f$ using the transformation : $$\Psi(x,y;t_x, t_y, \theta) = \begin{...
1
vote
0answers
35 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?
2
votes
2answers
35 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 ...
1
vote
0answers
26 views

Finding the linear mapping between homogeneous coordinates of affine camera

If I have an affine camera with a projection relationship governed by: \begin{equation} \begin{bmatrix} x & y \end{bmatrix}^T = A \begin{bmatrix} X & Y & Z \end{bmatrix}^T + b \end{...
0
votes
1answer
35 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 ...
-2
votes
1answer
40 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 ...
0
votes
1answer
25 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 ...
1
vote
0answers
16 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 ...
1
vote
0answers
38 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 ...
0
votes
0answers
32 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 ...
1
vote
1answer
50 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?
1
vote
0answers
24 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 ...
1
vote
0answers
35 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 ...
1
vote
0answers
44 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, ...
1
vote
0answers
27 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 ...
2
votes
1answer
83 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 ...
1
vote
0answers
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 ...
1
vote
1answer
37 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 ...
1
vote
1answer
39 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 ...
0
votes
0answers
25 views

object measurement with MaskRCNN

I'm looking for the way to measure the size of objects in an image and I'm taking my consideration into MaskRCNN after coming to the conclusion that opencv contour detection doesn't satisfy our needs ...
1
vote
0answers
39 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 ...
2
votes
1answer
42 views

Hough Transform, Computer Vision

There is some thing i dont understand about Hough Transform in polar coordinates. From wikipedia article: "The simplest case of Hough transform is detecting straight lines. In general, the straight ...
1
vote
1answer
51 views

Comparing variable image to static image

What are Levenshtein distance algorithms, but for images? I will have one static image (the target: what it should look like) and one variable image (actual: what the user has created) For example, ...
0
votes
0answers
12 views

Edge tracking from a Video

I want to track an edge which is deformable throughout the video. Are there any algorithm available which can directly do the job in MATLAB? I have tried using the Lucas Kanade tracker but it can only ...
0
votes
2answers
33 views

detectEigenFeatures with polygon ROI

I am using detectEigenFeatures in the Matlab command to obtain the corner points. This function only can provide the corner points within a rectangular boundary region. But I want to extract the ...
0
votes
0answers
15 views

Cancelling the camera motion while tracking a particle

I have a video recording where a particle is in motion. I want to track the movement of the particle as accurately as possible. But the camera which is recording the particle motion is also moving (...
2
votes
1answer
44 views

The task of recognizing game units in the screenshot

I'm new to computer vision and I want to solve the task of recognizing the game units of the game Clash Royale in the screenshot. Briefly, there are about 70 different types of gaming units belonging ...
0
votes
0answers
32 views

Understanding depth maps in computer vision

It is clear to me that a depth map shows the distance of each pixel from the camera. Can anyone tell me what is the unit of this distance and how many bits they are usually coded with ? Also, I would ...
0
votes
1answer
42 views

Sample K representative frames within a video

I have an image-based processing module that takes photos for some computer vision processing. I have many videos, but I need to sample representative frames as its inputs, preferably those frames ...
2
votes
1answer
122 views

Capsule networks for classification with limited data

Capsule networks seem to match performance of convolutional neural networks on image classification tasks (more specifically on classification of handwritten digits in the MNIST dataset) 1. I have ...
6
votes
3answers
207 views

In lieu of neural networks and deep learning, what are some approaches to computer vision?

So much software related to computer vision relies on AI and neural networks, I wonder some of the approaches which don't use those methods. How could some of the mainstays of computer vision (eg. ...
1
vote
0answers
265 views

Backward mapping with bilinear sampler

I have some experiences with Convolutional Neural Networks before. I have a question regarding the Bilinear Sampler used in "Unsupervised Monocular Depth Estimation With Left-Right Consistency" (the ...
0
votes
0answers
250 views

How to recognize digits in water meter image

I need to read the digits of images like the one below: From what I understand, this will involve: Registering and segmenting the image into each individual digit Hand labeling a bunch of these ...
4
votes
1answer
64 views

Interpreting camera matrix

I'm having some trouble interpreting the camera matrix $K = \begin{bmatrix} f_x & s & x_0 \\ 0 & f_y & y_0 \\ 0 & 0 & 1 \end{bmatrix}$ after it multiplies some 3D vector. ...
1
vote
1answer
23 views

Relationship between depth and the vertical displacement of the object between two frames

I am trying to find the relation between the vertical displacement of an object to the depth of the object. Say, there is an object in an image and as the center of gravity of this object moves ...
2
votes
0answers
20 views

How to find the matched SIFT features that are spatially consistent?

I have extracted DenseSIFT from the query and database image and quantized by kmeans. The challenge is to find those SIFT features that quantized to the same visual ...
1
vote
0answers
28 views

Open source implementation of Multiscale Combinatorial Grouping [closed]

I would like to use Multiscale Combinatorial Grouping for my PhD research. However, I am restricted to use open-source implementations and this one runs on Matlab. Does anyone know of an equivalent ...
1
vote
0answers
43 views

Combining Computer Science and Humanities

I currently hold a bachelors in Computer science and a masters in Art History. I really want to combine the two and I know of Digital Humanities but I'm not completely aware of where Digital Humanists ...
2
votes
1answer
57 views

Is it possible to transfer a point from one camera to another, given n corresponding points?

I have 2 images of a scene taken at one moment by two identical cameras (similar cameras intrinsic parameters) by to arbitrary locations and at two arbitrary orientations (different cameras poses). On ...
0
votes
1answer
36 views

Generate a dataset for binarization of text in images

I want to generate a dataset of binarized masks of scene-text images to use them to train a model. I have no previous experience in dataset synthesization especially related to font-rendering. Can ...