Signal Processing Stack Exchange
Signal Processing Stack Exchange

Questions tagged [computer-vision]

Computer vision includes methods of processing, analyzing, images and high-dimensional data to form high level understanding and recognition of the scene or images.

Computer vision enables images, or sequences of images, to be processed by a computer using an algorithm. There are many aspects to computer vision, including mathematics, imaging hardware, imaging software, physics (especially optics), signal processing and artificial intelligence.

The problems that computer vision is trying to solve include:

  • Object detection
  • Object recognition
  • Tracking moving objects in video
  • 3D reconstruction

Some basic techniques used in computer vision are:

  • Image acquisition
  • Pre-processing
  • Feature extraction
  • Detection/Segmentation
  • High-Level processing
  • Decision making

A theme in the development of this field has been to duplicate the abilities of human vision by electronically perceiving and understanding an image. This image understanding can be seen as the disentangling of symbolic information from image data using models constructed with the aid of geometry, physics, statistics, and learning theory.

Source: Wikipedia – Computer vision

831 questions
26
votes
3 answers

How to find tennis courts in aerial imagery

I'm interested in finding all tennis courts (and other similar well defined features like basketball courts) in my county, and I have aerial imagery of good (but varying) resolution, but I'm not sure of the best way to find them. Here are two…
joshdoe
  • 363
  • 2
  • 6
12
votes
1 answer

Interpretation of the eigenvalues of the inverse Hessian in a KLT tracker

I'm a masters student, preparing a seminar in computer vision. Among the topics is the Kanade-Lucas-Tomasi (KLT) tracker, as described in J. Shi, C. Tomasi, "Good features to track". Proceedings CVPR '94. Here's a web resource that I'm using to…
nathan g
12
votes
1 answer

Are there preferred patterns for creating texture on objects to aid computer vision?

In the comment to this answer using a laser diode and diffraction grating to provide texture on a surface was suggested to aid in height calculations in a computer vision system. I believe the pattern that I'm familiar with is projecting a…
Stephen
  • 731
  • 8
  • 14
10
votes
2 answers

Are there any computer vision algorithms specifically targeting depth images?

I've been looking into marker detection algorithms to use with a kinect based application, and the majority of the work I've been able to find is obviously focused on feature detection in 'normal' images. However, the kinect hardware provides…
Doug
  • 203
  • 1
  • 5
9
votes
2 answers

iPhone iOS UIImage how to detect a "laser pointer" dot on a camera feed?

I got a tracked robot toy and I'm controlling it with an iPhone. The robot outputs a live camera feed of a known frame size and I'm displaying it on UIImage. I've added a laser pointer to the robot and fixed it alongside the axis of the robot. I'm…
Alex Stone
  • 315
  • 1
  • 7
6
votes
0 answers

Jacobian Matrix of a Quaternion $q$ respect to Angular Velocity $\omega$

In the context of visual tracking and video processing I need to estimate variations of the orientation related to the angular velocity. I am trying to calculate the Jacobian matrix of a quaternion $\vec{q}_k$ respect to its (supposed to be…
Jav_Rock
  • 1,213
  • 2
  • 14
  • 24
5
votes
1 answer

Jacobian of affine warp in Lucas-Kanade image alignment

I hate this kind of questions, but I'm really stuck. I'm trying to implement Lucas-Kanade algorithm as described in this paper (see pages 4 and 5). Unlike most explanations I've seen they don't assume optical flow, but instead use affine…
ffriend
  • 443
  • 3
  • 7
4
votes
1 answer

Academic problem solving in Computer Vision

I am currently pursuing a Master degree of Engineering and I will have to write a thesis about solving a specific Machine Vision application. I have done some CV projects in the past but now I am tinkering about the methods of problem solving in the…
Doombot
  • 268
  • 1
  • 3
  • 11
3
votes
1 answer

Camera Calibration of a Depth Camera

For a regular RGB camera, reading the wikipedia page for camera resectioning/calibration here, they divide the paramters into two categories: Intrinsic: - focal length, scale factors in x and y, and principal point Extrinsic: - the rigid body…
IntegrateThis
  • 231
  • 1
  • 13
3
votes
0 answers

Projection Matrix (Computer Vision)

I'm trying to understand a piece of code that is using a camera projection matrix. The camera projection matrix $P = \left[\begin{array}{c}p_1^T \\ p_2^T \\ p_3^T\end{array}\right]$ takes a point $X$ in 3D world coordinates and projects it onto…
Mustafa
  • 420
  • 3
  • 7
2
votes
0 answers

What is the difference between full octave and half octave pyramid?

I couldn't find a good source to explain the diffrence between the Full octave and Half Octave pyramid in Computer-Vision. I saw the Gaussian-Pyramid, and the Laplacian Pyramid, but I didn't see anything about Full Octave - Half Octave…
Bilal
  • 167
  • 9
2
votes
4 answers

How is digital signal processing related to Computer Vision?

Keeping in reference this image, I want to build a concrete understanding of interconnection between Digital Signal Processing and Computer Vision. What would be the applications of this co-relation?
codeonion
  • 121
  • 2
2
votes
1 answer

Faster R-CNN and 4-step Alternating Training

I am reading the paper Faster R-CNN available here. In section 3.2, page 6 bottom left, the authors describe what they refer to as a 4-step Alternating Training between the Region Proposal Network, used to obtain region proposals used in the Fast…
IntegrateThis
  • 231
  • 1
  • 13
2
votes
1 answer

Understanding the relationship between the convolutional feature map and the region proposals in Fast R-CNN

In the paper Fast R-CNN available here, I am trying to understand the relationship between the region proposals and the convolutional feature map. So from what I understand, Fast R-CNN takes in an image and a set of region proposals for object…
IntegrateThis
  • 231
  • 1
  • 13
2
votes
1 answer

Matching features points of rotate image using SURF

I'm trying to match SURF points between 2 images using SURF with opencv. One is the rotation of the other. The problem is that the few matching it can found are wrong. image of matching points I mainly took my code from opencv…
Seltymar
  • 135
  • 1
  • 5
1
2 3