Questions tagged [computer-vision]

Questions about algorithms for processing and analyzing images and videos.

Filter by
Sorted by
Tagged with
2
votes
1answer
100 views

Use of Activation Units in Facial Expression Understanding

The topic of extracting the Facial Action Coding System (FACS) Action Units (AUs) [1] from images and it's translation into emotion prediction [2] is pretty well studied, but I'm not clear on how it ...
2
votes
1answer
1k views

How to obtain the camera extrinsic matrix without using chessboard

I'm working on a problem to find the camera position in the world system when each picture was shot. I currently have several pictures taken from different angles, and for each picture there is only ...
2
votes
0answers
107 views

Image properties given by similitude moments

What image properties are given by similitude moments? These are image moments of the form shown below: $$\eta_{pq}=\frac{\sum_x\sum_y(x-\mu_x)^p(y-\mu_y)^qI(x,y)}{(\sum_x\sum_yI(x,y))^{\frac{p+q}{2}+...
5
votes
1answer
248 views

Machine learning: do the benefits of more data plateau after a certain point?

This question is both general in nature and also specific to computer vision. If this is the wrong forum, apologies in advance and suggestions on where to post would be much appreciated. After a ...
3
votes
1answer
292 views

Image registration algorithms for images with varying distances

I have two cameras side by side. I'd like to register two images taken from each camera. I think global transformation will not work for this issue since changes of distances between two images for ...
4
votes
2answers
337 views

Is there a metric for the similarity of two image filters?

Definitions An image filter is a matrix $m \in \mathbb{R}^{k_1 \times k_2 \times k_3}$ which gets applied to an image $I \in \mathbb{R}^{l_1 \times l_2 \times l_3}$ as a discrete convolution $$I'(...
2
votes
1answer
352 views

How to use PHOG and LPQ features for Emotion Recognition?

I have a database that consists of PHOG and LPQ features for each image. Now, I wish to train an SVM on these features for emotion recognition i.e SVM classifies the images on basis of emotion in the ...
1
vote
1answer
341 views

CRF message passing as convolution operation

I was reading the paper _Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials (Philipp Krähenbül and Vladen Koltun, in Proceedings of 25th Annual Conference on Neural Information ...
1
vote
1answer
164 views

Given a binary matrix, how to find the starting coordinates of a sub matrix?

Say, I have an image of bit depth 1 (i.e. binary matrix) and I cropped the image to form a smaller matrix. From the cropped matrix (of a reasonable size). I need to know the starting coordinates from ...
6
votes
1answer
296 views

Why is Scale Space Needed to Detect Scale Invariant Features?

I have been doing research on the SIFT (scale invariant feature transform) algorithm, and while I have repeatedly read that in order to detect image features that do not vary with respect to scales of ...
6
votes
1answer
17k views

Convert HSV to RGB colors

HSV colors are composed of a triple of numbers: hue $\in [0, 360)$ (in degrees), saturation $\in [0, 1]$ and value or brightness $\in [0, 1]$. RGB colors instead are more well-known and are also ...
1
vote
0answers
66 views

Machine learning / Computer vision [closed]

Suppose I have a set of images that I will use for training. Just as an example take that I have pics of the same car in many different camera angles. I am required to identify the important features ...
1
vote
0answers
576 views

How to find the position of camera given the known world coordinate of objects?

Assume that I have a picture of multiple objects (lets say more than 6). The world coordinate of these objects are known. The intrinsic parameters of the camera are also known. How can I find the ...
1
vote
1answer
993 views

Circle Hough Transform. Improvement by knowing edge direction

I'm studying Hough Transform. I have fully understood the HT for detecting lines and successfully implemented it. I have more problems with the circle detection HT. Given a circle, if the radius is ...
2
votes
1answer
115 views

Extracting intersecting objects of the same colour from an image

What is the good way to extract the objects(circles) from image as shown in picture below? respectively create two images one with lines and one with circles from source image. I started with ...
2
votes
0answers
683 views

Relative pose estimation using epipolar geometry: Wrong translation estimate

I am trying to use epipolar geometry concepts to estimate the relative pose of cameras between two images. I am currently using a simulator to get my camera images, so the distortion is zero and I ...
0
votes
0answers
393 views

Appearance-based methods for object detection

Object detection can be divided into Feature-based methods and Appearance-based methods. I want to find out what the most common Appearance-based methods are for object detection. There is not much ...
7
votes
1answer
2k views

Computer vision: object detection with labels that are single coordinates

Are there papers in the literature that address the following object detection task ? The task can be described as follows: Given a set of images, the labels are just coordinates (x,y) that ...
3
votes
1answer
639 views

HandyAR finger tip detection and tracking

I am reading this paper Handy AR. As suggested I am adding certain quotes from paper to get basic idea of what is it about : Intro In this paper, we present and evaluate a method to use a user’...
2
votes
0answers
48 views

Registering 3D-NIR image to thermal image and vice versa

In the past I have thought a bit about how to register a NIR-image and a thermal image and noticed that this is not trivial - one statement was that if I had the depth information for each pixel, the ...
2
votes
1answer
50 views

Processing weighted points of interest. Is there a name for this task/algorithm?

Is there a name for the following problem? Is there a measure of quality of a given solution? How can we even define what a proper solution is? Context: I want to detect long lines (most lines over ...
3
votes
1answer
3k views

HOG vs. neural networks for person detection

I am very new to computer vision, (a high school student) and I am working on a project to count the number of people present in a room. I have tried to use the HOGDecriptor for person detection ...
1
vote
2answers
841 views

How to label a video for supervised learning?

I have just started discovering the machine learning world! I found many tutorials showing how to deal with different types of data. I walked through some tensorFlow tutorials and I think they have ...
4
votes
3answers
193 views

Is there an efficient algorithm to extract the farthest ends of a thin contour?

Let's say you have pixel bitmaps that look something like this: From this I can easily extract a contour, which will be a concave polygon defined by a set of 2D points. The question is what is the ...
1
vote
1answer
1k views

Width of a String/Line in an Image

I have been looking for a method to find the width of a line. I found the solution(link: http://www.mathworks.com/matlabcentral/answers/88645-average-width-of-lines), "sum up the image to get the ...
1
vote
1answer
86 views

Computing gaussian kernel for image blurring

When I compute a gaussian kernel for image blurring should I normalize the 1D vectors? Because when I apply the raw values sometimes the image gets lighter or darker. The function I'm using is $f(x) = ...
1
vote
1answer
29 views

What is the need of re-sampling the image for HOG features?

I read Dalal and Triggs paper for HOG description and a blog Chris McCormick HOG regarding the same. The blog says that the image needs to be re-sampled at different scales to recognize different ...
4
votes
4answers
4k views

How to generate stereo image pair from a stationary mono camera?

I have a stationary mono camera which captures a single image frame at some fps. Assume the camera is not allowed to move,how do i generate a stereo image pair of the acquired frame? Is there any ...
1
vote
2answers
373 views

Hough transform: difference in cartesian to polar equation

According to Wikipedia and most other resources on the internet, the relation between cartesian coordinate and polar coordinate parameters are described by the equation $x\cos{\theta}+y\sin{\theta}=d$....
0
votes
1answer
42 views

Using Headpose Vector and 2D Points to Compute Distances

I have a frame taken from a video. The frame contains a face and I have the (x, y) locations of the features (corners of lips, edge of eyebrows, etc.) and the headpose vector (pitch, yaw, roll), which ...
1
vote
3answers
3k views

What is 'real time' in a Computer Vision context?

Suppose you have a program which works on a stream of images. It gets an image, makes edits and stores the image. What is the maximum latency with which one can still speak of a "real time application"...
12
votes
1answer
319 views

Google DeepDream Elaborated

I've seen a few questions on this site about Deep Dream, however none of them seem to actually speak as to what DeepDream is doing, specifically. As far as I've gathered, they seem to have changed the ...
0
votes
1answer
14 views

Is there any merging procedure for multiple scenes taking from RGB-D to avoid noise?

To avoid the noise as much as possible, I'm planning to take multiple scenes from RGB-D then try to merge them .... so is there any research papers , thoughts , ideas , algorithms or anything to help
4
votes
4answers
1k views

Which algorithm for counting the occurrences of a certain pattern (spots) in an image?

The Problem : Finding the number of occurrences of a certain pattern (or shape) in an image. In my example, the problem is about finding the number of spots (in variety of sizes) in an image. See ...
1
vote
1answer
235 views

Algorithms to convert 2D videos to 3D ones

Are there published algorithms that can convert 2D videos to 3D ones? If there are few published algorithms for this I am also interested to know how the conversion quality is.
0
votes
1answer
196 views

Using Taylor series in 1D Grayscale Image

Could someone point me in the direction of how to solve this? I = [I1, . . . , In] is a 1D grayscale image and D = [D1, . . . , Dn] represents the second derivative of I. I am given the four pixel ...
2
votes
1answer
2k views

Is it a good idea to determine coordinates of object on images with regression algorithms?

I am doing doing one of getting started competitions on kaggle, the one which requires you to find coordinates of different objects on images. I know that the usual method for this is to use sliding ...
2
votes
3answers
895 views

Is it correct to use the pinhole camera model to get the mapping of a 3D line to a line in an image?

I've been working on a computer vision project in which I'm using the pinhole camera model to map one line of the world to one line in an image. From previous research on the topic, I know that it is ...
0
votes
0answers
67 views

Belief Propagation in Computer Vision

I am working on dense matching using DSP algorithm. They have used belief propagation to optimize their energy function? How do we do it? I mean how do we assign prior belief? Link: Deformable Spatial ...
1
vote
2answers
64 views

Reconstruction of drawing sequence from video

I have a video that record the drawing sequence with a pencil by a painter. I want to reconstruction the sequence from the video. And I have google some keywords like "drawing sequence reconstruction"...
4
votes
4answers
2k views

How can I sum pixel values over a rotated rectangle?

I have an optimization problem in which I need to sum pixel values in an image over a rectangular region. This is a core component of the optimization so it will be done often and the naive solution ...
1
vote
0answers
65 views

In determining shape from line, what is special about the lines I've shown in these drawings by Ken Reid? [closed]

I'm interested in the way artists use lines to indicate shape in drawings. Strictly speaking, my question is about human vision — how our brains interpret certain lines — but I'm asking it here ...
5
votes
2answers
705 views

Segmenting a human body point cloud into limbs

I have a human body point cloud taken through a Kinect (v1). Now, I want to segment the point cloud into different parts, namely hands, lower arms, upper arms, torso, upper legs, lower legs, feet and ...
7
votes
1answer
842 views

Computer vision: Why do random filters perform similar to edge detectors?

I read here that "a randomly initialized filter acts very much like an edge detector!". I want to know if there are any papers describing and explaining this phenomenon.
5
votes
1answer
712 views

How to choose the number of HOG pyramid layers?

Reading Histograms of Oriented Gradients for Human Detection, I cannot see any discussion of how many layers there should be in the HOG pyramid. OpenCV offers a scaling factor of 1.05 which would mean ...
4
votes
1answer
40 views

Inverting radial distortion

I'm trying to understand the math behind correcting a radial distortion (caused by a lens), but I'm failing to have it explained in simple terms. I found several examples that proceed this way: a ...
0
votes
1answer
136 views

Does the SIFT feature be calculated in the original image or the corresponding octave(s)?

Given there are 4 octaves(the 1st octave is the original image, the 2nd octave is half size of the original image, and so on.), does SIFT calculate the keypoint's orientation in the original image or ...
29
votes
5answers
39k views

What is the difference between object detection, semantic segmentation and localization?

I've read those words in quite a lot of publications and I would like to have some nice definitions for those terms which make it clear what the difference between object detection vs semantic ...
8
votes
1answer
8k views

What is the difference between 'features' and 'descriptors' in computer vision / machine learning?

I've read multiple time sentences similar to Finally, for standard image classification bag-of-words features based on SIFT descriptors have been found critical for high performances. We first ...
1
vote
1answer
2k views

How are HOGs calculated?

Histograms of oriented gradients for human detection seems to be the paper from which all other papers cite when they use HOG features. However, this was the only description I could find in it: [.....