Questions tagged [computer-vision]
Questions about algorithms for processing and analyzing images and videos.
264
questions
0
votes
1answer
114 views
Convolutional Neural Network for Insects
I've recently started learning CNN's. I need a CNN that is specialized for insects detection. Dead insects will be put on a piece of paper / container, then images will be taken from a same distance, ...
4
votes
4answers
1k views
Efficiently labelling training data in machine learning
Obviously it always depends on the specific case. However, my question is how to label data efficiently without writing a source code from scratch which solves the final problem itself?
For example, ...
1
vote
2answers
21 views
Distinguishing between side-by-side liquid streams
I'm new to computer vision and am looking for advice. I'd like to perform computer vision on a spiral system, in this system a down flowing liquid separates into different regions based on density:
...
1
vote
0answers
59 views
Should I go for computer science or maths? [closed]
I am in 11th grade. The only subject which I love the most is solving alegebraic equations and questions related to it. I enjoy doing trigonometry but hate the part of proving theorems. I opted ...
1
vote
1answer
5k views
How to convert pixel relative focal lengths to mm. [closed]
Ive been playing around with the Intel Realsense R200 Camera.
I am able to exact focal length in x and y i.e. fx and fy,
but only "up to scale relative to pixel width and height, respectively"
At the ...
2
votes
1answer
113 views
Camera position w.r.t. basketball court
I am new in Computer Vision. Suppose you have 8 points (players in a basketball court) in a 2D image (png photo), that is we know the pixel coordinates of each. I would like to compute camera position ...
1
vote
1answer
35 views
Perspective-Three-Point Questions
I'm following this explanation on the P3P problem and have a few questions.
In the heading labeled Section 1 they project the image plane points onto a unit sphere. I'm not sure why they do this, is ...
0
votes
1answer
435 views
How to identify object(s) in image when given a list of all images?
I see a lot of articles and topics about OpenCV and machine learning in regards to identifying general things (like cats, or alphanumeric characters) but I am wondering if something more specific is ...
0
votes
0answers
58 views
Recognizing features in images (uncontrolled environment)
I have been working for some time in several kinds of image recognition. They work well. One example is , character or shape recognition. I have implemented this in an embedded processor and I can ...
1
vote
0answers
25 views
Want to do 3D reconstruction via simple matching
I have 2 images, called left and right images. I have some matched points $[c_l,r_l]$ and $[c_r,r_r]$ in both of them (these points are in pixel coordinates).
For a 3D point in the real world, they ...
1
vote
0answers
49 views
Detecting shapes using CNNs in respect to other shapes in the image
I'm solving a problem of detecting an optic disc in a retina image. As you can see from the image:
the optic disc is the epicentrum of the blood vessels, has an irregular circular shape and has a ...
3
votes
1answer
84 views
What are some research papers or techniques that deals with fitting clothes on a human?
Given an image of a dress (from different angles), what could be ways to fit it on a human image (again multiple angles corresponding to dress)? Any link to research papers or tutorial regarding this?
3
votes
3answers
609 views
Is the Tomasi-Kanade factorization still commonly used as a modern computer vision technique?
My understanding is that, in very rough terms, the Tomasi-Kanade algorithm published in 1992 describes a way to reconstruct the 3D structure of an object from multiple images of that object, given ...
0
votes
0answers
75 views
Does photogrammetry have non-rigid 3D reconstruction methods?
Prerequisites
I've found out that photogrammetry methods allow us to fetch 3D model from set of images of a scene. I call this rigid reconstruction.
There are methods of finding correspondence ...
1
vote
0answers
50 views
Finding a line shape objects (bars) in video images using neural networks (instead of Hough transform)
I'm currently trying to learn about computer vision stuff and I want to try it on a simple project of real time tracking of figures of players in a foosball game while the camera can be moving a ...
-2
votes
2answers
92 views
Obtaining Image Measurements of a Known Object [closed]
Given the image of an adhesive tape as below, what would be possible method to find the tape radius?
The image sepia toned with artificial background added. The tape itself is partially hidden.
2
votes
1answer
117 views
Specific Examples with Explanation of Similarities and Differences of how Distance Functions are used Across Different Fields [closed]
I took a tangent from a student
project
I had done a number of years ago and spent some time studying distance
functions.
(please note that the above link contains the full question with links as I ...
3
votes
1answer
843 views
Given a low resolution video, is it possible to create a higher resolution image
This question is purely theoretical as I've not been able to find anyone who's done such a thing, so my question is - is it possible, and if not why?
Say you have a short video (CCTV) of a face, or ...
1
vote
0answers
20 views
Convergent cameras stitching
I am currently working on a computer vision problem that involve 8 convergent cameras.
I am trying to recreate a 2D image (I actually don't care of the shape of the image) that is the representation ...
0
votes
0answers
248 views
Multi-camera calibration wand
I am master student, and I work on project with camera tracking based on sphered Infrared (IR) markers.
Now I have to implement multi-camera calibration system with a wand like this one:
And I want ...
1
vote
0answers
47 views
What kind of numerical image features should I use to distinguish between the attached types of poses?
I've around $500$ binary (black and white) images, of which I attach $2$ samples. I'm working on a machine learning problem of classifying images like them. I'd like to know what image features I can ...
1
vote
0answers
51 views
Question about (in)dependent Haar-features and (Ada)boosting
I have an old exam question for my pattern recognition course which is stated as follows:
Consider a pool of Haar features, determine if these Haar features are independent or not. Is it a problem ...
0
votes
0answers
32 views
Maximum Ratio of White/Black pixels in an Edge Map
Is there a maximum possible ratio of white/black pixels in an edge map?
In my theoretical consideration all areas in an image which have the same intensity are black and only the edges are white. ...
0
votes
0answers
247 views
computer vision - How to construct a 3d map?
I have some good basics -I think- in computervision (using openCV) and am considering to build a quadcopter to create a 3D maps while flying.
I would like to place a camera on each side of the ...
6
votes
1answer
157 views
using orientation sensor data to predict image points
I want to use Android's gyro/accelerometer/magnetometer to predict (over a very short time interval) how image points corresponding to a fixed object will change (without trying to scan for them in ...
1
vote
1answer
91 views
Description of shape in a vector form
I would like to ask for references to algorithms that can project shape information about an object to 1 dimension. Specifically I am training a neural network to be able to identify objects with ...
0
votes
0answers
107 views
More Efficient Feature Method Than Haar-Feature For Face Detection
The seminal work by Viola-Jones had the most impact in face detection. It used Haar-Feature, which is fast to compute with the help of integral image method.
Is there a feature method that is more ...
2
votes
0answers
53 views
How the SIFT results vary by changing some parameters
I'm studying the SIFT algorithm and I have some problem understanding its operation, in particular I don't understand how the results vary according to the parameters: number of octaves, number of ...
3
votes
0answers
100 views
How can color spaces be compared?
I am currently working on image classification methods. One group of preprocessing methods are color space transformations. While there are "traditional" color spaces like RGB (the raw data), HSV, LUV,...
0
votes
0answers
39 views
What is the best way to find similarity between two bodies?
Suppose we have two human bodies. We need to find some number that represents a similarity score between the two bodies.
However in order to achieve that we need to find the similarity between the ...
0
votes
0answers
158 views
Reversible 2D Shape Descriptor
This is a research problem and I am just wondering if there is any already existing answer in any computer vision related paper that may have skipped my notice since this is not my active area of ...
0
votes
0answers
20 views
Create 2D panoramas from 3D image
Given a 3D greyscale image (particularly a dental scan) I have localized a jaw on it, i.e. made jaw's voxel intensity values much higher than others. Using this, how can I create a 2D panoramas from ...
1
vote
0answers
500 views
Why are SIFT features significantly different after simply re-sizing image?
I'm new to SIFT and was surprised by how much the features changed after resizing an image. Here's the images I used for testing:
Original:
Resized:
Cropped:
After running SIFT on those 3 images, ...
7
votes
0answers
2k views
Detecting the damaged regions in cars
Detecting the regions where a car has been damaged and the extent to which it has been damaged is a very interesting problem. It has potential applications in automatic auto insurance claims. ...
1
vote
0answers
65 views
Up to what extent the hypothesis of piece wise constant intensity values is valid in ocean images?
Usually, in MR images one hypothesis research communities are making is,
" the spatial intensity distribution is
piecewise constant and that each tissue corresponds to a
unique grayscale level. Based ...
2
votes
0answers
240 views
Geometric interpretations of midpoint algorithm, homogeneous linear least squares and nonlinear least squares method in 3D reconstruction?
In "Multiple View Geometry in Computer Vision" Chapter 12. Structure Computation, page 310-313, triangulation is used for point 3D reconstruction. There are three methods mentioned:
Midpoint method ...
1
vote
2answers
6k views
How is RANSAC used to estimate a homography given the descriptors of both images computed with SIFT?
Let image $x$ be an original (non-warped) image. Let $I_1$ be $I_1'$ having suffered some projective transformation and possibly some noise.
Suppose we have computed SIFT descriptors for both images.
...
1
vote
0answers
20 views
Systems for inter-human touch classification?
I'm trying to find any publications involving a system that can classify if there is physical contact in a video. Ideally, if the physical contact is brief, it would also be beneficial to classify. ...
2
votes
1answer
2k views
Computer Vision - What is spatial histogram/pyramid feature?
I am trying to re-implement the model in this paper https://arxiv.org/pdf/1511.02917v2.pdf. But the paper omitted some details in feature extraction (Section 4.1). I am new to computer vision so I am ...
-1
votes
1answer
1k views
Using landmark points on the face for face recognition
I am currently working in area of computer vision for my master's thesis and am trying to use distances between landmark points on the face for recognition.
My question is this: What landmark points ...
0
votes
0answers
60 views
How motion capture system works?
Can you explain in step-by-step basis of how motion capture system work? Especially the part, that enables the 3D models to mimic the movement of the actor.
1
vote
0answers
488 views
Class activation mapping using inception-v3 network
I am using the technique of this paper: https://arxiv.org/pdf/1604.07953.pdf
to localize food objects. The difference is that I am using the next generation of google-net, inception-v3 network. For ...
1
vote
1answer
222 views
How does an image classifier select relevant features?
I am trying to understand cascade classifiers for computer vision. I use OpenCV Traincascade for now and successfully trained some cascades.
However I am trying to grasp the whole process. One thing ...
1
vote
1answer
168 views
Basic queries for Object Detection using deep learning
I have recently started working on the Object detection using deep learning.
I have understood the basic steps of object detection are:
Input Image -> Object proposals -> Feature Extraction -> ...
0
votes
1answer
649 views
Big number of false positives in binary classification
I am fine-tuning the inception-v3 network(pretrained on ILSVRC) of tensorflow in a binary classification problem. I want to recognize if an image contains food or not. My dataset is imbalanced, the ...
0
votes
0answers
59 views
Edge detection in images
I am working on edge detectors: Canny, Sobel, Prewitt, and Roberts. These edge detectors work with conventional kernels to compute the edge. The kernel values are multiplied with the pixel values of ...
2
votes
1answer
97 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
95 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}+...
4
votes
1answer
239 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 ...
