# 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.

743 questions
Filter by
Sorted by
Tagged with
17 views

### Homography valid for patch within the image but not the entire image?

The homography I have is non-degenerate (det!=0), and generated from a valid planar pose. When I use it to warp the four corners of image, it returns something like the following: ...
24 views

### Calculate surface of objects (rocks) in an image with lots of noise

Is there a way to caculate the size/surface of every individual rock visible in this image? I have tried: Contours - this doesnt seem to work the contours touch, gets real messy. Watershed algorithm -...
9 views

### How to obtain height above ground, angle the pixel’s local surface normal makes with the inferred gravity direction from depth map of image?

For extraction of the HHA features from the image depth map we need to calculate the height above ground, angle the pixel’s local surface normal makes with the inferred gravity direction. How to ...
28 views

### Removing halo effect in image composition: Google Meet's solution

Wanted to understand how google meet is removing halo effect when composing their image. They describe their method briefly in their blog as: "The blur shader simulates a bokeh effect by ...
12 views

### Feature Based Methods for Quality Inspection Problem

I am currently working on an image classification problem to classify thermal images (can be interpreted as false-color images) of certain products as with or without defect. From an initial search in ...
12 views

### Suggestions for creating 3D Bounding Boxes of Books on a Shelf from RGB-D Images

I am new to image processing, so I beg your pardon if this is a trivial question. I am trying to use an RGB-D camera to detect 3D bounding boxes of books on a shelf. Here are some examples of possible ...
8 views

### Three Projective Cameras in the Same “Projective Frame” - What Can I Do With This Info?

[I originally posted this under Mathematics, but I didn't get any replies. I thought I'd try here.] In Hartley & Zisserman's Multiple View Geometry in Computer Vision, in the chapter on trifocal ...
64 views

### Importance of Phase in FFT of an image

While processing digital images in the Fourier domain, mostly we exploit the amplitude and not the phase. This could be because the amplitude is much more structured and the amplitude spectrum reveals ...
12 views

### When computing mAP for object detection, how many detections should one consider?

I am trying to write some code to evaluate the MS COCO style mAP (mean average precision, average computed at the category level) at different IOU levels in the context of object detection with a ...
19 views

### Improving Vanishing Point Accuracy

I've been working for a while on 3D building reconstruction from old photos (c. 1904). In all of these cases, the cameras and buildings are long gone, making standard camera calibration impossible. ...
28 views

### In pulse code modulation what is pulse word represent?

we study lot of things in PCM we do sampling quantization encoding etc but we never come across pulse so what is pulse word represent in PCM
24 views

### Numerical computation of the derivative of a curve valued in $\operatorname{Diff}(\mathbb{R}^2)$

Assume we have a (discretized) sufficiently smooth curve $\alpha : [0, 1] \to \operatorname{Diff}(\mathbb{R}^2)$. Further assume that this curve is generated via a large deformation diffeomorphic ...
48 views

### Easiest Pattern to Recognize with Machine Vision

I need to detect the exact position of some kitchen tools using machine vision. I've the possibility to label the tools with a pattern, to make the detection (more specifically the image segmentation) ...
26 views

### Normalizing directed graphs from image space to compute joint differences

My question is how to transform a 'skeleton' (directed graph) from image space so that I can compare it joint-wise against another 'template' or reference skeleton that may be differently sized/...
46 views

### 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 ...
29 views

### Help or suggestions with Line detection in microscopy images

I'm doing a personal project in which I want to select some very specific lines in a microscopy image. The first picture is the raw image, the second picture is the image for the lines (in yellow) I ...
19 views

### Implementing Felzenszwalb's segmentation for 3D images

Is there an implementation available for unsupervised 3D segmentation using the Felzenszwalb's Graph Cut algorithm? If implemented what do you think are the bottlenecks of such an algorithm? In ...
13 views

### Problem definition in KLT tracking

I am studying about the KLT tracker algorithm. In the KLT tracker, we can try to estimate the optical flow for corner points (because these are good features to track) between frames and the computed ...
30 views

### Kalman Filtering with measurement latency

The timing involved in this problem is a little hard to explain, so I'll start with my specifics: I'm developing a program that visualizes output (a bounding box) from a computer vision model on top ...
21 views

### multi-frame image restoration

Suppose we have a sequence of still images each of which has been contaminated by some particles(ex, dust/sand/smoke) making the images very poor in certain areas. What approach would be best to teach ...
31 views

### Which one is better method and why? Manually Handcrafted sound features vs spectrogram + convolution

I am working on classifying different sounds ( not speech or words exactly something like ambulance alarm, police alarm, cough sounds etc) I read few paper which suggested to extract dsp features such ...
24 views

### Why not use synthetic datasets for training machine vision (deep learning) algorithms?

I am studying some examples of how to perform 3D instance segmentation in indoor scenes, and I have noticed many of the available datasets are from real environments. I was wondering with the ...
60 views

### Understanding the math used to generate a point cloud from a depth image

In reviewing various algorithms for converting a depth image to a point cloud where the camera has extrinsic parameters $c_x, c_y$ the center point of a camera $f_x = f*m_x$, where $f$ is the focal ...
48 views

### Interpreting the accuracy of solutions to the correspondence problem

I have two pictures of the same object, taken by a car travelling down the road like shown on the right side of the image below. I want to find pixels of the object in each frame that correspond to ...
61 views

### 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 ...
49 views

### Obtaining a horizontal disparity image from a depth image

In the paper Learning Rich Features from RGB-D Images for Object Detection and Segmentation available here, the authors encode depth images using three features computed from the depth image, called ...
143 views

### 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?
18 views

### Is there an algorithm in Matlab that could track moving objects that present change of color?

I'm studying the photomechanical behavior of photochromic thin films. They react to specific light wavelengths exhibiting bending movement. I use a yellow light, which turns the film from blue to ...
20 views

### Are location in BRIEF feature descriptor reused?

In the BRIEF feature descriptor ("BRIEF: Binary Robust IndependentElementary Features", Calonder et al., 2011) they investigate five different methods of choosing point pairs to compute the ...