Questions tagged [computer-vision]

For questions related to computer vision, which is an interdisciplinary scientific field (which can e.g. use image processing techniques) that deals with how computers can be made to gain high-level understanding from digital images or videos. For example, image recognition (that is, the identification of the type of objects in an image) is a computer vision problem.

Filter by
Sorted by
Tagged with
1
vote
2answers
442 views

Can I detect unique people in a video?

I am having a video feed with multiple faces in it. I need to detect each face and the gender as well and assign the gender against each person. I am not sure how to uniquely identify a face as Face1 ...
1
vote
0answers
11 views

Aggregating 2D object detections into 3D object detections

I have a data set of 3D images with some bounding box annotations. The images are too large to train something like YOLO 3D (would run out of memory), so I instead created slices of the 3D images with ...
2
votes
0answers
61 views

How are nested bounding boxes handled in object detection (and in particular in the case of the SSD)?

The basic approach to non-maximum-suppression makes sense, but I am kind of confused about how you handle nested bounding boxes. Suppose you have two predicted boxes, with one completely enclosing ...
0
votes
0answers
16 views

Interpreting coordinates of the function from the image using Grid Lines

I have a very different kind of problem at hand. I have a function plotted on the grid lines as shown below Now, I need to get the x and y coordinates for this particular function at regular ...
1
vote
0answers
20 views

In the DeepView paper, do they use the same FCN for all depth slices AND all views?

I'm trying to replicate a paper from Google on view synthesis/lightfields from 2019: DeepView: View Synthesis with Learned Gradient Descent and this is the PDF. Basically the input to the neural ...
1
vote
0answers
69 views

What are the pros and cons of 3D CNN and 2D CNN combined with optical flow for action recognition?

For action recognition or similar tasks, one can either use 3D CNN or combine 2D CNN with optical flow. See this paper for details. Can someone tell the pros/cons of each, in terms of accuracy, cost ...
1
vote
1answer
52 views

Training a classifier on different datasets with different image conditions for different labels causes the model to infer using the background

I have an interesting problem related to training the model on two different datasets for the target feature on images taken on different conditions, which might affect the model's ability to ...
1
vote
0answers
871 views

Applying a 1D convolution for 4D input

i'm trying to implement this paper and I'm stuck for quite some time now. Here is the issue: I have a 3D tensor and has (180,200,20) as dimension and I'm trying ...
1
vote
1answer
48 views

How does general image background removal AI work?

I'm well aware of the inner workings of CNN models for object detection, and although I've not worked on a semantic segmentation problem I can imagine how it works. With these types of models, we need ...
0
votes
0answers
26 views

How to build a commercial Image-Image search engine using LSH / Near Duplicate or some other algo on more than 20M images

TL;DR: HOW DO I APPLY LSH WITH A DEEP LEARNING MODEL TO BUILD A IMAGE-IMAGE SEARCH ENGINE ON >20M IMAGES? I want to build a system where I am helping my ...
1
vote
0answers
25 views

Reading Data from a Twilio Stream [closed]

I work for a video tutoring organisation that uses Twilio Video API to carry out the video class. I want to run the object detection and other computer vision models on the input stream. I am stuck at ...
1
vote
0answers
13 views

Is there a pre-trained network trained on RGB-D (4) channels? [closed]

The most used pre-trained networks for computer vision (e.g. ResNet50) are trained on 3 channels (RGB). At the same time, many cameras used in robotics return RGB-D outputs, that is including depth ...
0
votes
0answers
14 views

What are the best metrics for Multi-Object Tracking (MOT) evaluation and why?

I want to compare multiple computer vision Multi-Object Tracking (MOT) methods on my own dataset, so first I want to choose the best metrics for this task. I have carried out some research in ...
0
votes
1answer
396 views

What is the difference between Attention Gate and CNN filters?

Attention models/gates are used to focus/pay attention to the important regions. According to this paper, the authors describe that a model with Attention Gate (AG) can be trained from scratch. Then ...
3
votes
2answers
921 views

How to calculate the distance between the camera and an object using Computer Vision?

I want to create a Deep Learning model that measures the distance between the camera and certain objects in an image. Is it possible? Please, let me know some resources related to this task.
1
vote
0answers
55 views

Computer vision - Can you put more weight on a specific part of the object?

Let's say I'm looking for any item that has a certain shape (outline) in a photo. but I can further classify it only according to particular features, that most of them are expected to be shown only ...
1
vote
2answers
76 views

Why is my Keras prediction always close to 100% for one image class?

I am using Keras (on top of TF 2.3) to train an image classifier. In some cases I have more than two classes, but often there are just two classes (either "good" or "bad"). I am ...
1
vote
0answers
34 views

Face detection and replacement in photos

I have 2 photos, and my goal is to detect the face in one and place it on the face of the person in the other photo- basically face detection and replacement. It's not deep fakes. It's more of a ...
1
vote
0answers
19 views

Object Detection as a means of Anomaly Detection

Is it possible to train an Object Detector (e.g. SSD), to detect when something is not in the image. Imagine an assembly line that transports some objects. Each object needs to have 5 screws. If the ...
1
vote
1answer
113 views

How to compute dominant colors in an image?

I was trying Google Cloud's Vision API, and how the dominant colors part shows. I uploaded a sample image, and here is the results for the dominant colors. I realized it doesn't simply count pixel ...
1
vote
1answer
29 views

Why do we need to provide false labels to the discriminator on purpose to train GANs?

This is the tutorial that I used to learn about GANs. In this tutorial, it taught us to intentionally provide false labels to "fool" the discriminator, but does it make the discriminator ...
3
votes
2answers
2k views

Why is no activation function used at the final layer of super-resolution models?

I'm trying to implement some image super-resolution models on medical images. After reading a set of papers, I found that none of the existing models use any activation function for the last layer. ...
0
votes
0answers
42 views

Distinguishing between handwritten compound fraction and subtraction

I am working in a project named "Handwritten Math Evaluation". So what basically happens in this is that there are 11 classes of (0 - 9) and (+, -) each containing 50 clean handwritten ...
0
votes
0answers
33 views

How does one measure image similarity using Radial Basis Kernel?

Here is the formula of a radial basis kernel $$ k\left(x_{i}, x_{j}\right)=\exp \left(-\frac{d\left(x_{i}, x_{j}\right)^{2}}{2 l^{2}}\right), $$ where $x'$ and $x$ are feature vectors. I have two very ...
1
vote
1answer
203 views

Why do we resize images before using them for object detection?

In object detection, we can resize images by keeping the ratio the same as the original image, which is often known as "letterbox" resize. My questions are Why do we need to resize images? ...
1
vote
0answers
29 views

What is a "center loss"?

I have seen that a center loss is beneficial in computer vision, especially in face recognition. I have tried to understand this concept from the following material A Discriminative Feature Learning ...
0
votes
0answers
24 views

Generating data from a High-Res. RGB image for a CNN

Say I want to build a detection model that detects the existence of X or NO X. The only piece of information I have, though, is a high res. RGB image, say 100k (width) x ~1000 pixels (height). Let's ...
2
votes
0answers
92 views

Why can we perform graph convolution using the standard 2d convolution with $1 \times \Gamma$ kernels?

Recently I was reading this paper Skeleton Based Action RecognitionUsing Spatio Temporal Graph Convolution. In this paper, the authors claim (below equation (\ref{9})) that we can perform graph ...
1
vote
0answers
82 views

Are there any deep learning techniques to use the content of an image for another image?

Are there any machine learning or deep learning techniques to use the content of an image for another image? More specifically, suppose I take a photo of a notebook. I get the angle, lighting, and ...
1
vote
0answers
16 views

Find object's location in an area using computer vision

I'm trying to see how to detect the location of a soccer ball in the field using the live camera. What are some ways to achieve this? 1- Assuming we have a fixed camera with a wide shot. How to find ...
0
votes
0answers
50 views

Deep Learning based image restoration using multiple frames

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 architecture would be best to ...
1
vote
1answer
42 views

Are there any known models/techniques to determine whether a person in a store is a customer or a store representative?

Are there any known models/techniques to determine whether a person in a store is a customer or a store representative? For example, customer representatives can wear uniforms and then one possible ...
0
votes
1answer
64 views

Why isn't medical imaging improving faster with AI?

Researcher here. I just read this piece about medical imaging ai with object recognition and it left me wondering why there are still 100,000+ deaths a year in the US due to misdiagnosis - anyone out ...
2
votes
2answers
491 views

What is the need for so many filters in a CNN?

Consider the following coding line related to CNNS Conv2D(64, (3,3), strides=(2, 2), padding='same') It is a convolution layer with filter size $3 \times 3$ and ...
0
votes
1answer
67 views

How can I train a CNN to detect when a person is smoking outside of shop given images from a video camera?

My friend is working at a pizza shop. He takes cigarette breaks in an area that is covered by the public webcam of our town. I now want to train a convolutional neural network to be able to detect ...
0
votes
1answer
25 views

Is training a CNN object detector on an image containing multiple targets that are not all annotated will teach it to miss targets?

I want to train a convolutional neural network for object detection (say YOLO) to detect faces. Consider this image: In this training image, I have many people, but only 2 of them are annotated. Is ...
2
votes
0answers
515 views

Why aren't the BERT layers frozen during fine-tuning tasks?

During transfer learning in computer vision, I've seen that the layers of the base model are frozen if the images aren't too different from the model on which the base model is trained on. However, on ...
3
votes
2answers
98 views

Are there ensemble methods for regression?

I have heard of ensemble methods, such as XGBoost, for binary or categorical machine learning models. However, does this exist for regression? If so, how are the weights for each model in the process ...
6
votes
1answer
157 views

Formal definition of the Object Detection problem

For many problems in computer science, there is a formal, mathematical problem defition. Something like: Given ..., the problem is to ... How can the Object Detection problem (i.e. detecting objects ...
6
votes
2answers
162 views

Why don't we use auto-encoders instead of GANs?

I have watched Stanford's lectures about artificial intelligence, I currently have one question: why don't we use autoencoders instead of GANs? Basically, what GAN does is it receives a random vector ...
2
votes
1answer
44 views

Does the bag-of-visual-words method improve the classification accuracy?

I'm a beginner in computer vision. I want to know which option among the following two can get better accuracy of image classification. SIFT features + SVM Bag-of-visual-words features + SVM Here's ...
1
vote
0answers
11 views

What is a wavefront algorithm?

I am designing and researching algorithms which I call of a wavefront nature. It is image analsyis agorithms when every pixel may change many times during the processing. I have heard this name before,...
1
vote
0answers
19 views

How do you make a regression model from a binary labeled dataset?

Suppose I have a dataset with hand images. Hand completely opened is labeled as 0 and hand completely closed (fist) are labeled as 1. I also have a bunch of unlabeled images of hands which, if ...
1
vote
0answers
38 views

Would it be possible to use AI to measure pupil dilation diameters and fluctuation, on video films on a regular webcam?

I've been researching the topic of Cognitive Load Measurement through pupil dilation measurement. All solutions to pupil dilation measurement require some kind of special hardware setup. I was ...
3
votes
1answer
143 views

How to keep track of the same person detected in different frames of a camera?

At this moment, I am able to use NN to identify an object, such as a human, when given a frame from the camera. Once locate the object, then I can feed the human object image to either NN that's ...
2
votes
1answer
412 views

How does non-max suppression work when one or multiple bounding boxes are predicted for the same object?

My understanding of how non-max suppression works is that it suppresses all overlapping boxes that have a Jaccard overlap smaller than a threshold (e.g. 0.5). The boxes to be considered are on a ...
2
votes
1answer
130 views

Understanding a paragraph about object detection with two objects

I was reading this article on detecting rectangles in an image. My doubt is in the part where the model works fine with detecting a single object, but struggles with two rectangles detection. The ...
3
votes
1answer
72 views

How to draw bounding boxes for gender classification?

I wonder what is the better way of drawing rectangles on images for gender classification. My task is to create a classifier (CNN based) to detect gender from pictures of entire bodies (not just faces)...
1
vote
0answers
30 views

How do non-local neural networks relate to attention and self-attention?

I've been reading non-local neural networks as explained in the original paper. My understanding is that they solve the restrained reception of local filters. I see how they are different from ...
1
vote
1answer
382 views

YOLO Architecture - kmeans clustering [closed]

In YOLO, why use k-means clustering to determine bounding-box priors ? Why if we use standard k-means with Euclidean distance, larger boxes generate more error than smaller boxes? Why using IOU (...

1 2 3
4
5
9