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
2
votes
1answer
31 views

Structured lighting basic principles for depth mapping

I've been wondering, how, in the most simple-to-implement basic principle, does the light projection to depth map technique described here https://www.lightform.com/how-it-works actually functions? Is ...
5
votes
2answers
324 views

Is the word “pose” used correctly in the paper “Matrix Capsules with EM Routing”?

In traditional computer vision and computer graphics, the pose matrix is a $4 \times 4$ matrix of the form $$ \begin{bmatrix} r_{11} & r_{12} & r_{12} & t_{1} \\ r_{21} & r_{...
1
vote
2answers
314 views

Normalization for well known data sets like coco-text and total text data set

In the data-sets like coco-text and total-text, the images are of different sizes (height*width). I'm using these data sets for text detection. I want to create a DNN model for this. So input data ...
9
votes
3answers
365 views

Detect visual attention area in an image

I'm trying to detect the visual attention area in a given image and crop the image into that area. For instance, given an image of any size and a rectangle of say LxW dimension as an input, I would ...
2
votes
1answer
1k views

How can I detect thin objects (like pens and pencils) without a bounding box but only 2 endpoints and the orientation?

I am looking to detect thin objects, like pens, pencils, and surgical instruments. The bounding box is not important, but I am looking to see if I can train a model to detect both the object as well ...
7
votes
3answers
336 views

How to use computer vision to find corners of a soccer field based on location coordinates?

I want to use computer vision to allow my robot to detect the corners of a soccer field based on its current position. Matlab has a detectHarrisFeatures feature, but I believe it is only for 2D ...
2
votes
1answer
572 views

How are IOUs for ground truth boxes in YOLO calculated?

I know how IOU works during detection. However, while preparing targets from ground-truth for training, how is the IOU between a given object and all anchor boxes calculated? Is the ground truth ...
4
votes
2answers
118 views

Kalman filter pre inovation

I am trying to track LIDAR objects using Kalman filter. The problem is that the innovation has the value 0, which makes the Kalman gain be Infinity. Here is a link with the Kalman equations. The ...
1
vote
1answer
63 views

Given a query image Q and two other images X and Y, how to determine which one is most similar to Q?

Given a query image Q and two other images X and Y (you can assume they have more or less the same resolutions if that simplifies the problem), which algorithm would perform extremely well at ...
1
vote
0answers
46 views

How to combine heterogeneous image features extracted with different algorithms for similar image retrieval?

Say I have access to several pre-trained CNNs (e.g. AlexNet, VGG, GoogleLeNet, ResNet, DenseNet, etc.) which I can use to extract features from an image by saving the activations of some hidden layer ...
3
votes
2answers
564 views

How to use a VAE to reconstruct an image starting from an initial image instead of starting from a random vector?

Is it possible to use a VAE to reconstruct an image starting from an initial image instead of using K.random_normal, as shown in the “sampling” function of this ...
4
votes
1answer
2k views

What are some tools for labelling images and videos? [closed]

I am looking for AI tools for image and video labeling. It would be great if someone could share its own experience as well suggest tools. I also have some questions Which tools are available? (...
6
votes
1answer
223 views

Why does nobody use decision trees for visual question answering?

I'm starting a project that will involve computer vision, visual question answering, and explainability. I am currently choosing what type of algorithm to use for my classifier - a neural network or a ...
0
votes
1answer
1k views

Can YOLO detect large objects?

I have a rather basic question about YOLO for bounding box detection. My understanding is that it effectively associates each anchor box to an 8-dimension output. During testing, does YOLO take each ...
4
votes
1answer
701 views

What are the minimum computing resources needed to train a machine learning algorithm?

For a school project, I would like to investigate a paper on either reinforcement learning or computer vision. I am particularly interested in DQN, RNNs, CNNs or LSTMs. I would eventually like to ...
6
votes
3answers
284 views

Has anybody tried unsupervised deep learning from youtube videos?

YouTube has a huge amount of videos, many of which also containing various spoken languages. This would presumably provide something like the data that a "challenged" baby would experience - "...
1
vote
0answers
26 views

Commercial API Q: is there an api for converting vision tags into a caption?

There are many machine learning api for scanning images but they just return a bunch of tags. https://azure.microsoft.com/en-gb/services/cognitive-services/computer-vision/ ...
6
votes
2answers
461 views

Algorithms for scene rotation

My goal is to take an image and return another image that looks as if the scene was viewed from another angle. The difference in angle can be small — let's say as if the hand holding the camera moved ...
2
votes
1answer
601 views

JavaScript Client Side GAN implementation [closed]

Recently I came across this website which is a year old: https://affinelayer.com/pixsrv/ On Desktop we can draw and download the trained model in browser and see the corresponding image generated on ...
6
votes
1answer
269 views

Which neural networks are suitable for visual place recognition?

I am doing a project on visual place recognition in changing environments. The CNN used here is mostly AlexNet, and a feature vector is constructed from layer 3. Does anyone know of similar work ...
3
votes
1answer
37 views

Executing trained image classification model for video

I've been working with vanilla feed forward neural networks and have been researching the convolutional neural network literature. Thus far I've have not encountered how often the model is executed in ...
4
votes
1answer
802 views

Training a Yes/No NN for Image Classes

I am fairly a newbie to Neural Networks. I wanted to ask if it is possible to train a NN to identify only one type object? For instance, a table from a large set of images, where the NN should be able ...
1
vote
2answers
3k views

Training an AI to play Starcraft 2 with superhuman level of performance?

I'm interested in working on challenging AI problems, and after reading this article (https://deepmind.com/blog/deepmind-and-blizzard-open-starcraft-ii-ai-research-environment/) by DeepMind and ...
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. ...
3
votes
1answer
84 views

Is there a way of computing a prominence score based on the prevalence of features in an image?

Is there any previous work on computing some sort of prominence score based on the prevalence of features in an image? For example, let's say I am classifying images based on whether or not they have ...
1
vote
0answers
73 views

Data extraction from medical reports

I am new in Machine Learning. I have taken a course in vision and we are required to do a project. I am thinking of data mining medical lab report images. My code must take an image and jpg file ...
2
votes
1answer
62 views

Continuous ground truth in supervised (metric) learning?

I am writing my thesis in the field of (deep) metric learning (DML). I am training a network in the fashion of contrastive / triplet Siamese networks to learn similarity and dissimilarity of inputs. ...
9
votes
1answer
3k views

In YOLO, what exactly do the values associated with each anchor box represent?

I'm going through Andrew NG's course, which talks about YOLO, but he doesn't go into the implementation details of anchor boxes. After having looked through the code, each anchor box is represented by ...
2
votes
0answers
198 views

Extracting specific features using HOG

I am using HOG (Histogram of Oriented Gradients) for car detection from a video. I have used the Matlab function extractHOGFeatures() , it has given me a feature ...
1
vote
2answers
66 views

Searching an AI to recognize and locate persons in a factory

TLDR : Is there an AI available that can recognize employees in a factory and tell when they entered and left pre-defined areas? I work in a factory where we gather cycle time data from various ...
2
votes
3answers
161 views

Neural Network that Predicts Game State Based on Actions

I am trying to find literature on a network architecture that takes the following as in input: Action (like 'Up', 'Down', etc) Image of current state and outputs: Image of next state I already ...
2
votes
2answers
534 views

Is it possible to count the number of squats with Computer Vision techniques?

I am planning to build an app which will count the number of sqauts from videos. Assuming that the user and camera do not move, are there ways I can count the number of squats? Do such models to ...
3
votes
1answer
136 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 ...
3
votes
1answer
1k views

What is the difference between pixel-based object recognition and feature-based object recognition?

From my understanding and text I found in research papers online : Pixel-based object recognition: neural networks are trained to locate individual objects based directly on pixel data. Feature-based ...
1
vote
1answer
34 views

Could a multi-camera SLAM system that is accurate at low driving speeds be equally accurate at high driving speeds?

Could a multi-camera SLAM system for self-driving cars that is accurate to under 10 cm (3.9 in) at parking lot speeds (i.e. very low driving speeds) retain this level of accuracy at high driving ...
12
votes
3answers
18k views

Measuring Object size using Deep Neural Network

I have a large dataset of vehicles with the ground truth of their lengths (Over 100k samples). Is it possible to train a deep network to measure/estimate vehicle length ? I haven't seen any papers ...
2
votes
0answers
48 views

Detecting symmetry in small images with RNN

My network works on 32x32 normalized (translationally) but noisy images. Its task it to determine whether image has simple symmetry (horizontal/vertical). It needs to be reasonably robust to rotation (...
2
votes
1answer
128 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 ...
2
votes
0answers
57 views

How do cognitive services work?

Currently big tech companies like Microsoft, Google, and Amazon (to name a few) offer cognitive services on their cloud platforms. With these services it is possible to identify faces, objects, texts,...
6
votes
1answer
1k views

Can reinforcement learning algorithms be applied to computer vision problems?

Can reinforcement learning algorithms be applied to computer vision problems? If yes, what are some examples of these applications?
3
votes
2answers
314 views

Is there a computer vision service for classifying images on a fixed array of images provided by me?

I was checking services like Microsoft Azure's Cognitive Services Computer Vision API and Google's Vision API and they are amazing. I was wondering if these services, or any other cloud service for ...
7
votes
1answer
119 views

What algorithms are used for segmentation and classification of non solid regions in an image?

In the process of segmentation, pixels are assigned to regions based on features that distinguishes them from the rest of the image. Value Similarity and Spatial Proximity, for example, are two ...
5
votes
1answer
173 views

Is it feasible to train a Machine Learning Model (with image inputs) in an average personal computer?

There are lots of examples of machine learning systems that can recognize objects and extract other information from images with very high precision. To train the models of such systems is necessary (...
5
votes
1answer
712 views

Precise localization and characterization of rudimentary shapes with neural networks

I understand that there are flavors of (convolutional) neural networks that are useful for object localization and detection tasks of reasonable difficulty. In all of the examples I have seen so far, ...
1
vote
1answer
60 views

Can I limit the possible choices for a computer vision framework to recognize?

To risk giving away too much info, im building a piece of hardware with the job of identifying the object in front of it. If it can only be one of three different items, how can I tell the computer ...
4
votes
1answer
768 views

Image comparison algorithm, trying to figure out how similar two “binary” forms are

I'm a student I'm completely new to this technology maybe my approach could be completely wrong, I want to create an algorithm that compares the similarity between two binarized images. I'll explain: ...
4
votes
1answer
106 views

Can augmented reality be a training system for computer vision?

Is augmented reality a training system for computer vision? As in, Augmented systems use their data to help train computer vision algorithms, or is augmented reality computer vision itself?
0
votes
2answers
3k views

Is it possible to run SSD or YOLO object detection on Raspberry Pi 3 for live object detection?

Is it possible to run SSD or YOLO object detection on Raspberry Pi 3 for live object detection (2/4frames x second)? I've tried this SSD implementation but it takes 14 s per frame. Is there anything I ...
2
votes
1answer
591 views

Why do action recognition algorithms perform better on ucf101dataset than HMDB51 dataset?

If we look at state of the art accuracy on the UCF101 data set, it is around 93% whereas for the HMDB51 data set it is around 66%. I looked at both the data sets and both contain videos of similar ...
5
votes
1answer
122 views

Use ConvNet to predict bitmap

I want to build a classifier which takes an aerial image and outputs a bitmap. The bitmap is supposed to be 1 at every pixel where the aerial image has water. For this process I want to use a ConvNet ...

1
5 6 7
8
9