We’re rewarding the question askers & reputations are being recalculated! Read more.

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
1answer
84 views

How do I segment each part of a DICOM image?

As I'm beginner in image processing, I am having difficulty in segmenting all the parts in DICOM image. Currently, I'm applying watershed algorithm, but it segments only that part that has tumour. ...
4
votes
2answers
92 views

What are applications of object/human tracking in autonomous cars?

Objects tracking is finding the trajectory of each object in consecutive frames. Human tracking is a subset of object tracking which just considers humans. I've seen many papers that divide tracking ...
2
votes
2answers
450 views

How to architect a network to find bounding boxes in simple images

I have an application where I want to find the locations of objects on a simple, relatively constant background (fixed camera angle, etc). For investigative purposes I've created a test dataset which ...
1
vote
1answer
2k views

Counting people in an image of a crowd

What are some good approaches that I can use to count the no. of people in a crowd. Tracking each person individually is obviously not an option. Any good approaches or some references to research ...
5
votes
2answers
201 views

Can one use an Artificial Neural Network to determine the size of an object in a photograph?

My question relates to but doesn't duplicate a question that has been asked here. I've Googled a lot for an answer to the question: Can you find the dimensions of an object in a photo if you don't ...
3
votes
1answer
150 views

What exactly does “channel” refer to in tensorflow/lucid?

Tensorflow/Lucid is able to visualize what a "channel" of a layer of a neural network (image recognition, Inception-v1) responds to. Even after studying the tutorial, the source code, the three ...
3
votes
1answer
255 views

Alternative to sliding window neural network (was: Object detect (or) image classification at specific locations in the frame)

Recent advances in Deeplearning and dedicated hardware has made it possible to detect images with a much better accuracy than ever. Neural networks are the gold standard for computer vision ...
4
votes
1answer
725 views

Training a CNN from scratch over COCO dataset

I am using Tensorflow Object Detection API for training a CNN from scratch on COCO dataset. I need to use this specific configuration. There is no pre-trained model on COCO with that configuration and ...
4
votes
2answers
124 views

What is the best approach for writing a program to identify objects in a picture then crop them a specific way?

My works quality control department is responsible for taking pictures of our products at various phases through our QC process and currently the process goes: Take picture of product Crop the ...
0
votes
1answer
146 views

How to label “other” while labeling image for object detection/classification?

I want to train a model to recognize different category of food (example: rice, burger, apple, pizza, orange,... ) After the first training, I realized that the model is detecting other object as ...
1
vote
0answers
26 views

Difference in trained models between GCP's Google Vision and Firebase's ML kit?

Anyone here know if the image-recognition/text-recognition/etc features of Google Vision API use the same trained models as the image-recognition/text-recognition/etc of Firebase's ML kit? If they don'...
1
vote
1answer
552 views

How to label training data for YOLO

I am having a question on how to label training data for YOLO algorithm. Let's say that each label Y, we need to specify [Pc, bx, by, bh, bw], where Pc is the indicator for presence(1=present, 0=not ...
2
votes
1answer
52 views

Are there benchmarks for assessing the speed of the forward-pass of neural networks?

I have a task where I would like to use a convolutional neural network (CNN). I would like to incrementally start from the fastest models, fine-tune and see whether they fit my "budget". At the moment,...
2
votes
1answer
22 views

How to quantify the reflectance in an image?

I am working on a problem where I have to train a CNN to recognize different kinds of surfaces. One important characteristic of the surfaces I am interested is is how reflective they are. I have been ...
2
votes
1answer
27 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 ...
4
votes
2answers
251 views

Wrong usage of 'Pose' in Matrix Capsules with EM?

In traditional computer vision and computer graphics, the pose matrix is a 4x4 matrix of the form ...
1
vote
2answers
82 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 ...
-2
votes
1answer
96 views

GPU to train object recognition neural networks

I'm starting to play around with python neural networks, mainly for object recognition like this one: https://github.com/huangshiyu13/RPNplus. I plan to train more networks with more kinds of objects. ...
8
votes
3answers
251 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 ...
6
votes
3answers
171 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 ...
4
votes
2answers
99 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
56 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
40 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
300 views

VAE image reconstruction question?

Is it possible to use a VAE to reconstruct and image starting from an initial image instead of using K.random_normal as show in the “sampling” function of this example? I have used a sample image ...
4
votes
1answer
1k views

What are some tools for labelling images and videos?

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? (...
5
votes
1answer
163 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, and am currently choosing what type of algorithm to use for my classifier - a neural net, or a ...
4
votes
1answer
233 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
256 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
1answer
82 views

Extracting one class from a pretrained Convolutional Neural Network

I am new to deep learning and computer vision. I have a problem where i use yolo algorithm (https://pjreddie.com/) to detect objects. In the original paper, they define the output to recognize 80 ...
1
vote
0answers
24 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/ ...
5
votes
2answers
221 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
430 views

JavaScript Client Side GAN implementation

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 ...
4
votes
1answer
192 views

Other Deep Learning Networks 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 ...
2
votes
1answer
32 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 ...
3
votes
1answer
413 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 ...
2
votes
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 ...
2
votes
3answers
1k views

What activation function is not used at the final layer of super resolution neural 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 layer for the last layer. What'...
2
votes
1answer
69 views

Computing a “prominence score” (Computer Vision)

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
64 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 ...
1
vote
0answers
40 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. ...
7
votes
1answer
3k views

Confusion regarding anchor boxes in YOLO

I'm going through Andrew NG's course which talks about YOLO but he doesn't go into the implementation details of anchor boxes. Look through the code, each anchor box is represented by two values, but ...
2
votes
0answers
171 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
60 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 ...
1
vote
2answers
120 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
1answer
275 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 ...
2
votes
1answer
109 views

Tracking object

At this moment, I am able to use NN to identify object such as 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 designed to ...
3
votes
1answer
857 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 : 1) Pixel based object recognition: Neural networks are trained to locate individual objects based directly on pixel data. 2) ...
1
vote
1answer
33 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 ...
10
votes
3answers
10k 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
35 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 (...