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
0answers
9 views

How to use machine learning to create combine of opposite images side by side

Inspired by: Two Worlds Pictures I just want to create a Machine Learning Model that can automatically combine the opposite images into 1 image. I am thinking about 2 possible solutions: Pose ...
2
votes
2answers
61 views

Why do we get a three-dimensional output after a convolutional layer?

In a convolutional neural network, when we apply the convolution on a $5 \times 5$ image with $3 \times 3$ kernel, with stride $1$, we should get only one $4 \times 4$ as output. In most of the CNN ...
4
votes
1answer
66 views

Aesthetics analysis with deep learning

I'm trying to score video scenes in terms of aesthetics and cinematography features. Basically, how "interesting" a scene or video frame can be for a viewer. Simpler, how attractive a scene is. My ...
5
votes
1answer
32 views

Video summarization similar to Summe's TextRank

We have the popular TextRank API which given a text, ranks keywords and can apply summarization given a predefined text length. I am wondering if there is a similar tool for video summarization. ...
2
votes
1answer
126 views

What is the difference between 2d vs 3d convolutions?

I was trying to understand the definition of 2d convolutions vs 3d convolutions. I saw the "simplest definition" according to Pytorch and it seems the following: 2d convolutions map $(N,C_{in},H,W) \...
2
votes
0answers
22 views

How can I detect fast and slow motion in videos?

I'm trying to detect if a given video shot is fast or slow motion. Basically, I need to calculate a "video motion" score in a given video sequence, meaning how fast or slow motion the video is. For ...
3
votes
2answers
133 views

How should we pad an image to be fed in a CNN?

As everyone experienced in deep learning might know, in an image classification problem we normally add borders to images then resize it to the input size of a CNN network. The reason of doing this is ...
3
votes
2answers
79 views

Untrained CNNs as feature extractors?

I've heard somewhere that due to their nature of capturing spatial relations, even untrained CNNs can be used as feature extractors? Is this true? Does anyone have any sources regarding this I can ...
3
votes
0answers
17 views

Reverse engineering controller sensitivity/aim for several games ie acceleration curves, deadzones, etc

A machine learning project I am working on requires me to interface with an Xbox controller connected to a PC. The implementation must do the following two things: Record the joystick input from the ...
2
votes
0answers
17 views

Can Microsoft's cognitive service find similar person in a set of images without using the face service?

I need to create an application that can detect if a person X entered as an input exists in an image set and return as output all the images in which the person X exists. The problem is that the ...
3
votes
0answers
66 views

Does Retina-net's focal loss accomplish its goal?

Taking out the weighting factor we can define focal loss as $$FL(p) = -(1-p)^\gamma log(p) $$ Where $p$ is the target probability. The idea being that single stage object detectors have a huge ...
2
votes
0answers
24 views

Extracting Descriptors and feature points for 3d mesh

I'm programming my work with python, and I have a mesh and I want to extract 3d descriptors and feature points from it( trying to work on multi-scale strategy) , to visualize them later on the mesh, ...
2
votes
1answer
183 views

What does the words “coarse” & “fine” means in the context of computer vision and semantic segmentation?

I was reading the well know paper Fully Convolutional Networks for Semantic Segmentation and throughout the whole paper they talk use the term fine and coarse. I was wondering what the meant. The ...
1
vote
1answer
42 views

How do I identify the number and type of objects in the same picture?

I need to identify the number and type of all objects in a picture, so there can be multiple objects of the same type. For example, I have a picture with $10$ animals, and I want my program to tell ...
0
votes
0answers
24 views

How can I convert the annotations produced by LabelImg to labels for Yolov2?

I was recommended to use LabelImg to create annotation labels for YOLOv2. However, the annotations look something like this: 4 0.517500 0.597500 0.915000 0.735000 (classes and 4 coordinates x,y,w,h)...
3
votes
1answer
27 views

Is this technique image processing or computer vision?

If I use my mobile camera on a signboard or announcement board on a road or in a street (like the one attached in photo) where the message is written in Russian and my mobile shows me that message in ...
3
votes
1answer
84 views

What is the difference between image processing and computer vision?

What is the difference between image processing and computer vision? They are apparently both used in artificial intelligence.
0
votes
0answers
27 views

When should I stop the object detection model training while mAP are not stable?

I am re-training the SSD MobileNet with 900 images from the Berkeley Deep Drive dataset, and eval towards 100 images from that dataset. The problem is that after ...
2
votes
1answer
48 views

What is “dense” in DensePose?

I've recently come across an amazing work for human pose estimation: DensePose: Dense Human Pose Estimation In The Wild by Facebook. In this work, they have tackled the task of dense human pose ...
1
vote
0answers
425 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
248 views

YOLO Architecture - kmeans clustering

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 (...
2
votes
1answer
54 views

Are there any better visual models for transfer rather than ImageNet?

Similar to the recent pushes in Pretrained Language Models (BERT, GPT2, XLNet) I was wondering if such a thrust exists in Computer Vision? From my understanding, it seems the community has converged ...
1
vote
0answers
36 views

Understanding average precision (AP) in measuring object detector performance

I am trying to understand the average precision (AP) metrics in evaluating the performance of deep-learning based object detection models. Suppose we have the following ground true (four objects ...
1
vote
0answers
72 views

YOLO architecture

1) How (Is it possible) to combine Fast-RCNN (2-stage) and YOLO (1-stage)? 2) Why with the addition of anchor boxes we changed the resolution to 416 x 416? Why using anchor boxes we get a small ...
2
votes
1answer
167 views

How does ARKit's Facial Tracking work?

iPhone X allows you to look at the TrueDepth camera and reports 52 facial blendshapes like how much your eye is opened, how much your jaw is opened, etc. If I want to do something similar with other ...
1
vote
2answers
352 views

Autoencoder for MobileNetV2

I have way more unlabeled data than labeled data. Therefore I would like to train an Autoencoder using MobileNetV2 as the encoder. Then I will use the pretrained model for the classification of the ...
0
votes
1answer
64 views

What is wrong with this CNN network, why are there hot pixels?

I'm building a CNN decoder, which mirrors (in reverse) the VGG network structure from Conv-4-1 layer. The net seems to be working fine, however, the output looks broken. Please note that the colour ...
2
votes
1answer
34 views

Which API can I use for tracking the position of animal in one or more images?

I'd like to build an application for tracking the position of a given animal (e.g. a cat) in a series of images. Is there any off-the-shelf API I could use? Azure has some Vision APIs, but it seems ...
2
votes
0answers
38 views

Object size identification and maximum number of classes with convolutional neural networks

I am working on a project that involves using a ConvNet to identify screws. I am able to train from scratch a ConvNet based on the first version of the inception network, but shallower (only 3 ...
2
votes
0answers
32 views

Estimate distance between points in perspective image

I am trying to estimate the real world distance (in metres) between two points in a perspective image using an uncalibrated camera. However, the dimensions of an object in the image are known. I ...
0
votes
0answers
77 views

Can we use Autoencoders for unsupervised CNN feature learning?

I searched through the internet but couldn't find a reliable article that answers this question. Can we use Autoencoders for unsupervised CNN feature learning of unlabeled images like the below and ...
3
votes
1answer
135 views

Object IN/OUT counting using CNN+RNN

I am building a video analytics program for counting moving things in a video. I am detecting bicycles and nothing else. I run object detection using the SSD mobile-net model in all the frames and ...
1
vote
0answers
45 views

Transposed convolution as upsampling in DCGAN

I read several papers and articles where it is suggested that transposed convolution with 2 strides is better than upsampling then convolution. However implementing such model with the transposed ...
4
votes
1answer
148 views

Name of paper for encoding/representing XY coordinates in deep learning

It this podcast between Oriol Vinyals and Lex Friedman: https://youtu.be/Kedt2or9xlo?t=1769, at 29:29, Oriol Vinyals refers to a paper: If you look at research in computer vision where it makes a ...
2
votes
1answer
91 views

Is there any other rotated object detection datasets?

I have googled for a long time for rotated object detection datasets. Most of papers focused on rotated object detection using DOTA, HRSC2016 or coco text detection dataset. Some researcher also ...
5
votes
2answers
355 views

Why is image recognition a key function of AI?

Image recognition, in the context of machine vision, is the ability of software to identify objects, places, people, writing and actions in images. Computers can use machine vision technologies in ...
4
votes
0answers
40 views

How do I denoize a microscopic image?

I'm working in a computer vision project, where the goal is to detect some specific parasites, but now that I have the images, I noticed that they have a watermark that specifies the microscope ...
4
votes
1answer
147 views

Which loss function is the brain optimizing in order to learn advanced visual skills without expert/human supervision?

In computer vision is very common to use supervised tasks, where datasets have to be manually annotated by humans. Some examples are object classification (class labels), detection (bounding boxes) ...
3
votes
2answers
105 views

Do we also need to model a probability distribution for the decoder of a VAE?

I'm working on understanding VAEs, mostly through video lectures of Stanford cs231n, in particular lecture 13 tackles on this topic and I think I have a good theoretical grasp. However, when looking ...
1
vote
2answers
58 views

Detecting abnormalities in x-rays while taking into account demographics of a patient -automated

This is my first post so please forgive me for any mistakes. I am working on an object detection algorithm that can detect abnormalities in an x-ray. As a prototype, I will be using yolov3 (more ...
0
votes
0answers
30 views

Next step after lane detection in vehicle automation

I have an RC car with a camera, I have implemented so that i can detect lanes on my track (think like a nascar track). I want to get this car to be able to go around the track autonomous. But I am ...
3
votes
0answers
208 views

YOLO v3 complete architecture

I am attempting to implement YOLO v3 in Tensorflow-Keras from scratch, with the aim of training my own model on a custom dataset. By that, I mean without using pretrained weights. I have gone through ...
1
vote
0answers
44 views

Image-Specific Class Saliency Visualisation

In the paper "Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps", https://arxiv.org/abs/1312.6034, at part 3, there is a first-order Taylor expansion(...
1
vote
0answers
33 views

Live video object detection with pose estimation

I was researching about hierarchical object detection, and end up reading that Yolo v3 is the state of art for that kind of tasks, besides, the inference time make it one of the best for run it on ...
0
votes
0answers
16 views

how to work with multi-labels or two inputs and a output

I’m in this problem and haven’t found a sound solution to it. Been like 20 days now. I have a dataset that looks like this: ...
0
votes
0answers
98 views
0
votes
0answers
27 views

What are the reference papers of image captioning model 'all_img', 'att2in2', 'adaattmo' and 'topdown'?

I Want to cite the reference paper of The models appeared in this webpage: https://github.com/ruotianluo/ImageCaptioning.pytorch/blob/master/models/init.py But which papers do these four models '...
2
votes
1answer
39 views

How could we estimate the square footage of a room from an image?

I wonder if it would be possible to know the size of a room using image, I don't see anything about this subject, do you have some idea how it could be done?
1
vote
0answers
85 views

Siamese Network for unknown object

I am currently trying to create a One-Shot network using the Siamese architecture for an object that isn't a face. My problem is, in normal Face Recognition the detecting gadget (e.g. Smartphone) ...
2
votes
2answers
807 views

Why does a fully connected layer only accept a fixed input size?

I'm studying how SPP (Spatial, Pyramid, Pooling) works. SPP was invented to tackle the fix input image size in CNN. According to the original paper https://arxiv.org/pdf/1406.4729.pdf, the authors say:...