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.

112 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
15
votes
1answer
942 views

Are information processing rules from Gestalt psychology still used in computer vision today?

Decades ago there were and are books in machine vision, which by implementing various information processing rules from gestalt psychology, got impressive results with little code or special hardware ...
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. ...
5
votes
1answer
209 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 ...
4
votes
0answers
27 views

How can I improve the performance of a model trained to detect vehicle poses?

I'm looking for some suggestions on how to improve our vehicle image recognition. We have an online marketplace where customers submit photos of their vehicles. The photos need to meet certain ...
4
votes
0answers
94 views

Extending FaceNet’s triplet loss to object recognition

FaceNet uses a novel loss metric (triplet loss) to train a model to output embeddings (128-D from the paper) such that any two faces of the same identity will have a small Euclidean distance, and such ...
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
224 views

Point A to B Avoidance

I understand A* and Dijkstra for avoiding obstacles, they require that points are traversable there are points that are not traversable thus the algorithms wont bump into the obstacles because the ...
3
votes
0answers
125 views

Understanding the results of “Visualizing and Understanding Convolutional Networks”

I am trying to understand the results of the paper Visualizing and Understanding Convolutional Networks, in particular the following image: What are these 3x3 blocks and their 9 cells representing? ...
3
votes
1answer
42 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)...
3
votes
0answers
15 views

Size of image input of neural networks while resizing may not be appropriate

I have the following problem while using convolutional neural networks to detect forgeries: Resizing the image to fit the required input size may not be a good way because the forgery detection ...
3
votes
0answers
49 views

Ideas on a network that can translate image differences into motor commands?

I'd like to design a network that gets two images (an image under construction, and an ideal image), and has to come up with an action vector for a simple motor command which would augment the image ...
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 ...
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 ...
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 ...
3
votes
1answer
367 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 ...
2
votes
0answers
16 views

Detect object in video and augment another video on top of it

I'm trying to detect an object in a video (with slight camera movement), and then augment another video on top of it. What is the simplest approach to do that? For instance, let's assume I have this ...
2
votes
0answers
20 views

How is visual attention mechanism different from a two branch convolutional neural network?

I am doing some research on the visual attention mechanism in remote sensing domain (where the features learnt from one layer are highlighted using the attention mask derived from another layer). From ...
2
votes
0answers
17 views

Merge two different CNN models into one

I have 2 different models with each model doing a separate function and have been trained with different weights. Is there any way I can merge these two models to get a single model. If it can be ...
2
votes
0answers
28 views

Creating Dataset for Image Classification

I want to develop a CNN model to identify 24 hand signs in American Sign Language. I created a custom dataset that contains 3000 images for each hand sign i.e. 72000 images in the entire dataset. For ...
2
votes
0answers
24 views

Is there an efficient way of determining the layers with the best performance as feature extractors in GoogleNet?

I am using a caffe model of pre-trained GoogleNet trained on ImageNet from here for image retrieval task (place recognition, more specifically). I would like to know the layer with best performance ...
2
votes
0answers
21 views

Suitable algorithms for classifying terrain condition (asphalt, dirt etc) for motor vehicles

I am required to obtain data through a sensor located on the vehicle reading speed, vibration, roll and tilt, within a sample time, to classify the current road condition using machine learning for a ...
2
votes
0answers
44 views

Does a fully convolutional network share the same translation invariance properties we get from networks that use max-pooling?

Does a fully convolutional network share the same translation invariance properties we get from networks that use max-pooling? If not, why do they perform as well as networks which use max-pooling?
2
votes
0answers
20 views

What are the current tools and techniques for image segmentation in order of pragmatism?

To explain what I mean I'll depict the two extremes and something in the middle. 1) Most pragmatic: If you need to just segment a few images for a design project, forget AI. Go into Adobe Photoshop ...
2
votes
1answer
178 views

How feasible is it to perform pose estimation on a Raspberry Pi 4 using a Pi-Cam?

I want to estimate hand poses and recognize gestures using an open-source library like OpenPose on live video. Considering the fact that such libraries are very computationally intensive. How likely ...
2
votes
1answer
38 views

When training a CNN, what are the hyperparameters to tune first?

I am training a convolutional neural network for object detection. Apart from the learning rate, what are the other hyperparameters that I should tune? And in what order of importance? Besides, I read ...
2
votes
1answer
45 views

Semantic Segmentation For Multiple Objects When Trained On Single Object

More of a conceptual question here: I'm working on semantic segmentation tasks in the medical space using the U-Net. Let's say that I train a U-Net model on medical images with the goal of segmenting ...
2
votes
2answers
84 views

What is the reasoning behind the number of filters in the convolution layer?

Let's assume an extreme case in which the kernel of the convolution layer takes only values 0 or 1. To capture all possible patterns in input of $C$ number of channels, we need $2^{C*K_H*K_W}$ filters,...
2
votes
0answers
16 views

Can an image recognition model used for human pose estimation?

I am currently writing my thesis about human pose estimation and wanted to use Google's inception network, modify it for my needs and use transfer learning to detect human key joints. I wanted to ask ...
2
votes
0answers
24 views

SLAM versus “STAM” in vision

In the paper 'Visual SLAM algorithms: a survey from $2010$ to $2016$' by Takafumi Taketomi, Hideaki Uchiyama and Sei Ikeda it is mentioned 'It should be noted that tracking and mapping (TAM) is used ...
2
votes
0answers
16 views

Ghost camera or video overlays for example in sports

Secondary camera, ghost overlay, video merge... I do not know if what I mean has a more specific name. I wonder if this is a thing. This could be insightful for example in racing sports where ...
2
votes
1answer
62 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 ...
2
votes
0answers
98 views

Is there a dataset for the detection of bomb explosions?

I would like to train a deep neural network to recognize bomb explosions. I was wondering if there is an open visual dataset for bomb explosion? Alternatively, if you know a good deep architecture or ...
2
votes
0answers
21 views

Confidence Maps and Non-Linearity

I am currently trying to improve a CNN architecture that was proposed for generating depth images. The architecture was originally proposed for autonomous driving and it looks like following : The ...
2
votes
1answer
60 views

What should load_mask() return if an image doesn't have any objects? (Mask RCNN)

I want to use Mask RCNN to do image segmentation. I need to override the load_mask function for the dataset class. I know this function should return mask tensors and class ids of objects in an image. ...
2
votes
0answers
28 views

How to implement fisherface algorithm and how much time will it take?

I found on the web that fisherface is the best algorithm for face detection. Before investing deeply into it, I just want to know how hard is it to implement it and how much time will it take. I am ...
2
votes
0answers
25 views

How do I generate structured light for the 3D bin picking system?

I want to know how to generate the structured light which projects different patterns of light on a 3D object which is under scanning.
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
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 ...
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 ...
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
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 ...
2
votes
0answers
25 views

Calculating tangent vector of curve s(P,$\alpha$) at given point $\alpha$ = 0

I am reading the paper "Transformation Invariance in Pattern Recognition – Tangent Distance and Tangent Propagation", where the tangent vector is calculated for the given curve $s(P,\alpha)$ at $\...
2
votes
0answers
32 views

Presence of object (highly occluded vehicle) in a scene

How to detect presence of object (highly occluded) in a scene? There are specific features (small patterns, etc), which allow to say that object is present, but it is not enough for detection for ...
2
votes
0answers
22 views

Is there any deep learning object detection algorithms that can work without bounding boxes annotated data?

For example Haar Cascade can be trained using only positive and negative examples, you don't need any bounding box annotations. But it not a deep learning approach. Another example can be the most ...
2
votes
0answers
23 views

How exactly is equivariance achieved in capsule networks?

I have read quite a lot about capsule networks but cannot understand how the squashed vector would also rotate in response to rotation or translation of the image.A simple example would be helpful.I ...
2
votes
0answers
189 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 ...
2
votes
2answers
136 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
0answers
37 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
0answers
55 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,...