Page Not Found
Page not found. Your pixels are in another canvas.
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Page not found. Your pixels are in another canvas.
We harness Artificial Intelligence to make robust and sustainable solutions for problems in society.
The official blog site of Computer Vision and Intelligence Group, IIT Madras
We harness Artificial Intelligence to make robust and sustainable solutions for problems in society.
We harness Artificial Intelligence to make robust and sustainable solutions for problems in society.
We harness Artificial Intelligence to make robust and sustainable solutions for problems in society.
We harness Artificial Intelligence to make robust and sustainable solutions for problems in society.
In this post, we shall explain how you can get started with our containers - for either python, deep learning, computer vision or probabilistic modelling.
Now that we’re done with the first session and the basics of Computer Vision and OpenCV, we have some problem statements for you to delve into. Do go through...
Session 1: Introduction to Computer Vision
Thank you for the wonderful participation yesterday at PySangamam 2018.
Yet Another Hackathon (YAH!) 2018
We are pleased to announce that 3 of our talk proposals from the Computer Vision and Intelligence group (CVI) have been selected as a part of PySangamam 2018.
Recurrant Neural Networks
An introduction to Convolutional Neural Networks
Deep Feedforward Networks - a general description
Math behind Deep Learning and Introduction to Keras
In this post we will be going over the content covered during the fourth Summer School Session
In this post we will be going over the content covered during the third Summer School Session
In this post we will be going over the content covered in the second Summer School session of 2018
In this post we will be going over the content covered during the first session of Summer School 2018
Our Summer School sessions of 2018 begin on July 6. We are going to be covering several topics which should give you a basic understanding and hopefully cult...
This post forms the second part of the introductory material we covered during our sessions on SVMs and Neural Networks. Both posts are slightly more biased ...
This post forms the first part of the introductory material covered during our sessions on SVMs and Neural Networks. Both posts are slightly more biased towa...
What? ML Sessions.
We are in 2018, a year where computer vision seems more dominated by Deep Learning and Reinforcement learning than photogrammetry, and when language is the ...
While conducting some of our sessions, we’ve often had that wiry need where practically no-one has the bare minimum tools installed. Sometimes, it’s an entir...
We would like to thank E-Cell for this wonderful article. A pleasent read indeed!
Goals: Create a software to detect animals in pictures and then identify separate individuals of the same species. Focusing mainly on Chital (Spotted D...
The objective of the CARLA project is to create an Autonomous Driving System (ADS) that would run on the open-source simulator CARLA, which closely models re...
Simultaneous Localisation and Mapping ( SLAM ) is a rather useful addition for most robotic systems, wherein the vision module takes in a video stream and at...
Crowd Analysis in Banking environments ( as a part of the SBI Stockroom Problem Set ): The SBI Stockroom project is mainly aimed at developing an automatic c...
Deep Fake ( Deep Learning + Fake ) is a human image synthesis technique using artificial intelligence methods. It has often been used for doing face swaps, ...
Goal: Deep nets have gotten extremely effective at solving problems that we want them to, and as we use them to solve furthermore complex problems, we also ...
This project could morph expressions to one’s face, to make him smile or frown. It used a few libraries which would help obtain the facial keypoints and afte...
India has a major part of its land area as forests. A lot of resources and effort goes into monitoring these forests and the wildlife in them and preventing ...
This project was a small scale attempt at Snapchat with a few filters which would add certain add ons to your face. The final version used a library called d...
This project aims to use dual channel convnets to perform Audio-Video recognition as well as synchronisation. Synchronisation is done to ensure that there is...
Goal: To digitize and recover text from documents which are not in good shape Objective: To extract text from documents using OCR and fill in the places w...
This project aims to build a stable negative feedback system between hardware and software components for multiple object tracking. The applications include ...
Goal: To analyze the performance of various RL algorithms on different games such as Minesweeper, Slither.io and Reconnaissance Blind Chess. Objective: By...
Given images of the 6 sides of a Rubik’s cube, this project will be able to solve the cube within seconds and will give a 3d simulation and the steps require...
Goal: The project Smartcopter aims to achieve completely autonomous navigation in a GPS denied environment, by using completely vision-based systems such as...
This project was aimed at implementing a CSI ( TV Serial ) style Resolution enhancer for images. A Deep Learning Super Resolution approach was adopted, and ...
Early stage TB detection ( JIPMER collaboration ) s: Tuberculosis is the leading cause of death from a single infectious disease in adults and is the world’s...
The project Textile Quality Analysis aims at counting the wefts(horizontal lines), warps(vertical lines)of a given fabric image uner _pick glass(a glass used...
Goal: We are motivated to develop a supportive eye that can assist the driver to mitigate an accident before it occurs to improve road-safety with the help ...
Present systems of traffic surveillance in India have not caught up with the technological developments and heavily rely on manual surveillance by traffic po...
Disaster relief operations at present have the dual disadvantage of being cut off from resources and also being a risk to the rescue teams deployed. Our main...
Goal: To make a VR shooter game with agents trained by reinforcement learning Objective: Investigate factors like reward signals, training practices and e...
India generates 62 million tonnes of solid waste per annum and has a rather rooted waste management problem which is spiralling out of control. At the heart ...
Introduction
Introduction Background subtraction (BS) is a common and widely used technique for generating a foreground mask (namely, a binary image containing the pixels...
By T Lokesh Kumar
By Rajat V D
Introduction:
In this notebook we are going to learn about different algorithms available for object tracking and thier usage. Object detection and tracking has been a gre...
What is Thresholding?
What are contours?
Introduction:
Corners are good features to find and are useful in a lot of practical situations where opencv is needed. Corners can be considered as points where the inten...
Hough Line Transform
This jupyter notebook walks you through the basic image morphological transformations. These are normally performed for binary images i.e, those having pixel...
Introduction
By Rajat V D
Author: Varun Sundar
Goals: Create a software to compete in RBC competition and beat other competitors Focussing on solving the problem of POMDP in RBC Objective: The ai...
Goal: The project CVspice aims to achieve a UI which inputs hand-drawn electric circuits which in turn identifies the components and the nodes which can the...
Goal: We attempt to solve the age old problem of detecting cracks in architecture by bringing together traditional CV techniques and state-of-the-art Deep L...
Goals: Create a crime detection software that is able to detect various crime thus mitigating the manual effort required to sift through large video cont...
Goal: To identify Cephalometric Landmarks from an Lateral Cephalogram and perform Cephalometric Analysis. Objective: Develop a software that can input Lat...
Goal: To be able to provide real-time joint angle estimation of sports players just using cameras. Objective: Develop a pipeline for obtaining Joint angle...
Goal: The Hawk Eye technology used by cricket bodies is very expensive and is thus not available to most coaching centers. To enable them to implement this ...
Goal: In the recent times, due to the pandemic video conferencing tools have become an integral part of our lives. The current solutions in the market don’t...