This is a project for socks card label validation where the socks card is validated comparing with the correct socks card whose coordinates are stored in the database. When the test socks card is compared with the correct socks card(master socks card) the software checks whether both test and master socks card matches or not.

image stitching using superglue

3D scene reconstruction (stereo)

Map images to representation vectors.

Using OpenCV to match features and identify an object.

Make Rendered Database using Rendered Image Obtained by Trained Gaussian Splatting

A collection of scripts that handle and compare images based on terrain traversability estimation grid maps

Implementation of my MSc thesis work, entitled "Optical pose estimation in robotics applications"

Computer vision small projects. Algorithms from scratch.

Stabilo is a Python package for stabilizing video frames or object trajectories using advanced transformation techniques. It supports user-defined masks to exclude specific areas, making it ideal for dynamic scenes with moving objects. Unlike traditional stabilization, it stabilizes content relative to a chosen reference frame.

This repository consists of two major components for a project called E-waste recycling system. One component is used to generate a labelled dataset to train U-Net segmentation network. The second component is used to perform non-rigid registration using Demon's algorithm.

Scale Invariant Feature Transform and Feature Matching

This reposetory contains codes to evaluate the extent of attenuation of shock waves.

ConveyorVision is an innovative real-time system designed to automate the counting and tracking of cement bags on conveyor belts. Utilizing cutting-edge deep learning techniques like YOLOv8 for object detection and Byte tracker for precise tracking, ConveyorVision accurately monitors cement bags as they traverse the conveyor belt.

When given different views of an object as input, it can tell us if that specific object is present in a larger picture or not.

Implementing the concept of Stereo Vision. We are given 3 different datasets, each of them containing 2 images of the same scenario but taken from two different camera angles. By comparing the information about a scene from 2 vantage points, we can obtain the 3D information by examining the relative positions of objects.

This project provides a tool to compare two images using various similarity metrics, including histograms, structural similarity index (SSIM), mean squared error (MSE), mean absolute error (MAE), feature matching, and image hashing.

A computer vision toolkit focused on color detection and feature matching using OpenCV. It allows you to easily start the picamera in case you're using a Raspberry PI

3D scene reconstruction and camera pose estimation from custom dataset images

Repository of NCTR