Multi-object tracking of water fleas from video. Detects dark blotches on light background, performs multi-object association, tracks them with Kalman filters.

A multi-stage computer vision algorithm to detect edges in images. Developed by John Canny in 1986, widely used in image processing, computer vision, and other fields. This repo provides an implementation in Python

Python implementation of Laplacian pyramid algorithm for blending images using reduce/expand, Gaussian/Laplacian pyramids, and combine/collapse functions for realistic outputs

Implementation of Classical Structure from Motion pipeline

Lane Detection using classical approach and a deep learning based approach

Haar cascade classifiers detecting faces and eyes in images with OpenCV.

This repo contains implementations of some of the classical computer vision algorithms/techniques for feature extraction, feature matching, image transformation, color image reconstruction, image denoising, image classification, and image segmentation.

Telexistence Box Detection Take Home Assignment

This project involves developing a simplified boundary detection algorithm that combines texture, brightness, and color gradients with classical edge detection methods like Sobel and Canny. The final boundary map is generated by fusing these feature gradients with traditional edge detection methods for more robust and accurate edge detection.