Sai Charan's Projects
BFS implementation to solve the 8-Puzzle-Problem
A-Star Search algorithm implemented on 2D maps
Controlling a Turtlebot in ROS and implemented path planning using the A-Star algorithm
A mobile observer samples sequences of narrow-field projections of configurations in ambient space. For rigid transformations, a unique metrical reconstruction is known to be possible from three orthographic views of four points.
Tracking a QR tag and superimposing an Image and projecting a cube on to it using OpenCV methods
A Simulation of a Production line, using C++ and Python in ROS Melodic
Implemented TLS, LS, Homography and SVD on given data sets
DexiNed: Dense EXtreme Inception Network for Edge Detection
An individual project aimed at implementing Dijkstra's path planning algorithm on a point robot to navigate a map that contains obstacles
Water level detection using draft marker readings, through the means of computer vision, machine learning and optical flow methods
Edge detection includes a variety of mathematical methods that aim at identifying edges, curves in a digital image at which the image brightness changes sharply or, more formally, has discontinuities. This program explores various methods to approach edge detection
A program to identify epipoles. The epipolar line is the straight line of intersection of the epipolar plane with the image plane. It is the image in one camera of a ray through the optical center and image point in the other camera. All epipolar lines intersect at the epipole.
The Gaussian pyramid provides a representation of the same image at multiple scales, using simple lowpass filtering and decimation techniques. The Laplacian pyramid provides a coarse representation of the image as well as a set of detail images (bandpass components) at different scales. This program generates both at various N values
As applied in the field of computer vision, graph cut optimization can be employed to efficiently solve a wide variety of low-level computer vision problems, such as image smoothing, the stereo correspondence problem, image segmentation, object co-segmentation, cv problems that can be formulated in terms of energy minimization.
Histogram equalization is a method in image processing of contrast adjustment using the image's histogram.This method usually increases the global contrast of many images, especially when the image is represented by a narrow range of intensity values.
The circle Hough Transform (CHT) is a basic feature extraction technique used in digital image processing for detecting circles in imperfect images. The circle candidates are produced by βvotingβ in the Hough parameter space and then selecting local maxima in an accumulator matrix. This program showcases Hough Circles usage
A hybrid image is an image that is perceived in one of two different ways, depending on viewing distance, based on the way humans process visual input.
CIFAR-10 is an established computer-vision dataset used for object recognition. It is a subset of the 80 million tiny images dataset and consists of 60,000 32x32 color images containing one of 10 object classes, with 6000 images per class. Using this we develop a model that can classify images
A Jekyll plugin to add metadata tags for search engines and social networks to better index and display your site's content.
A script to create 4 clusters that filter based on the K- Mean Algorithm
The Kanade-Lucas-Tomasi (KLT) Feature Tracker algorithm estimates the 2D translation and scale changes of an image template between original template coordinates and a given reference image using the Inverse Compositional algorithm.
This program detects and classifies lanes and Determines which direction the car has to turn
Set of Solution to all my LeetCode Question and answers
Lowe-style object instance recognition, using SIFT. The scale-invariant feature transform (SIFT) is a computer vision algorithm to detect, describe, and match local features in images
Reinforcement Learning Environments for Omniverse Isaac Gym
A python script that can stitch two images into a panorama through feature detection and matching.
A simulation of a turtle bot in a dynamic environment using a novel RRT-Star-Fixed-Nodes algorithm
Semantic segmentation classifies image pixels into one or more classes which are semantically interpret able. CNNs for semantic segmentation typically use a fully convolutional network (FCN) architecture, which replaces the fully connected layers of a traditional CNN with convolutional layers.
A function that aligns two sets of points using global image transformation (similarity, affine, or perspective) and returns T where T is a transformation that maps non-zero points in im1 to non-zero points in im2.