Udacity CarND - Vehicle Detection and Tracking

"Where is my coffee cup" is a simple research and fun project where computer vision program looking for difference between images and mark them by boundbox

Mirror only. Official repository is at https://src.doom.fm/citruspi/glyph-bbox-render

In this project, I implement a framework to detect and track vehicles across different frames from road recordings.

The goal is to find a minimum area convex hull in higher dimensions. The work here is done under the jurisdiction of Information Technology University, Lahore, Pakistan

Textract Geometry Tool for annotating PDFs with bounding boxes for recognized LINE elements

Simple object tracking by using the centroid tracking algorithm

ObjectDetection-Yolo-V3

Application which aims to visualise how tesseractOCR work

This repository is made up to support codes for this medium post: Features: tools for adding bboxes and corresponding labels. flexible to add more labels and its confidences and categories. an example code for object detection is provided. The code is developed using Test-Driven-Development.

This repository contains a simple project for the implementation of an object detection system, using bounding boxes. The project was implemented using Python and specifically the Keras framework.

Object detection and segmentation in TensorFlow

Vehicle Detection Project using HOG and SVM classifier

Real time automatic creation of bounding boxes as well as salience maps around detected objects for fixed backgrounds. Save images as well as the corresponding annotations once the object has been detected. Uses OpenCV and TensorFlow

Grape detection project that can classify and draw bounding boxes around them. Created using pretrained RetinaNet model from Tensorflow object detection API

Tool to inflate the bounding box of a Collada file to match the bounding box of another.

An AI model which detects a cats nose

This project focuses on detection of number plates from both photos and videos utilizing a custom-built model as well as a fine-tuned YOLOv8 architecture.

This study proposes the design and evaluation of a deep learning model using YOLOv8, an advanced object detection algorithm, for object detection and counting in satellite images