Semi-automatic YOLO dataset preparation. Use a pre-trained object detection model to annotate your dataset, then review each image and 'accept' or 'refuse'. Can also edit/mark bounding boxes by hand. Store project data in a single .csv file.

A real-time object detection system that identifies and classifies objects in images or video streams using deep learning models like YOLO, Faster R-CNN, or SSD. Built with TensorFlow and OpenCV, it supports applications in surveillance, autonomous vehicles, and more.

useful tools for box visualization

An object detection model based on YOLOv8 to detect and localize mangoes in images and videos. This project covers image annotation, transfer learning with pretrained weights, and evaluation using a public dataset from Hugging Face, manually annotated for mango detection.

Put bounding boxes over images.

Leveraging advanced image processing and deep learning, this project classifies plant images using a subset of the Plant Seedlings dataset. The dataset includes diverse plant species captured under varying conditions. This project holds significance within my Master's in Computer Vision at uOttawa (2023).

Implementation for 3D bounding box prediction of objects using images, point clouds, and segmentation masks.

Annotate images with bounding boxes inside Jupyter*

A utility script to transform bounding boxes along with the object image.

A real time face detection that captures video from your webcam. Highlights detected faces with bounding boxes in the live feed.

💻 🧐 NTUA ECE Computer Vision Source Codes

Multi-class bounding box labeling tool

Add arbitrary shapes to a pixel-perfect pygame 2D-animation in progress.

Python-based application for YOLO format image annotation. Efficiently label bounding boxes and polygons for object detection datasets using a user-friendly Tkinter GUI. Features include segment snapping, zoom/pan, YOLO label generation, and more. Ideal for preparing datasets for YOLO training.

A website demonstrating augmentation layers of KerasCV

Clean and legitimate bounding box implementation

This is useful to debug the Argoverse V1.1 dataset.

Deep bounding box regression built using keras framework

This project performs real-time object detection using your laptop camera or external webcam with OpenCV and the MobileNetSSD model. It captures live video frames, detects common objects (like person, chair, dog, etc.), and draws bounding boxes around them in real-time. The goal is to help beginners understand object detection using OpenCV’s.