AI For Good Lab
Télécharger
Open datasheets framework
avril 2024
This framework aims to assist in the documentation of datasets to promote transparency and help dataset creators and consumers make informed decisions. You can read more about it in our paper: Open Datasheets: Machine-readable Documentation for Open Datasets and Responsible AI…
BankNote-net: Open Dataset for Assistive Currency Recognition
avril 2024
Assistive software applications have been developed for a variety of day-to-day tasks, including currency recognition. BankNote-Net is an open dataset for assistive currency recognition.
Causal impact long-COVID
avril 2024
Code supplementing AI for Good Lab’s work on long COVID sequelae using EHR data. This project aimed to discover long COVID sequelae (symptoms) from Electronic Health Records (EHR) data using causal impact analysis of time series and analyze its association with…
Identifying Whales in High-resolution Satellite Imagery
avril 2024
This repository contains code for an active learning pipeline for detecting whales in high-resolution satellite imagery.
Turkana grid mapping
avril 2024
Mapping electrical infrastructure can support measuring access to electricity and can help identify opportunities to improve or extend existing power infrastructure.
Turkana camp roof mapping
avril 2024
This project automates the identification of buildings and solar panels in aerial imagery, aiding humanitarian mapping. In many developing regions, maps are often outdated or missing, hindering development planning and disaster response. Our work accelerates the creation of up-to-date maps,…
Giraffe keypoint detection
avril 2024
This repository contains code for running a giraffe keypoint detection model. The model estimates 4 keypoint locations in images containing a single giraffe, namely: top of ossicone, top of head, neck indent, and front bottom hoof.
Lymphoma lesion segmentation DNN
novembre 2023
Lymphoma lesion segmentation and quantitation plays a pivotal role in the diagnosis, treatment planning, and monitoring of lymphoma patients. Accurate segmentation allows for the precise delineation of pathological regions, aiding clinicians in assessing disease extent and progression. Moreover, lesion quantitation,…
Damage Assessment Visualizer
novembre 2022
The Damage Assessment Visualizer leverages satellite imagery from a disaster region to visualize conditions of building and structures before and after a disaster. It includes a visual layer on top of the satellite images which predicts the extent of damage…