Albumentations on GitHub in Environment and conservation

#1

VIAME/VIAME

Video and Image Analytics for Multiple Environments

#2

agentmorris/MegaDetector

MegaDetector is an AI model that helps conservation folks spend less time doing boring things with camera trap images.

#3

PetervanLunteren/AddaxAI

Simplify camera trap image analysis with AI species recognition models based around the MegaDetector model

#4

WildMeOrg/Wildbook

Wild Me's first product, Wildbook supports researchers by allowing collaboration across the globe and automation of photo ID matching

#5

Climate-Vision/ClimateVision

Open-source ML platform for detecting deforestation, ice melt, and flooding from Sentinel-2 / Landsat imagery.

#6

WildMeOrg/wildbook-ia

Wildbook's Image Analysis (WBIA) backend service supporting machine learning for wildlife conservation

#7

Alexandre-Delplanque/HerdNet

Code for paper "From Crowd to Herd Counting: How to Precisely Detect and Count African Mammals using Aerial Imagery and Deep Learning?"

#8

SaiSwarup27/Animal-Intrusion-Detection

Animal Detection using YOLOv5

#9

Restor-Foundation/tcd

Restor's ML pipeline for tree crown mapping in aerial images

#11

microsoft/landcover-orinoquia

Land cover mapping of the Orinoquía region in Colombia, in collaboration with Wildlife Conservation Society Colombia. An #AIforEarth project

#12

huiandeguangying/forest-fire-smoke-alert

该系统在本地计算机上使用 YOLOv5 模型进行烟雾检测。YOLOv5 是一种高效的目标检测模型，能够在复杂的场景中快速识别火灾烟雾。该模型部署在高性能硬件上，以确保实时响应和高精度的检测效果，在使用时对获取的图片可以进行推理，以检测火情。 YOLOv5-Lite 部署 在树莓派上部署了 YOLOv5-Lite 版本，以实现低功耗设备上的烟雾检测。YOLOv5-Lite 是 YOLOv5 的简化版本，专为资源受限的设备设计，尽管计算资源有限，它仍能提供可靠的检测性能。树莓派设备负责监控远程或野外的森林区域，上位机可获得相应检测结果。

#13

microsoft/MegaDetector-Overhead

MegaDetector-Overhead — The Microsoft open-source AI for overhead wildlife detection. Point-based detection model for aerial and drone imagery, identifying wildlife from above. Maintained by Microsoft AI for Good Lab. Part of the Pytorch-Wildlife ecosystem.

#14

IBM/ImpactMesh

Multimodal, multitemporal dataset for flood and wildfire prediction

#15

QuantuMobileSoftware/clearcut_detection

According to the WWF (World Wildlife Fund), forests cover more than 30% of the Earth’s land surface and are considered to be the lungs of the planet. Unfortunately, people are not using this resource wisely and every day an alarmingly high amount of trees are being cut. Whether it is a natural loss of trees or human-driven – deforestation has horrifying consequences.

#16

drivendataorg/deep-chimpact-winners

Winners of the Deep Chimpact: Depth Estimation for Wildlife Conservation Competition

#18

MatteoM95/Multitask-segmentation-from-satellite-imagery-for-burned-area-delineation-and-severity-estimation

A multi-task learning semantic segmentation approach is employed for targeting both wildfire delineation and burn severity estimation. By exploiting a large dataset of images from past wildfires and integrating both tasks into a single network can exceed the state-of-the-art results on this topic.

#19

ebouhid/BandSelection

Remote sensing image band selection for deforestation detection in the Brazilian Legal Amazon using Evolutionary Algorithms.

#20

wxmiked/cannabis-deforestation

Deforestation analysis from cannabis cultivation in Calaveras County, California

#21

Hritikagore11/Marine-Species-Classification-using-ConvNext

A deep learning-based image classification project using ConvNeXt-Tiny to identify 23 marine species with high accuracy. Leveraging transfer learning, data augmentation, and visualization tools to analyze performance and improve model generalization.

#22

jesquivel2027/Landscape-Change-Detection-Model

A YOLO-based AI model designed to detect and classify changes in landscapes, including vegetation growth, water body expansion, soil erosion, and infrastructure development. Built to support environmental monitoring, conservation, and land management efforts, particularly for applications in engineering and civil planning.

#23

peter1998/WildlifeDetectionSystem

I-powered system for detecting and analyzing wildlife in camera trap images

#24

rithick007/Deforestation-and-Forestfire-Analyser-using-ML

A Streamlit-based machine learning tool for detecting deforestation. It includes a live monitor for identifying recent frequent fires and forest fires, providing a complete analysis of forest issues. The tool processes satellite data and offers insights through interactive visualizations for researchers and policymakers.

#27

HiBorn4/PyVision_Low-Resolution-Human-Detection-in-the-Wild

PyVision: Detect humans in the wild with precision, even in low-resolution scenarios. Ideal for wildlife monitoring, outdoor security, and diverse surveillance applications.

#34

ebouhid/greenAI

Improving Semantic Segmentation model efficiency for Deforestation Detection in the Amazon Rainforest.

#35

ebouhid/superpixel_comparison

Comparing superpixel methods for deforestation detection in the Brazilian Legal Amazon.

#37

karmarv/manacus-dynamics

Camera Trap video processing for Manacus dynamics assessment

#38

kbcoder19/osapiens-challenge

Deforestation challenge for Makeathon 2024

#45

SamBall999/wild

Protecting Wildlife through Low-Cost Data Annotation for Aerial Poaching Detection

#46

Steven-Herrera/real-time-fire-detection

Real Time Forest Fire Detection with Compressed Deep Learning Models

#47

vishalrajofficial/forest-fire-detection-system1

This project utilizes 🔬 machine learning algorithms to predict 🔥 forest fires using inputs such as 🌡️ temperature, 🧪 oxygen level, and 💧 humidity. The trained model can analyze the inputs and provide a prediction of the likelihood of a forest fire occurring. The prediction results are displayed through a 🌐 Flask web application.

#48

WildMeOrg/pairx

PairX wildme fork