Ant Detection Computer Vision Project

Overview

An object detection and tracking model to automatically monitor the behaviour of jet ants, Lasius fuliginosus, from videos recorded at foraging sites in the field. The system is amenable to videos recorded at 1080p from a distance of 100mm on standard phone cameras against a white background, and enables the automated tracking of >1000 individuals simultaneously.

Current functionality includes monitoring foraging activity in real-time, and counting occupancy within specified regions of interest (ROIs) utilising the scripts outlined in the API Docs.

Trained Model API

This project has a trained model available that you can try in your browser and use to get predictions via our Hosted Inference API and other deployment methods.

YOLOv8

This project has a YOLOv8 model checkpoint available for inference with Roboflow Deploy. YOLOv8 is a new state-of-the-art real-time object detection model.

Cite This Project

If you use this dataset in a research paper, please cite it using the following BibTeX:

@misc{ ant-detection-079b3_dataset, title = { Ant Detection Dataset }, type = { Open Source Dataset }, author = { Thomas A. O’Shea-Wheller}, howpublished = { \url{ https://universe.roboflow.com/projects-k8s3q/ant-detection-079b3 } }, url = { https://universe.roboflow.com/projects-k8s3q/ant-detection-079b3 }, journal = { Roboflow Universe }, publisher = { Roboflow }, year = { 2024 }, month = { jun }, note = { visited on 2024-06-02 }, }