airsim-vehicle-detection Computer Vision Project
This is an object detection experiment to identify the location of vehicles from aerial images captured in an AirSim session. The data set is small 45-ish original annotated images (256x144) with 2X additional augmented images. Images were captured from a drone's 'bottom_center' camera with 90 deg FOV at 45m height. Used AirSim-js and Nodejs to code the flight path and grab images from the camera.
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.
Cite This Project
If you use this dataset in a research paper, please cite it using the following BibTeX:
@misc{
airsim-vehicle-detection_dataset,
title = { airsim-vehicle-detection Dataset },
type = { Open Source Dataset },
author = { ros2jsguy },
howpublished = { \url{ https://universe.roboflow.com/ros2jsguy/airsim-vehicle-detection } },
url = { https://universe.roboflow.com/ros2jsguy/airsim-vehicle-detection },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2022 },
month = { nov },
note = { visited on 2024-04-28 },
}
Connect Your Model With Program Logic
Find utilities and guides to help you start using the airsim-vehicle-detection project in your project.