AUV Training Computer Vision Dataset
About AUV Training Dataset
=== AUV Training Dataset === Contributors: Vinay Nagappala, John McCollough, Alex Xu
=== Description === This dataset is meant to be used to train a vareity of deep learning models for the RoboSub competition. Currently, it is being used on a vareity of the YOLOv5 architectures. The majority of the images come from the robosub_transdec_dataset (https://github.com/beaverauv/robosub_transdec_dataset), and others were added from other sources or generated using simulated environments in Unreal Engine.
Use Free Bin, Buoy_green and Buoy_red Detection API
Powered by general detection model
Code
pip install inference-sdk# 1. Import the library
from inference_sdk import InferenceHTTPClient
# 2. Connect to your workspace
client = InferenceHTTPClient(
api_url="https://serverless.roboflow.com",
api_key="API_KEY"
)
# 3. Run your workflow on an image
result = client.run_workflow(
workspace_name="<YOUR_WORKSPACE>",
workflow_id="<YOUR_WORKFLOW_ID>",
images={
"image": "YOUR_IMAGE.jpg" # Path to your image file
},
parameters={
"classes": "bin, buoy_green, buoy_red, buoy_yellow, channel"
},
use_cache=True # cache workflow definition for 15 minutes
)
# 4. Get your results
print(result)Run on custom image
Drop an image here or click to upload
Detecting classes:
Or try a test image
Roboflow Agent
Tell the agent what you want to build.
Cite This Project
LicenseCC BY 4.0If you use this dataset in a research paper, please cite it using the following BibTeX:
@misc{ auv-training-wowrv_dataset,
title = { AUV Training Dataset },
type = { Open Source Dataset },
author = { QaAUV },
howpublished = { \url{ https://universe.roboflow.com/qaauv/auv-training-wowrv } },
url = { https://universe.roboflow.com/qaauv/auv-training-wowrv },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2025 },
month = { sep },
note = { visited on 2026-07-29 },
}