Formats
YOLOv5 Oriented Bounding Boxes
Object Detection
Object DetectionIMPORTEXPORT
FEATURED
Object Detection

YOLOv5 Oriented Bounding Boxes

A modified version of YOLO Darknet annotations that allows for rotated bounding boxes.

Overview

YOLOv5-OBB is a modified version of YOLOv5 that can predicted oriented (rotated) bounding boxes. This allows it to more closely fit oblong shapes.

Format Description

Below, learn the structure of YOLOv5 Oriented Bounding Boxes.

Each image has one txt file with a single line for each bounding box. The format of each row is

x1 y1 x2 y2 x3 y3 x4 y4 label

where fields are space delimited, and the coordinates are measured in pixels.

001.txt
236 267 271 267 271 306 236 306 helmet 0
188 230 216 230 216 257 188 257 helmet 0
169 146 200 146 200 174 169 174 helmet 0
201 114 230 114 230 140 201 140 helmet 0
247 245 272 245 272 268 247 268 helmet 0
261 231 285 231 285 257 261 257 helmet 0
146 150 172 150 172 179 146 179 head 0

The `data.yaml` file contains configuration values used by the model to locate images and map class names to class_id's.

data.yaml
path: ../datasets/roboflow

train: train/images
val: valid/images
test: test/images

nc: 3
names: ['head', 'helmet', 'person']

Split and Merge Datasets

With Roboflow supervision, an open source Python package with utilities for completing computer vision tasks, you can merge and split detections in YOLOv5 Oriented Bounding Boxes. Read our dedicated guides to learn how to merge and split YOLOv5 Oriented Bounding Boxes detections.

Split detections in YOLOv5 Oriented Bounding Boxes

No items found.

Merge detections in YOLOv5 Oriented Bounding Boxes

No items found.

Supported Models

Below, see model architectures that require data in the YOLOv5 Oriented Bounding Boxes format when training a new model.

On each page below, you can find links to our guides that show how to plot predictions from the model, and complete other common tasks like detecting small objects with the model.

YOLOv5 Oriented Bounding Boxes

YOLOv5-OBB is a variant of YOLOv5 that supports oriented bounding boxes. This model is designed to yield predictions that better fit objects that are positioned at an angle.
Object Detection
Deploy with Roboflow
•
•
1.7k+
stars
•
GPL-3.0
license
•
Released
Mar 12, 2020

On this page

Convert Data from YOLOv5 Oriented Bounding Boxes

Convert to...

Convert Data to YOLOv5 Oriented Bounding Boxes

Convert from...
Formats
YOLOv5 Oriented Bounding Boxes

What is YOLOv5 Oriented Bounding Boxes?

YOLOv5-OBB is a modified version of YOLOv5 that can predicted oriented (rotated) bounding boxes. This allows it to more closely fit oblong shapes.

Deploy Models with Ease on Roboflow

With Roboflow, you can deploy a computer vision model without having to build your own infrastructure.

Get Started Today

YOLOv5 Oriented Bounding Boxes

Below, we show how to convert data to and from

YOLOv5 Oriented Bounding Boxes

. We also list popular models that use the

YOLOv5 Oriented Bounding Boxes

data format. Our conversion tools are free to use.

CONVERT To
CONVERT From
EXAMPLE

Convert Data to YOLOv5 Oriented Bounding Boxes

Use Roboflow to convert
YOLOv5 Oriented Bounding Boxes
to the following formats.

Roboflow is a trusted solution for converting and managing your data. Today, over 250,000 datasets are managed on Roboflow, comprised of 100 million labeled and annotated images.

With Roboflow, you get a solution with:
‍

Free data conversion

SOC II Type 2 Compliant

Trusted by 250,000+ developers

Convert Data from YOLOv5 Oriented Bounding Boxes

Use Roboflow to convert the following formats to
YOLOv5 Oriented Bounding Boxes
format.

Roboflow is a trusted solution for converting and managing your data. Today, over 250,000 datasets are managed on Roboflow, comprised of 100 million labeled and annotated images.

With Roboflow, you get:
‍

Free data conversion

SOC II Type 1 Compliant

Trusted by 250,000+ developers

YOLOv8 PyTorch TXT
to
YOLOv5 Oriented Bounding Boxes
Pascal VOC XML
to
YOLOv5 Oriented Bounding Boxes
COCO JSON
to
YOLOv5 Oriented Bounding Boxes
YOLO Darknet TXT
to
YOLOv5 Oriented Bounding Boxes
CreateML JSON
to
YOLOv5 Oriented Bounding Boxes
SuperAnnotate JSON
to
YOLOv5 Oriented Bounding Boxes
LabelMe JSON
to
YOLOv5 Oriented Bounding Boxes
Google Cloud AutoML Vision CSV
to
YOLOv5 Oriented Bounding Boxes
Sagemaker GroundTruth Manifest
to
YOLOv5 Oriented Bounding Boxes
Supervisely JSON
to
YOLOv5 Oriented Bounding Boxes
LabelBox JSON
to
YOLOv5 Oriented Bounding Boxes
Scale AI JSON
to
YOLOv5 Oriented Bounding Boxes
VGG Image Annotator JSON
to
YOLOv5 Oriented Bounding Boxes
VGG Image Annotator CSV
to
YOLOv5 Oriented Bounding Boxes
LabelBox Video JSON
to
YOLOv5 Oriented Bounding Boxes
VoTT CSV
to
YOLOv5 Oriented Bounding Boxes
VoTT JSON
to
YOLOv5 Oriented Bounding Boxes
Unity Perception JSON
to
YOLOv5 Oriented Bounding Boxes
IBM Cloud Annotations JSON
to
YOLOv5 Oriented Bounding Boxes
OIDv4 TXT
to
YOLOv5 Oriented Bounding Boxes
YOLO Keras TXT
to
YOLOv5 Oriented Bounding Boxes
RetinaNet Keras CSV
to
YOLOv5 Oriented Bounding Boxes
OpenImages CSV
to
YOLOv5 Oriented Bounding Boxes
Tensorflow Object Detection CSV
to
YOLOv5 Oriented Bounding Boxes
Multiclass Classification CSV
to
YOLOv5 Oriented Bounding Boxes
Cogniac
to
YOLOv5 Oriented Bounding Boxes
Kaggle Wheat CSV
to
YOLOv5 Oriented Bounding Boxes
Udacity TXT
to
YOLOv5 Oriented Bounding Boxes
Marmot XML
to
YOLOv5 Oriented Bounding Boxes
Roboflow is a trusted solution for converting and managing your data. Today, over 100,000 datasets are managed on Roboflow, comprised of 100 million labeled and annotated images.

Once your data is in Roboflow, just add the link from your dataset and you're ready to go. We even include the code to export to common inference formats like TFLite, ONNX, and CoreML.

Below are pre-configured models that use the
YOLOv5 Oriented Bounding Boxes
data format
.

What computer vision models use YOLOv5 Oriented Bounding Boxes?

The

YOLOv5 Oriented Bounding Boxes

,

models all use the

YOLOv5 Oriented Bounding Boxes

data format.

YOLOv5 Oriented Bounding Boxes

YOLOv5-OBB is a variant of YOLOv5 that supports oriented bounding boxes. This model is designed to yield predictions that better fit objects that are positioned at an angle.

To see our entire list of computer vision models, check out the Roboflow Model Library.

Each image has one txt file with a single line for each bounding box. The format of each row is

x1 y1 x2 y2 x3 y3 x4 y4 label

where fields are space delimited, and the coordinates are measured in pixels.

001.txt
236 267 271 267 271 306 236 306 helmet 0
188 230 216 230 216 257 188 257 helmet 0
169 146 200 146 200 174 169 174 helmet 0
201 114 230 114 230 140 201 140 helmet 0
247 245 272 245 272 268 247 268 helmet 0
261 231 285 231 285 257 261 257 helmet 0
146 150 172 150 172 179 146 179 head 0

The `data.yaml` file contains configuration values used by the model to locate images and map class names to class_id's.

data.yaml
path: ../datasets/roboflow

train: train/images
val: valid/images
test: test/images

nc: 3
names: ['head', 'helmet', 'person']
Ready to get started?

Join over 1 million developers building with Roboflow

Try it for FreeTalk to Sales