STN-PLAD Dataset

Estimated reading: 3 minutes 1407 views

Visualization of STN-PLAD Dataset in the Deep Lake UI

STN-PLAD Dataset

What is STN-PLAD Dataset?

This STN-PLAD (STN Power Line Assets Dataset) dataset was generated to aid power line companies in detecting high-voltage power line towers in order to avoid putting workers at risk. The dataset contains 5 different annotated object classes such as Stockbridge damper, spacer, transmission tower, tower plate, and insulator. Each object class has an average of 18.1 annotated instances in total images of 133 power lines. The images were taken from various angles, resolutions, backgrounds, and illumination. All the images were taken through a hi-res UAV. This dataset can make use of popular deep object detection methods.

Downloading STN-PLAD Dataset in Python

Instead of downloading the STN-PLAD in Python, you can effortlessly load it in Python via our Deep Lake open-source with just one line of code.

Load STN-PLAD Dataset Subset in Python

				
					import deeplake
ds = deeplake.load('hub://activeloop/stn-plad')

STN-PLAD Dataset Structure

Data Fields

images: tensor containing the image
images_meta: contains meta information of images
boxes: a group of tensors holding boxes with information on the categories
categories: tensor containing categories of Power Line Assets
super_categories: tensor containing super category of the Power Line Assets
areas: tensor holding the information of the area of the box
iscrowds: bool value containing information about whether a certain image should be allowed for training
date_captured: the date on which the images were collected
file_name: contains the name of the image
height: contains the height of the image
width: contains the width of the image

How to use STN-PLAD Dataset with PyTorch and TensorFlow in Python

Train a model on STN-PLAD dataset with PyTorch in Python

Let’s use Deep Lake built-in PyTorch one-line dataloader to connect the data to the compute:

				
					dataloader = ds.pytorch(num_workers=0, batch_size=4, shuffle=False)

Train a model on STN-PLAD dataset with TensorFlow in Python

				
					dataloader = ds.tensorflow()

Additional Information about STN-PLAD Dataset

STN-PLAD Dataset Description

Repository: https://github.com/andreluizbvs/PLAD
Paper: https://arxiv.org/abs/2108.07944

STN-PLAD Dataset Licensing Information

Creative Commons CCO 1.0

STN-PLAD Dataset Citation Information

				
					@inproceedings{vieira2021stn,
  title={STN PLAD: A Dataset for Multi-Size Power Line Assets Detection in High-Resolution UAV Images},
  author={Vieira-e-Silva, Andr{\'e} Luiz Buarque and de Castro Felix, Heitor and de Menezes Chaves, Thiago and Sim{\~o}es, Francisco Paulo Magalh{\~a}es and Teichrieb, Veronica and dos Santos, Michel Mozinho and da Cunha Santiago, Hemir and Sgotti, Virginia Ad{\'e}lia Cordeiro and Neto, Henrique Baptista Duffles Teixeira Lott},
  booktitle={2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)},
  pages={215--222},
  year={2021},
  organization={IEEE}
}