Multi-head Attention Based Transformers for Vegetation Encroachment Over Powerline Corriders using UAV

Vemula, Srikanth; Frye, Michael

doi:10.1109/dasc52595.2021.9594293

Cited by 6 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Tversky loss effectively addresses the class imbalance issue, resulting in an improved segmentation performance for power line corridors. Similar studies, like that developed by [33], used UAV and transformers to detect zones of vegetation encroachment, and the prediction for the zone of encroachment (mixed both power lines and vegetation) obtained a Jaccard index of 0.87. Others studies like [34] combined UAVs and deep learning, but in this case to detect transmission towers, reaching an accuracy of 98.6% for a DenseNet.…”

Section: Vepl-net: a Fusion Of Neural Network For Enhanced Segmentati...mentioning

confidence: 69%

VEPL-Net: A Deep Learning Ensemble for Automatic Segmentation of Vegetation Encroachment in Power Line Corridors Using UAV Imagery

Cano-Solis,

Ballesteros,

Sanchez-Torres

2023

IJGI

View full text Add to dashboard Cite

Vegetation encroachment in power line corridors remains a major challenge for modern energy-dependent societies, as it can cause power outages and lead to significant financial losses. Unmanned Aerial Vehicles (UAVs) have emerged as a promising solution for monitoring infrastructure, owing to their ability to acquire high-resolution overhead images of these areas quickly and affordably. However, accurate segmentation of the vegetation encroachment in this imagery is a challenging task, due to the complexity of the scene and the high pixel imbalance between the power lines, the vegetation and the background classes. In this paper, we propose a deep learning-based approach to tackle this problem caused by the original and different geometry of the objects. Specifically, we use DeepLabV3, U-Net and a modified version of the U-Net architecture with VGG-16 weights to train two separate models. One of them segments the dominant classes, the vegetation from the background, achieving an IoU of 0.77. The other one segments power line corridors from the background, obtaining an IoU of 0.64. Finally, ensembling both models into one creates an “encroachment” zone, where power lines and vegetation are intersected. We train our models using the Vegetation Encroachment in Power Line Corridors dataset (VEPL), which includes RGB orthomosaics and multi-label masks for segmentation. Experimental results demonstrate that our approach outperforms individual networks and original prominent architectures when applied to this specific problem. This approach has the potential to significantly improve the efficiency and accuracy of vegetation encroachment monitoring using UAV, thus helping to ensure the reliability and sustainability of power supply.

show abstract

Section: Vepl-net: a Fusion Of Neural Network For Enhanced Segmentati...mentioning

confidence: 69%

VEPL-Net: A Deep Learning Ensemble for Automatic Segmentation of Vegetation Encroachment in Power Line Corridors Using UAV Imagery

Cano-Solis,

Ballesteros,

Sanchez-Torres

2023

IJGI

View full text Add to dashboard Cite

show abstract

“…Furthermore, if the calculated distance falls below the safety threshold, the original captured image and the measured result will be uploaded to the cloud data center and will be double checked by maintenance staff. In order to demonstrate the benefits of the proposed method, we compared it to methods based on the Deep Learning algorithm [36], point cloud [37], and stereovision [38]. The three most important factors in power line monitoring are detection accuracy, frequency, and cost.…”

Section: Simulation Of the Test Scenariomentioning

confidence: 99%

Online Monitoring of Overhead Power Lines Against Tree Intrusion via a Low-cost Camera and Mobile Edge Computing Approach

Qiu²,

Wang³

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Fast-growing trees pose risks to the operational safety of overhead power lines. Traditional methods of inspecting tree growth, such as ground inspection, are time-consuming and not accurate. Latest development employs drones equipped with either light detection and ranging (LiDAR) or camera for accurate inspections. However, those methods are expensive and cannot be used all the time. They are also susceptible to severe weather conditions. Therefore, in this paper, an online method for measuring and calculating the horizontal distances between the power lines and trees in a mobile edge computing architecture is proposed by taking into account a unique property of power systems. Firstly, two-dimensional images are taken by a standard optical camera mounted on the tower. Secondly, the power lines and the surrounding trees in the images are discovered by processing the images. Finally, the distances between the power lines and trees are calculated based on a reference distance. Furthermore, the applications that control the cameras and image processing are implemented on a mobile edge server for real-time monitoring and system updates. Experiment results in real-world scenarios show that the measurement error is less than 10%, which indicates that the proposed approach can reliably estimate the distances and the edge computing-based architecture can improve the efficiency.

show abstract

A Method for Identifying Vegetation Under Distribution Power Lines by Remote Sensing

Kinoshita,

Schmith,

Martins

et al. 2023

J Control Autom Electr Syst

View full text Add to dashboard Cite

Multi-head Attention Based Transformers for Vegetation Encroachment Over Powerline Corriders using UAV

Cited by 6 publications

References 23 publications

VEPL-Net: A Deep Learning Ensemble for Automatic Segmentation of Vegetation Encroachment in Power Line Corridors Using UAV Imagery

VEPL-Net: A Deep Learning Ensemble for Automatic Segmentation of Vegetation Encroachment in Power Line Corridors Using UAV Imagery

Online Monitoring of Overhead Power Lines Against Tree Intrusion via a Low-cost Camera and Mobile Edge Computing Approach

A Method for Identifying Vegetation Under Distribution Power Lines by Remote Sensing

Contact Info

Product

Resources

About