Real-time Power Line Detection Network using Visible Light and Infrared Images

Choi, Hyeyeon; Koo, Gyogwon; Kim, Bum Joon; Kim, Sang Woo

doi:10.1109/ivcnz48456.2019.8961002

Cited by 12 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To the best of authors’ knowledge, almost all the studies regarding PL detection use the dice scores (DSC) (also known as the F1-score), precision, true positive rate (TPR) (also known as recall or sensitivity), false discovery rate (FDR) and accuracy [ 4 , 6 , 7 , 8 , 12 , 13 , 14 ]. These evaluation parameters are defined as: DSC or F1-score = 2TP/(2TP + FP +FN) Precision = TP/(TP + FP) TPR or Recall or Sensitivity = TP/(TP + FN) FDR = FP/(FP + TP) Accuracy = (TP + TN)/(TP + TN + FP + FN) where TP, TN, FP and FN represent the true positive, true negative, false positive and false negative entries of the confusion matrix, respectively.…”

Section: Methodsmentioning

confidence: 99%

“…As far as PL detection is concerned, the work in [ 8 ] utilizes a compound loss based on BCE loss and the Jaccard loss [ 34 ] with a weighting parameter λ to weight the Jaccard loss. The study, however, lacks a thorough investigation of the proposed compound loss with other losses.…”

Section: Related Work and Theoretical Foundationmentioning

confidence: 99%

“…The recent deep learning-based semantic segmentation networks have been applied successfully to the PL detection task to detect the PLs at the pixel level [ 4 , 6 , 7 , 8 ]. These networks frame PL detection as a binary classification problem with the goal of effectively classifying the PL pixels against the background pixels.…”

Section: Introductionmentioning

confidence: 99%

“…The loss functions shift the focus to the minority class, thus, allowing it to contribute more to the loss in comparison to the major background class. Despite the fact that class imbalance affects the PL detection task adversely, only a handful of PL detection works address the class imbalance problem either via the popular variant of the binary cross entropy (BCE) loss function, namely the balanced BCE (BBCE) loss [ 4 , 7 , 12 ], or via a compound loss function [ 8 ] or the attention gated networks [ 13 ]. However, other notable studies on PL detection do not consider the prevalent class imbalance problem and utilize the vanilla BCE loss function for training the deep semantic segmentation networks [ 6 , 14 , 15 , 16 ].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Novel Focal Phi Loss for Power Line Segmentation with Auxiliary Classifier U-Net

Jaffari

Hashmani

Reyes-Aldasoro

2021

Sensors

View full text Add to dashboard Cite

The segmentation of power lines (PLs) from aerial images is a crucial task for the safe navigation of unmanned aerial vehicles (UAVs) operating at low altitudes. Despite the advances in deep learning-based approaches for PL segmentation, these models are still vulnerable to the class imbalance present in the data. The PLs occupy only a minimal portion (1–5%) of the aerial images as compared to the background region (95–99%). Generally, this class imbalance problem is addressed via the use of PL-specific detectors in conjunction with the popular class balanced cross entropy (BBCE) loss function. However, these PL-specific detectors do not work outside their application areas and a BBCE loss requires hyperparameter tuning for class-wise weights, which is not trivial. Moreover, the BBCE loss results in low dice scores and precision values and thus, fails to achieve an optimal trade-off between dice scores, model accuracy, and precision–recall values. In this work, we propose a generalized focal loss function based on the Matthews correlation coefficient (MCC) or the Phi coefficient to address the class imbalance problem in PL segmentation while utilizing a generic deep segmentation architecture. We evaluate our loss function by improving the vanilla U-Net model with an additional convolutional auxiliary classifier head (ACU-Net) for better learning and faster model convergence. The evaluation of two PL datasets, namely the Mendeley Power Line Dataset and the Power Line Dataset of Urban Scenes (PLDU), where PLs occupy around 1% and 2% of the aerial images area, respectively, reveal that our proposed loss function outperforms the popular BBCE loss by 16% in PL dice scores on both the datasets, 19% in precision and false detection rate (FDR) values for the Mendeley PL dataset and 15% in precision and FDR values for the PLDU with a minor degradation in the accuracy and recall values. Moreover, our proposed ACU-Net outperforms the baseline vanilla U-Net for the characteristic evaluation parameters in the range of 1–10% for both the PL datasets. Thus, our proposed loss function with ACU-Net achieves an optimal trade-off for the characteristic evaluation parameters without any bells and whistles. Our code is available at Github.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Work and Theoretical Foundationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Novel Focal Phi Loss for Power Line Segmentation with Auxiliary Classifier U-Net

Jaffari

Hashmani

Reyes-Aldasoro

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…We have listed the examples of such proofs of concept and published results in Table 2 . These are investigated in the context of power line inspection, helping for instance in: robust defect analysis for power line equipment using convolutional neural networks (CNN), achieving, with this large evaluation dataset, up to 98% accuracy [ 36 ]; preventing cascading failures of the grid [ 37 ]; detecting power lines themselves using CNNs [ 26 , 38 , 39 ], or method based on epipolar constraints (PLAMEC) [ 40 ]; transmission tower construction inspection (with detection of AP 89.9% [ 41 ]; or mAP of 94% using the ResNet50 framework [ 42 ]); for power line corridor monitoring with a mean average precision (mAP) of 72.45% from satellite imagery [ 27 ], or separation for vegetation management around power lines using time series analysis [ 43 ], or single images only [ 44 ]; for sub-element diagnostics, such as conductor detection purposes (with AP of 0.729 [ 12 ]) or insulator detection [ 45 ]. …”

Section: Power Line Elements Datasets Reviewmentioning

confidence: 99%

Overview of Image Datasets for Deep Learning Applications in Diagnostics of Power Infrastructure

Ruszczak,

Michalski,

Tomaszewski

2023

Sensors

View full text Add to dashboard Cite

The power sector is one of the most important engineering sectors, with a lot of equipment that needs to be appropriately maintained, often spread over large areas. With the recent advances in deep learning techniques, many applications can be developed that could be used to automate the power line inspection process, replacing previously manual activities. However, in addition to these novel algorithms, this approach requires specialized datasets, collections that have been properly curated and labeled with the help of experts in the field. When it comes to visual inspection processes, these data are mainly images of various types. This paper consists of two main parts. The first one presents information about datasets used in machine learning, especially deep learning. The need to create domain datasets is justified using the example of the collection of data on power infrastructure objects, and the selected repositories of different collections are compared. In addition, selected collections of digital image data are characterized in more detail. The latter part of the review also discusses the use of an original dataset containing 2630 high-resolution labeled images of power line insulators and comments on the potential applications of this collection.

show abstract

Automated Extraction of Energy Systems Information from Remotely Sensed Data: A Review and Analysis

Ren

Bradbury

et al. 2022

Applied Energy

View full text Add to dashboard Cite

Real-time Power Line Detection Network using Visible Light and Infrared Images

Cited by 12 publications

References 15 publications

A Novel Focal Phi Loss for Power Line Segmentation with Auxiliary Classifier U-Net

A Novel Focal Phi Loss for Power Line Segmentation with Auxiliary Classifier U-Net

Overview of Image Datasets for Deep Learning Applications in Diagnostics of Power Infrastructure

Automated Extraction of Energy Systems Information from Remotely Sensed Data: A Review and Analysis

Contact Info

Product

Resources

About