Weakly supervised power line detection algorithm using a recursive noisy label update with refined broken line segments

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

doi:10.1016/j.eswa.2020.113895

Cited by 25 publications

(17 citation statements)

References 20 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%

“…To the best of authors’ knowledge, all the studies on PL detection utilize the BCE loss [ 6 , 14 , 15 , 16 ] and its class imbalance variants [ 4 , 7 , 12 ] for segmenting the PLs. Although BCE loss is easier to optimize with lower training times, it might not always be the best choice for training deep classification networks [ 17 , 18 ].…”

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%

“…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 ]. Moreover, BCE loss and its variants are also the usual choice for loss function in the PL detection tasks [ 4 , 6 , 7 , 12 , 14 , 15 , 16 ].…”

Section: Introductionmentioning

confidence: 99%

“…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 ]. Moreover, BCE loss and its variants are also the usual choice for loss function in the PL detection tasks [ 4 , 6 , 7 , 12 , 14 , 15 , 16 ]. Nevertheless, it has been demonstrated that other kinds of losses can outperform the popular BCE loss for typical classification tasks [ 17 , 18 ].…”

Section: Introductionmentioning

confidence: 99%

See 4 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%

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

show abstract

Power Line Detection Based on Feature Fusion Deep Learning Network

Zou¹,

Jiang²,

Zhao³

2022

Advances in Computer Graphics

View full text Add to dashboard Cite

Development of power transmission line detection technology based on unmanned aerial vehicle image vision

Zhao

Wang

et al. 2023

SN Appl. Sci.

View full text Add to dashboard Cite

The unmanned aerial vehicle (UAV) technology provides a new option for power transmission line inspection. The cost of the UAV detection process is relatively low, and it is flexible and extensible. In order to ensure the safety and stability of power supply in the current large and complex power grid system, UAV detection with image recognition technology has become an urgent need for the development of the current power system. Herein, we review the development of this field in detail. Different from the previous simple discussion on UAV power line inspection technology, this work not only systematically summarizes the UAV power line detection platform and its system structure, but also discusses the image recognition technology based on UAV data. Further, we focus on the fundamental process and development of power line image processing technology based on depth learning, hoping to contribute a systematic reference to the field of power line inspection based on UAV image vision.

show abstract

Weakly supervised power line detection algorithm using a recursive noisy label update with refined broken line segments

Cited by 25 publications

References 20 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

Power Line Detection Based on Feature Fusion Deep Learning Network

Development of power transmission line detection technology based on unmanned aerial vehicle image vision

Contact Info

Product

Resources

About