Review of data analysis in vision inspection of power lines with an in-depth discussion of deep learning technology

Abstract

The widespread popularity of unmanned aerial vehicles enables an immense amount of power lines inspection data to be collected. How to employ massive inspection data especially the visible images to maintain the reliability, safety, and sustainability of power transmission is a pressing issue. To date, substantial works have been conducted on the analysis of power lines inspection data. With the aim of providing a comprehensive overview for researchers who are interested in developing a deep-learning-based analysis system for power lines inspection data, this paper conducts a thorough review of the current literature and identifies the challenges for future research. Following the typical procedure of inspection data analysis, we categorize current works in this area into component detection and fault diagnosis. For each aspect, the techniques and methodologies adopted in the literature are summarized. Some valuable information is also included such as data description and method performance. Further, an in-depth discussion of existing deep-learning-related analysis methods in power lines inspection is proposed. Finally, we conclude the paper with several research trends for the future of this area, such as data quality problems, small object detection, embedded application, and evaluation baseline.

References in corpus (36)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• SMOTE: Synthetic Minority Over-sampling Technique
• SSD: Single Shot MultiBox Detector
• Distilling the Knowledge in a Neural Network
• Conditional Generative Adversarial Nets
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• mixup: Beyond Empirical Risk Minimization
• A survey of cross-validation procedures for model selection
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Fully Convolutional Networks for Semantic Segmentation
• Unmanned Aerial Vehicles: A Survey on Civil Applications and Key Research Challenges
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
• Focal Loss for Dense Object Detection
• Rethinking the Value of Network Pruning
• ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
• A Survey of Model Compression and Acceleration for Deep Neural Networks
• Pruning Filters for Efficient ConvNets
• Efficient Neural Architecture Search via Parameter Sharing
• Wasserstein GAN
• Beyond Skip Connections: Top-Down Modulation for Object Detection
• Data Augmentation by Pairing Samples for Images Classification
• Light-Head R-CNN: In Defense of Two-Stage Object Detector
• Learning Efficient Convolutional Networks through Network Slimming
• Deep Learning for Generic Object Detection: A Survey
• Learning to Compare Image Patches via Convolutional Neural Networks
• Hybrid Task Cascade for Instance Segmentation
• CenterNet: Keypoint Triplets for Object Detection
• CornerNet: Detecting Objects as Paired Keypoints
• Bottom-up Object Detection by Grouping Extreme and Center Points
• Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal
• RON: Reverse Connection with Objectness Prior Networks for Object Detection
• Multiple Instance Detection Network with Online Instance Classifier Refinement
• RankIQA: Learning from Rankings for No-reference Image Quality Assessment
• X-GANs: Image Reconstruction Made Easy for Extreme Cases
• Defect Detection from UAV Images based on Region-Based CNNs

Cited by in corpus (4)

• Latent Variable Models in the Era of Industrial Big Data: Extension and Beyond
• Deep Learning in Automated Power Line Inspection: A Review
• InsPLAD: A Dataset and Benchmark for Power Line Asset Inspection in UAV Images
• An Application of Stereo Thermal Vision for Preliminary Inspection of Electrical Power Lines by MAVs