Robust real-time UAV based power line detection and tracking

Zhou, Guang-Quan; Yuan, Jinwei; Yen, I-Ling; Bastani, Farokh B.

doi:10.1109/icip.2016.7532456

Cited by 91 publications

(41 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main advantage of this method is the inspection accuracy due to its proximity to the power lines. However, according to [9], the weight of the robots could damage the lines, and the robots may not be able to pass across various obstacles on the lines. Another major disadvantage of this inspection method is that it is relatively slow compared to other inspection methods such automated helicopter-assisted inspection or UAVs inspection.…”

Section: Climbing Robots Inspectionmentioning

confidence: 99%

“…According to [9], there are three common approaches for UAV navigation in automatic power line inspection: GPS way points-based, pole detection-based, and power line detectionbased. While the first approach has been widely applied for decades, the other two approaches have recently been facilitated by advances in visual recognition.…”

Section: Vision-based Approaches For Navigationmentioning

confidence: 99%

“…To address the threshold selection problem in traditional edge detection approaches as well as the Hough transform, Guang Zhou et al proposed a method that can effectively tune the threshold in edge and line detection algorithms in [9]. A database was created for keeping optimal parameters for visited places, which can be retrieved later based on GPS coordinates.…”

Section: Power Line Detection-based Approachesmentioning

confidence: 99%

“…According to [9], there are three common approaches for UAV navigation in automatic power line inspection: pole detection-based, GPS way points-based, and power line detection-based. Unfortunately, none of the three methods offer a sufficient navigation accuracy for fully automatic autonomous UAV inspection.…”

Section: Vision-based Uav Navigationmentioning

confidence: 99%

See 3 more Smart Citations

Automatic autonomous vision-based power line inspection: A review of current status and the potential role of deep learning

Nguyen

Jenssen

Roverso³

2018

International Journal of Electrical Power & Energy Systems

382

117

View full text Add to dashboard Cite

To maintain the reliability, availability, and sustainability of electricity supply, electricity companies regularly perform visual inspections on their transmission and distribution networks. These inspections have been typically carried out using foot patrol and/or helicopter-assisted methods to plan for necessary repair or replacement works before any major damage, which may cause power outage. This solution is quite slow, expensive, and potentially dangerous. In recent years, numerous researches have been conducted to automate the visual inspections by using automated helicopters, flying robots, and/or climbing robots. However, due to the high accuracy requirements of the task and its unique challenges, automatic vision-based inspection has not been widely adopted. In this paper, with the aim of providing a good starting point for researchers who are interested in developing a fully automatic autonomous vision-based power line inspection system, we conduct an extensive literature review. First, we examine existing power line inspection methods with special attention paid to highlight their advantages and disadvantages. Next, we summarize well-suited tasks and review potential data sources for automatic vision-based inspection. Then, we survey existing automatic vision-based power line inspection systems. Based on that, we propose a new automatic autonomous vision-based power line inspection concept that uses Unmanned Aerial Vehicle (UAV) inspection as the main inspection method, optical images as the primary data source, and deep learning as the backbone of data analysis and inspection. Then, we present an overview of possibilities and challenges of deep vision (deep learning for computer vision) approaches for both UAV navigation and UAV inspection and discuss possible solutions to the challenges. Finally, we conclude the paper with an outlook for the future of this field and propose potential next steps for implementing the concept.

show abstract

Section: Climbing Robots Inspectionmentioning

confidence: 99%

Section: Vision-based Approaches For Navigationmentioning

confidence: 99%

Section: Power Line Detection-based Approachesmentioning

confidence: 99%

Section: Vision-based Uav Navigationmentioning

confidence: 99%

See 2 more Smart Citations

Automatic autonomous vision-based power line inspection: A review of current status and the potential role of deep learning

Nguyen

Jenssen

Roverso³

2018

International Journal of Electrical Power & Energy Systems

382

117

View full text Add to dashboard Cite

show abstract

“…Also, those that decided to run the experiment in a portable resource-constrained execution environment rely on classical computer vision methods and do not use CNN-based object detectors (Chiu, 2014;Martinez-de Dios, 2001;Wang et al, 2016;Yong and Yeong, 2018). Typically, Haar-like (Aguilar, 2017;Rudol & Doherty, 2018) and SVM techniques (Bejiga, 2016;Zhou, Yuan, Yen, & Bastani, 2016) are utilized due to their fast performance and easy implementation. Nevertheless, the higher accuracy of CNN-based object detectors comes at the expense of higher computational resources compared to classical methods.…”

Section: Uav Analysismentioning

confidence: 99%

Smartphone‐based object recognition with embedded machine learning intelligence for unmanned aerial vehicles

Martinez‐Alpiste

Casaseca‐de‐la‐Higuera

Alcaraz-Calero

et al. 2019

Journal of Field Robotics

View full text Add to dashboard Cite

Existing artificial intelligence solutions typically operate in powerful platforms with high computational resources availability. However, a growing number of emerging use cases such as those based on unmanned aerial systems (UAS) require new solutions with embedded artificial intelligence on a highly mobile platform. This paper proposes an innovative UAS that explores machine learning (ML) capabilities in a smartphone‐based mobile platform for object detection and recognition applications. A new system framework tailored to this challenging use case is designed with a customized workflow specified. Furthermore, the design of the embedded ML leverages TensorFlow, a cutting‐edge open‐source ML framework. The prototype of the system integrates all the architectural components in a fully functional system, and it is suitable for real‐world operational environments such as seek and rescue use cases. Experimental results validate the design and prototyping of the system and demonstrate an overall improved performance compared with the state of the art in terms of a wide range of metrics.

show abstract

Construction of Power Line Inspection System Using a Quadrotor Helicopter

Takaya,

Ohta,

Shibayama

et al. 2024

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

This work presents a construction of a novel system for autonomous inspection of power transmission lines using a quadrotor helicopter. The aircraft follows the power lines at a constant distance and acquires high‐resolution images of the conductors, dampers, and towers. Monitoring of the vegetation under the power lines is also performed. The traditional inspection is carried out by helicopters equipped with high‐resolution cameras or by direct visual examination by personnel climbing over de‐energized power lines. However, visual inspection is time‐consuming, labor‐intensive, and dangerous, and often, helicopter cameras cannot capture the acute details needed for accurate and comprehensive examinations. This work successfully evaluates a mathematical model for the quadrotor helicopter used in autonomous inspection through simulations and flight experiments. Two control strategies for power line tracking are compared: a classical PID and a fuzzy PD control. Several simulations and experimental results confirm the efficiency of both control laws, but the fuzzy controller performs better under strong wind disturbances. The results of this work will be implemented by an electric power company to inspect electrical transmission facilities regularly. © 2024 The Author(s). IEEJ Transactions on Electrical and Electronic Engineering published by Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

show abstract

Robust real-time UAV based power line detection and tracking

Cited by 91 publications

References 2 publications

Automatic autonomous vision-based power line inspection: A review of current status and the potential role of deep learning

Automatic autonomous vision-based power line inspection: A review of current status and the potential role of deep learning

Smartphone‐based object recognition with embedded machine learning intelligence for unmanned aerial vehicles

Construction of Power Line Inspection System Using a Quadrotor Helicopter

Contact Info

Product

Resources

About