Specifications of the drone and camera used.

Specifications of the drone and camera used.

Source publication
Article
Full-text available
Power lines are cables that carry electrical power from a power plant to an electrical substation. They must be connected between the tower structures in such a way that ensures minimum tension and sufficient clearance from the ground. Power lines can stretch and sag with the changing weather, eventually exceeding the planned tolerances. The excess...

Context in source publication

Context 1
... addition, a guard wire is placed on top of the towers. We used a low-cost drone, the Phantom 4 (DJI), the specifications of which are shown in Table 1. The focal length of the installed camera is 3.6 mm and the camera produces 12.4 megapixel images. ...

Similar publications

Citations

... Recently, as shown in Fig. 1, Unmanned Aerial Vehicles (UAVs) equipped with Light Detection and Ranging (LiDAR) and various types of cameras are widely used in power line monitoring [3,4,5]. The abundant data resources ensure complete and accurate monitoring results. ...
... Nowadays, UAVs are becoming a cost-effective solution to observe power lines in close proximity. UAVs can be utilized as carriers to undertake thorough and accurate power line inspections when equipped with various remote sensing technologies such as optical cameras, LiDAR, infrared cameras, and ultraviolet cameras [7,8,3,4,5]. ...
Article
Full-text available
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.
... In the case of robotics, this simplification has been contested in some applications [47]. Figure 2 visualizes the approximation of a catenary by a parabola, which may be good enough for some applications [55][56][57][58], especially in the development of cable-driven robots [59]. This article proposes a hybrid between catenary and parabola geometric models for a DLO section hanging between two drones. ...
Article
Full-text available
This paper deals with the control of a team of unmanned air vehicles (UAVs), specifically quadrotors, for which their mission is the transportation of a deformable linear object (DLO), i.e., a cable, hose or similar object in quasi-stationary state, while cruising towards destination. Such missions have strong industrial applications in the transportation of hoses or power cables to specific locations, such as the emergency power or water supply in hazard situations such as fires or earthquake damaged structures. This control must be robust to withstand strong and sudden wind disturbances and remain stable after aggressive maneuvers, i.e., sharp changes of direction or acceleration. To cope with these, we have previously developed the online adaptation of the proportional derivative (PD) controllers of the quadrotors thrusters, implemented by a fuzzy logic rule system that experienced adaptation by a stochastic gradient rule. However, sagging conditions appearing when the transporting drones are too close or too far away induce singularities in the DLO catenary models, breaking apart the control system. The paper’s main contribution is the formulation of the hybrid selective model of the DLO sections as either catenaries or parabolas, which allows us to overcome these sagging conditions. We provide the specific decision rule to shift between DLO models. Simulation results demonstrate the performance of the proposed approach under stringent conditions.
... Wang et al. [9] used machine learning algorithms such as random forest (RF) and artificial neural network (ANN) for power line classification in suburban and urban areas. Recently, compact and lightweight UAV-LiDAR sensors were presented on the market, although their performance is limited in terms of scan speed and measurement rate [10]. Ax et al. [11] employed the use of laser scanner data from a UAV Helicopter for vegetation control at high-voltage transmission lines. ...
Article
Full-text available
Three-dimensional (3D) mapping of power lines is essential for power line inspection. Many remotely sensed data products like light detection and ranging (LiDAR) have been examined for power line surveys. More and more data are being obtained via photogrammetric measurements. This increases the need for the implementation of advanced processing techniques. In recent years, there has been a significant advancement in visualization techniques for power lines using unmanned aerial vehicle (UAV) platform photography. The most advanced of such imaging systems can create dense point clouds. However, the accuracy is very often unstable and dependent on the radiometric quality of images and the efficiency of the image processing technique. In this study, the two-dimensional information is obtained by photographing the real-time panorama of the transmission line channel using a 3D camera, and the three-dimensional information is acquired using laser radar technology. The three-dimensional point orientation of the target object and the transmission line is determined using the mapping relationship between two and three dimensions, the obtained data are calculated, and the calculation results are produced. The proposed method can solve the problem of the image sensor being unable to map spatial distance and can provide broad coverage of the transmission line channel and 24-hours accurate real-time remote monitoring.
... Others have addressed the detection of components that have failed or that require immediate maintenance work. This has included detection of broken line strands [23]- [25] and measurement of sagging on line segments [26], [27]. However, insulators are the components that have been most studied in terms of automating detection and condition assessment on OHL towers [28]. ...
Article
Full-text available
Electricity networks are critical infrastructure, delivering vital energy services. Due to the significant number, variety and distribution of electrical network overhead line assets, energy network operators spend millions annually on inspection and maintenance programmes. Currently, inspection involves acquiring and manually analysing aerial images. This is labour intensive and subjective. Along with costs associated with helicopter or drone operations, data analysis represents a significant financial burden to network operators.We propose an approach to automating assessment of the condition of electrical towers. Importantly, we train machine learning tower classifiers without using condition labels for individual components of interest. Instead, learning is supervised using only condition labels for towers in their entirety. This enables us to use a real-world industry dataset without needing costly additional human labelling of thousands of individual components. Our prototype first detects instances of components in multiple images of each tower, using Mask R-CNN or RetinaNet. It then predicts tower condition ratings using one of two approaches: (i) component instance classifiers trained using class labels transferred from towers to each of their detected component instances, or (ii) multiple instance learning classifiers based on bags of detected instances. Instance or bag class predictions are aggregated to obtain tower condition ratings. Evaluation used a dataset with representative tower images and associated condition ratings covering a range of component types, scenes, environmental conditions, and viewpoints. We report experiments investigating classification of towers based on the condition of their multiple insulator and U-bolt components. Automated visual detection and analysis of U-bolts has not been previously reported. We demonstrate that tower condition classifiers can be trained effectively without labelling the condition of individual components.
... In recent years, to address the limitations of 2D observations, some studies attempted to generate three-dimensional (3D) point clouds from high-resolution images based on dense matching [27] and derive some distance measurements. For example, Zhang et al. used the dense matching method to reconstruct conductors and ground objects in 3D, and detected obstacles automatically by calculating the distance between the conductor and the ground point cloud extracted from the optical images [28]. ...
Article
In recent decades, a substantial increase in electricity demand has put pressure on powerline systems to ensure an uninterrupted power supply. In order to prevent power failures, timely and thorough powerline inspections are needed to detect possible anomalies in advance. In the past few years, the emerging unmanned aerial vehicle (UAV)-mounted sensors (e.g. light detection and ranging/lidar, optical cameras, infrared cameras, and ultraviolet cameras) have provided rich data sources for comprehensive and accurate powerline inspections. A challenge that still hinders the use of UAVs in powerline inspection is that their operation is highly dependent on the pilot’s experience, which may pose risks to the safety of the powerline system and reduce inspection efficiency. An intelligent automatic inspection solution could overcome the limitations of current UAV-based inspection solutions. The main objective of this paper is to provide a contemporary look at the current state-of-the-art UAV-based inspections as well as to discuss a potential lidar-supported intelligent powerline inspection concept. Overall, standardized protocols for lidar-supported intelligent powerline inspections include four data analysis steps, i.e., point cloud classification, key point extraction, route generation, and fault detection. To demonstrate the feasibility of the proposed concept, we implemented a workflow using a dataset of 3536 powerline spans, showing that the inspection of a single powerline span could be completed in 10 min with only one or two technicians. This demonstrates that lidar-supported intelligent inspection can be used to inspect a powerline system with extremely high efficiency and low costs.
... However, traditional inspection methods are much too reliant on artificial observation or manual analysis of aerial photos and videos, which is inefficient and relies on experience [3]. Meanwhile, PTLs are often exposed to harsh environments or high mountainous areas that are dangerous and difficult to reach for inspectors [4,5]. Therefore, it is a challenging task to detect a wide range of PTLs. ...
... Thus, the PTL classification has received much attention. In recent years, PTL extraction methods have been greatly researched, which mainly include optical images [4,7,[30][31][32], thermal images [33] and point clouds [9,15,28,34] acquired from different platforms. Thermal images are used to detect electrical faults but not for 3D reconstruction in high-voltage electric utilities [35]. ...
Article
Full-text available
Power-line inspection is an important means to maintain the safety of power networks. Light detection and ranging (LiDAR) technology can provide high-precision 3D information about power corridors for automated power-line inspection, so there are more and more utility companies relying on LiDAR systems instead of traditional manual operation. However, it is still a challenge to automatically detect power lines with high precision. To achieve efficient and accurate power-line extraction, this paper proposes an algorithm using entropy-weighting feature evaluation (EWFE), which is different from the existing hierarchical-multiple-rule evaluation of many geometric features. Six significant features are selected (Height above Ground Surface (HGS), Vertical Range Ratio (VRR), Horizontal Angle (HA), Surface Variation (SV), Linearity (LI) and Curvature Change (CC)), and then the features are combined to construct a vector for quantitative evaluation. The feature weights are determined by an entropy-weighting method (EWM) to achieve optimal distribution. The point clouds are filtered out by the HGS feature, which possesses the highest entropy value, and a portion of non-power-line points can be removed without loss of power-line points. The power lines are extracted by evaluation of the other five features. To decrease the interference from pylon points, this paper analyzes performance in different pylon situations and performs an adaptive weight transformation. We evaluate the EWFE method using four datasets with different transmission voltage scales captured by a light unmanned aerial vehicle (UAV) LiDAR system and a mobile LiDAR system. Experimental results show that our method demonstrates efficient performance, while algorithm parameters remain consistent for the four datasets. The precision F value ranges from 98.4% to 99.7%, and the efficiency ranges from 0.9 million points/s to 5.2 million points/s.
... It works in a way, where four strips of aerial images to automatically extract the power line points in the object space are processed. Such approach enables efficient and successful extraction of the power line points positions for power line generation and sag measurement with the elevation accuracy of a few centimeters only (Oh 2017). ...
Conference Paper
In this paper potential implementation of various digital image processing methods for the purpose of the initial, semi-automated spatial object diagnostics was presented. As an example – electrical power line latticework was applied. The study involved also a thorough background study on literature related to diagnostics, which encompassed the subject matter associated with the identification of objects and detection methods of specific properties of the studied object on digital images. In this paper, the authors presented their developed method of virtual photographs as a tool for support the work of technicians in the process of analysis of the photographic material collected during annual areal inspections of the lines. Additionally, this work discusses particular stages of the developed method and its software implementation. The primary objective of the virtual photograph method is to limit the number of analyzed photographs to only those, which indicates the potential risk of inconsistencies with the model – lack of an element or deformation. This paper also presents the analysis of the developed method’s results for different types of photographs, when modification of the values of specific variables affected the achieved results. It also presents the directions of further research in terms of functional development of the method and potential new applications.
... Additionally, there are hardly any cases of a comprehensive methodology for detecting and reconstructing power lines in the literature using neural networks [39]. Additional research on the 3D reconstruction of power lines was presented in two papers by the same authors [40,41]. In both, the lines are initially detected from epipolar images using a simple extraction template. ...
... Three-dimensional reconstruction is performed differently in each, however. One introduces a 3D grid based on the expected ground sampling distance (GSD) and the positions of the utility poles [40]. The grid is then reprojected on images to validate the detected power lines and establish their relative correspondence. ...
... The algorithm does not require an extensive learning set, which makes it different from many deep learning methods [37,38], which are currently gaining popularity. Similar to some other solutions [23,35,40,41], wire reconstruction in 3D space is performed using epipolar geometry. However, the proposed RANSAC-based approach to fit the catenary curve to previously obtained points representing the wires minimizes the noise. ...
Article
Full-text available
Regular power line inspections are essential to ensure the reliability of electricity supply. The inspections of overground power submission lines include corridor clearance monitoring and fault identification. The power lines corridor is a three-dimensional space around power cables defined by a set distance. Any obstacles breaching this space should be detected, as they potentially threaten the safety of the infrastructure. Corridor clearance monitoring is usually performed either by a labor-intensive total station survey (TS), terrestrial laser scanning (TLS), or expensive airborne laser scanning (ALS) from a plane or a helicopter. This paper proposes a method that uses unmanned aerial vehicle (UAV) images to monitor corridor clearance. To maintain the adequate accuracy of the relative position of wires in regard to surrounding obstacles, the same data were used both to reconstruct a point cloud representation of a digital surface model (DSM) and a 3D power line. The proposed algorithm detects power lines in a series of images using decorrelation stretch for initial image processing, the modified Prewitt filter for edge enhancement, random sample consensus (RANSAC) with additional parameters for line fitting, and epipolar geometry for 3D reconstruction. DSM points intruding into the corridor are then detected by calculating the spatial distance between a reconstructed power line and the DSM point cloud representation. Problematic objects are localized by segmenting points into voxels and then subsequent clusterization. The processing results were compared to the results of two verification methods—TS and TLS. The comparison results show that the proposed method can be used to survey power lines with an accuracy consistent with that of classical measurements.
... Inspection methods based on images [5], [9] use photogrammetric techniques for the wires and obstacles detection. Automatic extraction of the powerline can be based on the conventional image-to-object space [5] or object-to-image space [8] approach. ...
... Unlike the conventional image-to-object space approach that extracts image features, performs image matching, and reconstructs 3-D coordinates, in [9], the object-to-image space approach has been described. In particular, after a bundle adjustment of the images and line extraction in image space, cubic grid points were generated around the target powerlines in the 3-D object space. ...
Article
Powerline inspection is an important task for electric power management. Corridor mapping, i.e., the task of surveying the surroundings of the line and detecting potentially hazardous vegetation and objects, is performed by aerial light detection and ranging (LiDAR) survey. To this purpose, the main tasks are automatic extraction of the wires and measurement of the distance of objects close to the line. In this article, we present a new fully automated solution, which does not use time-consuming line fitting method, but is based on simple geometrical assumptions and relies on the fact that wire points are isolated, sparse and widely separated from all other points in the data set. In particular, we detect and classify pylons by local-maxima strategy. Then, a new reference system, having its origin on the first pylon and y-axis toward the second one, is defined. In this new reference system, transverse sections of the raw point cloud are extracted; by iterating such procedure for all detected pylons, we are able to detect the wire bundle. Obstacles are then automatically detected according to corridor mapping requirements. The algorithm is tested on two relevant data sets.
... Satellites and aerial vehicles provide cheaper and fast ways of inspecting them. They allow capturing the images of the power lines remotely [2]. They provide potentials for automatic extraction of the power lines so as to derive fast and up-to-date information. ...
... In [13] epipolar constraints based power line automatic measurement and semi patch matching methods were used in extracting 2D and 3D power lines from epipolar images. A 3D power lines extraction method from aerial images was also proposed using photogrammetric parameters, filtering and cubic grid points [2]. ...
Article
Full-text available
High resolution remote sensing systems provide cheaper and fast way of acquiring images of power lines. However, such images depicting the details of other complex background objects, noises, and complicated brightness measurements, make separate extraction of the power lines challenging. This paper addresses the problem of automatic extraction of power lines from high resolution remote sensing images obtained from different sources. In order to automatically extract the power lines, we proposed an integrated Multiscale Geometric Analysis (MGA) approach. First, complementary Gabor and matched filters (MF) were employed over an image to suppress unnecessary background and noises, and initial discrimination of the power lines. Then, the filtering output was decomposed in to scale and orientation based subband coefficients using the Fast Discrete Curvelet Transform (FDCT) so as to access and modify different image features separately. By employing selective modification operations, well-established power line structures ready for extraction were derived. Finally the powerlines were extracted with hysteresis thresholding. The approach was successful in extracting power lines from high resolution images captured in any orientation. It is robust even when the source image is cluttered, and degraded due to noise and brightness effects. Power lines represented by weak intensities, crossing bright image regions, changing direction, closer power lines and those crossing each other, disconnected/broken power lines due to noise and occlusions were all inferred and extracted successfully. The approach was validated using real test images and the performance measures showed over 90% average accuracy fitting the ground truth.