Automated electric utility pole detection from aerial images

Çetin, Burhanettin; Bikdash, Marwan; McInerney, Michael K.

doi:10.1109/secon.2009.5174047

Cited by 14 publications

(10 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We can also extrapolate and observe other applications that are related to the problem, such as the detection of poles in aerial images in [9], which uses the detection of the shadow of the poles and techniques such as pattern matching and feature extraction.…”

Section: Related Workmentioning

confidence: 90%

Inspection of Electric Power Distribution Systems with SCRDet

Restani¹,

Coelho²,

Filho³

2021

Anais Do 15. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

Faults in power distribution systems are among the factors that most affect the quality and continuity of the electric power supply, leading to higher operational costs and user dissatisfaction. Given this problem, this research applies deep learning techniques to develop an application capable of detecting utility poles in images, their angles, and the presence of fuse cutouts and their status (open or closed). The result is a system that can be used, among other applications, to detect or prevent faults in power distribution systems and as an asset inventory tool. We hypothesized that it is possible to use methods that perform well in the Dataset for Object Detection in Aerial images (DOTA) to accomplish this result, so, through the review of state of the art in object detection, we choose the SCRDet network to implement. Since there was no publicly available dataset with images of poles and fuse cutouts, we built it from scratch. Through the training and test, it was possible to evaluate the results and make adjustments, reaching a satisfactory result that has proven the viability of such application.

show abstract

Section: Related Workmentioning

confidence: 90%

Inspection of Electric Power Distribution Systems with SCRDet

Restani¹,

Coelho²,

Filho³

2021

Anais Do 15. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

show abstract

“…In practice, the shape of the pole-top of a utility pole varies and is usually occluded or mingled with other objects in images. Cetin et al (2009) proposed a method to locate utility poles from aerial images by detecting the shadow of a pole. The method is limited due to its requirement of a clear shadow falling on a plain terrain.…”

Section: Application Of a Convolutional Neural Network (Cnn) To Visuamentioning

confidence: 99%

Automatic Assessment and Prediction of the Resilience of Utility Poles Using Unmanned Aerial Vehicles and Computer Vision Techniques

Alam

Zhu

Tokgoz

et al. 2020

Int J Disaster Risk Sci

View full text Add to dashboard Cite

The utility poles of electric power distribution lines are very vulnerable to many natural hazards, while power outages due to pole failures can lead to adverse economic and social consequences. Utility companies, therefore, need to monitor the conditions of poles regularly and predict their future conditions accurately and promptly to operate the distribution system continuously and safely. This article presents a novel pole monitoring method that uses state-of-the-art deep learning and computer vision methods to meet the need. The proposed method automatically captures the current pole inclination angles using an unmanned aerial vehicle. The method calculates the bending moment exerted on the poles due to wind and gravitational forces, as well as cable weight, to compare it with the moment of rupture. The method also includes a machine learning-based model that is built by using a support vector machine to predict the resilience conditions of a pole after a wind event in a faster manner. The three modules of the proposed method are effective tools to classify pole conditions and are expected to enable utility companies to increase the resilience of their systems.

show abstract

“…For example, after hurricane Maria struck Puerto Rico in September of 2017, the lack of accurate maps for buildings, bridges, and electric facilities was considered as a main factor slowing recovery efforts [ 3 ]. Mapping utility poles is labor- and time-intense because the process is usually conducted using human interpretation of high spatial-resolution aerial imagery, ground-based field surveys, or unmanned aerial vehicles (UAVs)/helicopters [ 2 , 4 ]. The high degree of labor requirement makes mapping utility poles over large areas a daunting task.…”

Section: Introductionmentioning

confidence: 99%

“…Utility mapping has been explored using optical sensors, on both satellite and aerial platforms [ 5 , 6 , 7 , 8 , 9 , 10 , 11 , 12 ]; synthetic aperture radars (SAR) [ 13 , 14 ], and light detection and ranging (LiDAR) [ 15 , 16 , 17 , 18 , 19 ]. Cetin and Bikdash [ 4 ] mapped utility poles using shadow information derived from aerial images and Sun et al [ 20 ] mapped power poles using stereo images. Wang et al [ 19 ] developed a semi-automated method to classify power lines from LiDAR data in urban areas with both precision and recall up to 98%.…”

Section: Introductionmentioning

confidence: 99%

“…Wang et al [ 19 ] developed a semi-automated method to classify power lines from LiDAR data in urban areas with both precision and recall up to 98%. However, due to the small size of utility distribution poles, the spatial resolution of most satellite platforms is not sufficient for reliable detection [ 4 , 21 ]. The ultra-high spatial resolutions provided by UAV platforms have made them an emerging tool for surveying electric utilities [ 22 , 23 , 24 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Using Deep Learning to Identify Utility Poles with Crossarms and Estimate Their Locations from Google Street View Images

Zhang

Witharana

et al. 2018

Sensors

View full text Add to dashboard Cite

Traditional methods of detecting and mapping utility poles are inefficient and costly because of the demand for visual interpretation with quality data sources or intense field inspection. The advent of deep learning for object detection provides an opportunity for detecting utility poles from side-view optical images. In this study, we proposed using a deep learning-based method for automatically mapping roadside utility poles with crossarms (UPCs) from Google Street View (GSV) images. The method combines the state-of-the-art DL object detection algorithm (i.e., the RetinaNet object detection algorithm) and a modified brute-force-based line-of-bearing (LOB, a LOB stands for the ray towards the location of the target [UPC at here] from the original location of the sensor [GSV mobile platform]) measurement method to estimate the locations of detected roadside UPCs from GSV. Experimental results indicate that: (1) both the average precision (AP) and the overall accuracy (OA) are around 0.78 when the intersection-over-union (IoU) threshold is greater than 0.3, based on the testing of 500 GSV images with a total number of 937 objects; and (2) around 2.6%, 47%, and 79% of estimated locations of utility poles are within 1 m, 5 m, and 10 m buffer zones, respectively, around the referenced locations of utility poles. In general, this study indicates that even in a complex background, most utility poles can be detected with the use of DL, and the LOB measurement method can estimate the locations of most UPCs.

show abstract

Automated electric utility pole detection from aerial images

Cited by 14 publications

References 10 publications

Inspection of Electric Power Distribution Systems with SCRDet

Inspection of Electric Power Distribution Systems with SCRDet

Automatic Assessment and Prediction of the Resilience of Utility Poles Using Unmanned Aerial Vehicles and Computer Vision Techniques

Using Deep Learning to Identify Utility Poles with Crossarms and Estimate Their Locations from Google Street View Images

Contact Info

Product

Resources

About