Mapping Utility Poles in Aerial Orthoimages Using ATSS Deep Learning Method

Mapping utility poles using side-view images acquired with car-mounted cameras is a time-consuming task, mainly in larger areas due to the need for street-by-street surveying. Aerial images cover larger areas and can be feasible alternatives although the detection and mapping of the utility poles in urban environments using top-view images is challenging. Thus, we propose the use of Adaptive Training Sample Selection (ATSS) for detecting utility poles in urban areas since it is a novel method and has not yet investigated in remote sensing applications. Here, we compared ATSS with Faster Region-based Convolutional Neural Networks (Faster R-CNN) and Focal Loss for Dense Object Detection (RetinaNet ), currently used in remote sensing applications, to assess the performance of the proposed methodology. We used 99,473 patches of 256 × 256 pixels with ground sample distance (GSD) of 10 cm. The patches were divided into training, validation and test datasets in approximate proportions of 60%, 20% and 20%, respectively. As the utility pole labels are point coordinates and the object detection methods require a bounding box, we assessed the influence of the bounding box size on the ATSS method by varying the dimensions from 30×30 to 70×70 pixels. For the proposal task, our findings show that ATSS is, on average, 5% more accurate than Faster R-CNN and RetinaNet. For a bounding box size of 40×40, we achieved Average Precision with intersection over union of 50% (AP50) of 0.913 for ATSS, 0.875 for Faster R-CNN and 0.874 for RetinaNet. Regarding the influence of the bounding box size on ATSS, our results indicate that the AP50 is about 6.5% higher for 60×60 compared to 30×30. For AP75, this margin reaches 23.1% in favor of the 60×60 bounding box size. In terms of computational costs, all the methods tested remain at the same level, with an average processing time around of 0.048 s per patch. Our findings show that ATSS outperforms other methodologies and is suitable for developing operation tools that can automatically detect and map utility poles.

[1]  Raul Queiroz Feitosa,et al.  Assessment of CNN-Based Methods for Individual Tree Detection on Images Captured by RGB Cameras Attached to UAVs , 2019, Sensors.

[2]  Nilton Nobuhiro Imai,et al.  A convolutional neural network approach for counting and geolocating citrus-trees in UAV multispectral imagery , 2020, ISPRS Journal of Photogrammetry and Remote Sensing.

[3]  Hongzhang Xu,et al.  Deep learning in environmental remote sensing: Achievements and challenges , 2020, Remote Sensing of Environment.

[4]  The influence of cement type and admixture on life span of reinforced concrete utility poles subjected to the high salinity environment of Northeastern Brazil, studied by corrosion potential testing , 2004 .

[5]  Avik Bhattacharya,et al.  CMIR-NET : A Deep Learning Based Model For Cross-Modal Retrieval In Remote Sensing , 2019, Pattern Recognit. Lett..

[6]  Md Morshedul Alam,et al.  Automatic Assessment and Prediction of the Resilience of Utility Poles Using Unmanned Aerial Vehicles and Computer Vision Techniques , 2020, International Journal of Disaster Risk Science.

[7]  Gang Wan,et al.  Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark , 2020, ISPRS Journal of Photogrammetry and Remote Sensing.

[8]  Zhecheng Wang,et al.  Fine-Grained Distribution Grid Mapping Using Street View Imagery , 2019 .

[9]  Lingxuan Meng,et al.  Real-Time Detection of Ground Objects Based on Unmanned Aerial Vehicle Remote Sensing with Deep Learning: Application in Excavator Detection for Pipeline Safety , 2020, Remote. Sens..

[10]  Juha Hyyppä,et al.  Detection of Vertical Pole-Like Objects in a Road Environment Using Vehicle-Based Laser Scanning Data , 2010, Remote. Sens..

[11]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Wuming Zhang,et al.  Quantifying Understory and Overstory Vegetation Cover Using UAV-Based RGB Imagery in Forest Plantation , 2020, Remote. Sens..

[13]  Shifeng Zhang,et al.  Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  José Marcato Junior,et al.  Storm-Drain and Manhole Detection Using the RetinaNet Method , 2020, Sensors.

[15]  Yuzo Iano,et al.  Automatic Detection of Utility Poles Using the Bag of Visual Words Method for Different Feature Extractors , 2017, CAIP.

[16]  Tanima Dutta,et al.  Image Analysis-Based Automatic Utility Pole Detection for Remote Surveillance , 2015, 2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA).

[17]  Liang Zhu,et al.  How Well Do Deep Learning-Based Methods for Land Cover Classification and Object Detection Perform on High Resolution Remote Sensing Imagery? , 2020, Remote. Sens..

[18]  Kaiming He,et al.  Feature Pyramid Networks for Object Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Ross B. Girshick,et al.  Focal Loss for Dense Object Detection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Subasish Das,et al.  Severity analysis of tree and utility pole crashes: Applying fast and frugal heuristics , 2020 .

[21]  Brian C. Lovell,et al.  Deep Inspection: An Electrical Distribution Pole Parts Study VIA Deep Neural Networks , 2019, 2019 IEEE International Conference on Image Processing (ICIP).

[22]  Lúcio André de Castro Jorge,et al.  Deep Learning Applied to Phenotyping of Biomass in Forages with UAV-Based RGB Imagery , 2020, Sensors.

[23]  Li Zhu,et al.  Landslide Susceptibility Prediction Modeling Based on Remote Sensing and a Novel Deep Learning Algorithm of a Cascade-Parallel Recurrent Neural Network , 2020, Sensors.

[24]  Hao Chen,et al.  FCOS: Fully Convolutional One-Stage Object Detection , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[25]  Weidong Li,et al.  Using Deep Learning to Identify Utility Poles with Crossarms and Estimate Their Locations from Google Street View Images , 2018, Sensors.

[26]  Raul Queiroz Feitosa,et al.  Applying Fully Convolutional Architectures for Semantic Segmentation of a Single Tree Species in Urban Environment on High Resolution UAV Optical Imagery , 2020, Sensors.