Vision-Based Power Line Cables and Pylons Detection for Low Flying Aircraft

• URL: http://arxiv.org/abs/2407.14352v3
• Date: Tue, 30 Jul 2024 09:01:26 GMT
• Title: Vision-Based Power Line Cables and Pylons Detection for Low Flying Aircraft
• Authors: Jakub Gwizdała, Doruk Oner, Soumava Kumar Roy, Mian Akbar Shah, Ad Eberhard, Ivan Egorov, Philipp Krüsi, Grigory Yakushev, Pascal Fua,
• Abstract summary: We have developed a deep learning approach to jointly detect power line cables and pylons. We have combined a modern convolutional architecture with transfer learning and a loss function adapted to curvilinear structure delineation. We have integrated it within an onboard system and run it in flight, and have demonstrated with our experiments that it outperforms the prior distant cable detection method.
• Score: 33.552660821272205
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Power lines are dangerous for low-flying aircraft, especially in low-visibility conditions. Thus, a vision-based system able to analyze the aircraft's surroundings and to provide the pilots with a "second pair of eyes" can contribute to enhancing their safety. To this end, we have developed a deep learning approach to jointly detect power line cables and pylons from images captured at distances of several hundred meters by aircraft-mounted cameras. In doing so, we have combined a modern convolutional architecture with transfer learning and a loss function adapted to curvilinear structure delineation. We use a single network for both detection tasks and demonstrated its performance on two benchmarking datasets. We have integrated it within an onboard system and run it in flight, and have demonstrated with our experiments that it outperforms the prior distant cable detection method on both datasets, while also successfully detecting pylons, given their annotations are available for the data.

Related papers

• Expert Switching for Robust AAV Landing: A Dual-Detector Framework in Simulation [0.0]
  Two YOLOv8 experts are trained on scale-specialized versions of the HelipadCat dataset.<n>During inference, both experts operate in parallel, and a geometric gating mechanism selects the expert whose prediction is most consistent with the AAV's viewpoint.<n>Results show substantial improvements in alignment, landing accuracy, and overall robustness compared to single-detector baselines.
  arXiv  Detail & Related papers  (2025-12-16T03:41:59Z)
• J-DDL: Surface Damage Detection and Localization System for Fighter Aircraft [18.53607676786071]
  We propose a smart surface damage detection and localization system for fighter aircraft, termed J-DDL.<n>J-DDL integrates 2D images and 3D point clouds of the entire aircraft surface, captured using a combined system of laser scanners and cameras.<n>Key innovations include lightweight Fasternet blocks for efficient feature extraction, an optimized neck architecture, and the introduction of a novel loss function, Inner-CIOU.
  arXiv  Detail & Related papers  (2025-06-12T09:05:35Z)
• Bringing RGB and IR Together: Hierarchical Multi-Modal Enhancement for Robust Transmission Line Detection [67.02804741856512]
  We propose a novel Hierarchical Multi-Modal Enhancement Network (HMMEN) that integrates RGB and IR data for robust and accurate TL detection. Our method introduces two key components: (1) a Mutual Multi-Modal Enhanced Block (MMEB), which fuses and enhances hierarchical RGB and IR feature maps in a coarse-to-fine manner, and (2) a Feature Alignment Block (FAB) that corrects misalignments between decoder outputs and IR feature maps by leveraging deformable convolutions.
  arXiv  Detail & Related papers  (2025-01-25T06:21:06Z)
• Commissioning An All-Sky Infrared Camera Array for Detection Of Airborne Objects [0.11703603440337004]
  The Galileo Project is designing, building, and commissioning a multi-modal ground-based observatory to continuously monitor the sky. One of the key instruments is an all-sky infrared camera array using eight uncooled long-wave infrared FLIR Boson 640 cameras. We report acceptance rates (e.g. viewable airplanes that are recorded) and detection efficiencies (e.g. recorded airplanes which are successfully detected) for a variety of weather conditions. A toy outlier search focused on large sinuosity of the 2-D reconstructed trajectories flags about 16% of trajectories as outliers.
  arXiv  Detail & Related papers  (2024-11-12T17:31:51Z)
• Power Line Aerial Image Restoration under dverse Weather: Datasets and Baselines [17.3009572002435]
  Power Line Autonomous Inspection (PLAI) plays a crucial role in the construction of smart grids. PLAI is completed by accurately detecting the electrical components and defects in the aerial images captured byUAVs. The visible quality of aerial images is inevitably degraded by adverse weather like haze, rain, or snow, which are found to drastically decrease the detection accuracy in our research. We propose a new task of Power Line Aerial Image Restoration under Adverse Weather (PLAIR-AW), which aims to recover clean and high-quality images from degraded images with bad weather.
  arXiv  Detail & Related papers  (2024-09-07T12:53:05Z)
• Better Monocular 3D Detectors with LiDAR from the Past [64.6759926054061]
  Camera-based 3D detectors often suffer inferior performance compared to LiDAR-based counterparts due to inherent depth ambiguities in images. In this work, we seek to improve monocular 3D detectors by leveraging unlabeled historical LiDAR data. We show consistent and significant performance gain across multiple state-of-the-art models and datasets with a negligible additional latency of 9.66 ms and a small storage cost.
  arXiv  Detail & Related papers  (2024-04-08T01:38:43Z)
• Autonomous Point Cloud Segmentation for Power Lines Inspection in Smart Grid [56.838297900091426]
  An unsupervised Machine Learning (ML) framework is proposed, to detect, extract and analyze the characteristics of power lines of both high and low voltage. The proposed framework can efficiently detect the power lines and perform PLC-based hazard analysis.
  arXiv  Detail & Related papers  (2023-08-14T17:14:58Z)
• AirTrack: Onboard Deep Learning Framework for Long-Range Aircraft Detection and Tracking [3.3773749296727535]
  AirTrack is a real-time vision-only detect and tracking framework that respects the size, weight, and power constraints of sUAS systems. We show that AirTrack outperforms state-of-the art baselines on the Amazon Airborne Object Tracking (AOT) Empirical evaluations show that our system has a probability of track of more than 95% up to a range of 700m.
  arXiv  Detail & Related papers  (2022-09-26T16:58:00Z)
• Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Images [96.66271207089096]
  FCOS-LiDAR is a fully convolutional one-stage 3D object detector for LiDAR point clouds of autonomous driving scenes. We show that an RV-based 3D detector with standard 2D convolutions alone can achieve comparable performance to state-of-the-art BEV-based detectors.
  arXiv  Detail & Related papers  (2022-05-27T05:42:16Z)
• The State of Aerial Surveillance: A Survey [62.198765910573556]
  This paper provides a comprehensive overview of human-centric aerial surveillance tasks from a computer vision and pattern recognition perspective. The main object of interest is humans, where single or multiple subjects are to be detected, identified, tracked, re-identified and have their behavior analyzed.
  arXiv  Detail & Related papers  (2022-01-09T20:13:27Z)
• It's All Around You: Range-Guided Cylindrical Network for 3D Object Detection [4.518012967046983]
  This work presents a novel approach for analyzing 3D data produced by 360-degree depth scanners. We introduce a novel notion of range-guided convolutions, adapting the receptive field by distance from the ego vehicle and the object's scale. Our network demonstrates powerful results on the nuScenes challenge, comparable to current state-of-the-art architectures.
  arXiv  Detail & Related papers  (2020-12-05T21:02:18Z)
• Perceiving Traffic from Aerial Images [86.994032967469]
  We propose an object detection method called Butterfly Detector that is tailored to detect objects in aerial images. We evaluate our Butterfly Detector on two publicly available UAV datasets (UAVDT and VisDrone 2019) and show that it outperforms previous state-of-the-art methods while remaining real-time.
  arXiv  Detail & Related papers  (2020-09-16T11:37:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.