LS-Net: fast single-shot line-segment detector
- PDF / 3,209,107 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 22 Downloads / 204 Views
ORIGINAL PAPER
LS-Net: fast single-shot line-segment detector Van Nhan Nguyen1
· Robert Jenssen1 · Davide Roverso2
Received: 18 March 2020 / Revised: 23 September 2020 / Accepted: 6 October 2020 © The Author(s) 2020
Abstract In unmanned aerial vehicle (UAV) flights, power lines are considered as one of the most threatening hazards and one of the most difficult obstacles to avoid. In recent years, many vision-based techniques have been proposed to detect power lines to facilitate self-driving UAVs and automatic obstacle avoidance. However, most of the proposed methods are typically based on a common three-step approach: (i) edge detection, (ii) the Hough transform, and (iii) spurious line elimination based on power line constrains. These approaches not only are slow and inaccurate but also require a huge amount of effort in post-processing to distinguish between power lines and spurious lines. In this paper, we introduce LS-Net, a fast single-shot line-segment detector, and apply it to power line detection. The LS-Net is by design fully convolutional, and it consists of three modules: (i) a fully convolutional feature extractor, (ii) a classifier, and (iii) a line segment regressor. Due to the unavailability of large datasets with annotations of power lines, we render synthetic images of power lines using the physically based rendering approach and propose a series of effective data augmentation techniques to generate more training data. With a customized version of the VGG-16 network as the backbone, the proposed approach outperforms existing state-of-the-art approaches. In addition, the LS-Net can detect power lines in near real time. This suggests that our proposed approach has a promising role in automatic obstacle avoidance and as a valuable component of self-driving UAVs, especially for automatic autonomous power line inspection. Keywords Line segment detection · Power line detection · Power line inspection · Deep learning · UAVs
1 Introduction Obstacle detection and avoidance are the key to ensure low altitude fight safety. Due to their extremely small size, power lines are considered as one of the most threatening hazards and one of the most difficult obstacles for unmanned aerial vehicles (UAVs) to avoid [31]. In automatic autonomous vision-based power line inspection, power line detection is crucial, not only for ensuring flight safety, and for vision-based navigation of UAVs, but also for inspection to identify faults on power lines (e.g., cor-
B
Van Nhan Nguyen [email protected] Robert Jenssen [email protected] Davide Roverso [email protected]
1
The UiT Machine Learning Group, UiT The Arctic University of Norway, 9019 Tromsø, Norway
2
Analytics Department, eSmart Systems, 1783 Halden, Norway
roded and damaged power lines) and surrounding objects, such as vegetation encroachment [26]. In recent years, many techniques have been proposed to detect power lines automatically. However, most of the proposed methods are typically based on a common three-step approach:
Data Loading...
