Powerline Tracking with Event Cameras

Abstract

Autonomous inspection of powerlines with quadrotors is challenging. Flights require persistent perception to keep a close look at the lines. We propose a method that uses event cameras to robustly track powerlines. Event cameras are inherently robust to motion blur, have low latency, and high dynamic range. Such properties are advantageous for autonomous inspection of powerlines with drones, where fast motions and challenging illumination conditions are ordinary. Our method identifies lines in the stream of events by detecting planes in the spatio-temporal signal, and tracks them through time. The implementation runs onboard and is capable of detecting multiple distinct lines in real time with rates of up to 320 thousand events per second. The performance is evaluated in real-world flights along a powerline. The tracker is able to persistently track the powerlines, with a mean lifetime of the line 10× longer than existing approaches.

Autonomous aerial robotics for package delivery: A technical review

“…For delivery vehicles, given the prior knowledge of the delivery route or global plan, UAVs can increase the chance of detecting an obstacle. One such example is the tracking of narrow powerlines (Dietsche et al, 2021). This is a challenging task due to the UAV's fast motion and challenging environmental illuminating conditions.…”

Inspection and Maintenance

“…In AERIAL-CORE, we have developed an RGB-based [4] and an Event-based [5] power line tracker, (see Figure 3). The RGB-based power line tracker [4] is a novel algorithm that extends the deep-learning-based object detector in [6] to the case of power line detection.…”

“…Then, they are advantageous for the autonomous inspection of power lines with drones, where fast motions and challenging illumination conditions are ordinary. Our event-based power line tracker [5] identifies lines in the stream of events by detecting planes in the spatio-temporal signal and tracking them through time. Our algorithm can persistently track the power lines, with a mean lifetime of the line 10 times longer than existing approaches [9].…”

“…The predicted bounding boxes are then used in the gesture recognition pipeline. To maximize human worker detection accuracy, both the detector and the tracker were pre-trained on a manually annotated dataset 5 and then fine-tuned using videos of a human operator wearing safety equipment.…”

A Novel Charging Station on Overhead Power Lines for Autonomous Unmanned Drones

“…Drones can be fitted with cameras for visual and thermographic inspections to detect anomalous temperatures or with LiDAR sensors to create 3D maps [1] and can operate in remote areas and harsh environments [2]. These techniques for inspection enable both corrective and predictive maintenance [3] and are suitable for use in high-, medium-and low-voltage overhead lines [4][5][6][7]; substations; and protection and remote-control systems, among others. Tasks related to grid maintenance include felling, pruning, clearing and removing elements of the forest area from the electrical overhead line.…”