Wire Detection, Reconstruction, and Avoidance for Unmanned Aerial Vehicles

Abstract

Thin objects, such as wires and power lines are one of the most challenging obstacles to detect and avoid for UAVs, and are a cause of numerous accidents each year. This thesis makes contributions in three areas of this domain: wire segmentation, reconstruction, and avoidance.

Pixelwise wire detection can be framed as a binary semantic segmentation task. Due to the lack of a labeled dataset for this task, we generate one by rendering photorealistic wires from synthetic models and compositing them into frames from publicly available flight videos. We show that dilated convolutional networks trained on this synthetic dataset in conjunction with a few real images perform with reasonable accuracy and speed on real-world data on a portable GPU.

Given the pixel-wise segmentations, we develop a method for 3D wire reconstruction. Our method is a model-based multi-view algorithm, which employs a minimal parameterization of wires as catenary curves. We propose a bundle adjustment-style framework to recover the model parameters using non-linear least squares optimization, while obviating the need to find pixel correspondences by using the distance transform as our loss function. In addition, we propose a model-free voxel grid method to reconstruct wires via a pose graph of disparity images, and briefly discuss the pros and cons of each method.

To close the sensing-planning loop for wire avoidance, we demonstrate a reactive, trajectory library-based planner coupled with our model-free reconstruction method in experiments with a real UAV.