Fast, Accurate Thin-Structure Obstacle Detection for Autonomous Mobile Robots

TL;DR

This paper introduces fast and accurate methods for detecting thin obstacles like wires and branches using video sequences, enhancing safety for autonomous robots with monocular and stereo cameras.

Contribution

It presents novel edge-based visual odometry techniques for thin obstacle detection, including a monocular solution with IMU integration and a stereo vision approach.

Findings

Methods are fast and robust across various conditions

Accurately detect thin obstacles such as wires and branches

Improve safety for autonomous mobile robots

Abstract

Safety is paramount for mobile robotic platforms such as self-driving cars and unmanned aerial vehicles. This work is devoted to a task that is indispensable for safety yet was largely overlooked in the past -- detecting obstacles that are of very thin structures, such as wires, cables and tree branches. This is a challenging problem, as thin objects can be problematic for active sensors such as lidar and sonar and even for stereo cameras. In this work, we propose to use video sequences for thin obstacle detection. We represent obstacles with edges in the video frames, and reconstruct them in 3D using efficient edge-based visual odometry techniques. We provide both a monocular camera solution and a stereo camera solution. The former incorporates Inertial Measurement Unit (IMU) data to solve scale ambiguity, while the latter enjoys a novel, purely vision-based solution. Experiments demonstrated that the proposed methods are fast and able to detect thin obstacles robustly and accurately under various conditions.