TRADE: Object Tracking with 3D Trajectory and Ground Depth Estimates for UAVs

TL;DR

TRADE is a novel method enabling robust 3D target tracking and localization from UAVs using a single camera, combining trajectory prediction and scene geometry reasoning to improve accuracy in complex environments.

Contribution

It introduces a new 3D localization approach and trajectory-based target selection for UAVs, enhancing robustness and depth estimation in cluttered terrains.

Findings

Improved tracking robustness in dynamic scenes

Accurate 3D ground target localization

Successful autonomous target following with thermal cameras

Abstract

We propose TRADE for robust tracking and 3D localization of a moving target in cluttered environments, from UAVs equipped with a single camera. Ultimately TRADE enables 3d-aware target following. Tracking-by-detection approaches are vulnerable to target switching, especially between similar objects. Thus, TRADE predicts and incorporates the target 3D trajectory to select the right target from the tracker's response map. Unlike static environments, depth estimation of a moving target from a single camera is a ill-posed problem. Therefore we propose a novel 3D localization method for ground targets on complex terrain. It reasons about scene geometry by combining ground plane segmentation, depth-from-motion and single-image depth estimation. The benefits of using TRADE are demonstrated as tracking robustness and depth accuracy on several dynamic scenes simulated in this work. Additionally, we demonstrate autonomous target following using a thermal camera by running TRADE on a quadcopter's board computer.