TACO: Trajectory Aligning Cross-view Optimisation

TL;DR

TACO is a novel pipeline combining IMU and fine-grained cross-view geo-localisation to improve trajectory accuracy with minimal computational cost, using a single initial GNSS fix.

Contribution

It introduces a tightly-coupled IMU and CVGL system with a cross-track error model, multi-crop search, and loop closure for accurate, real-time trajectory estimation.

Findings

Reduced median ATE from 97.0m to 16.3m on KITTI dataset

Operates at less than 0.1 ms per-frame fusion cost

Uses only 5-10% camera duty cycle

Abstract

Cross-View Geo-localisation (CVGL) matches ground imagery against satellite tiles to give absolute position fixes, an alternative to GNSS where signals are occluded, jammed, or spoofed. Recent fine-grained CVGL methods regress sub-tile metric pose, but have only been evaluated as one-shot localisers, never as the primary fix in a live pipeline. Inertial sensing provides high-rate relative motion, but accumulates unbounded drift without an absolute anchor. We propose TACO, a tightly-coupled IMU + fine-grained CVGL pipeline that consumes a single GNSS reading at start-up and thereafter operates on onboard sensing alone. A closed-form cross-track error model triggers CVGL before IMU drift exceeds the matcher's capture radius, and a forward-biased five-point multi-crop search keeps inference cost fixed at five forward passes per fix. A yaw-residual gate rejects fixes that disagree with the onboard compass, and an anisotropic body-frame noise model scales each Unscented Kalman Filter update by per-fix confidence. A factor graph with vetted loop closures provides an offline smoothed trajectory. On the KITTI raw dataset, TACO reduces median Absolute Trajectory Error (ATE) from 97.0m (IMU-only) to 16.3m, a 5.9 times reduction, at <0.1 ms per-frame fusion cost and a 5-10% camera duty cycle. Code is available: github.com/tavisshore/TACO.