Trajectory-Anchor Optimization for Overconfident Thermal Visual Place Recognition: Zero-Leakage OOD Auditing and Kidnapped-Robot Recovery
2026-07-06 • Robotics
RoboticsComputer Vision and Pattern Recognition
AI summaryⓘ
The authors address a problem in thermal visual place recognition where current methods mistakenly think they recognize places even when they don't (false loops). They propose Trajectory-Anchor Optimization (TAO), which efficiently checks many possible place matches at once using a math trick to keep the calculations fast. TAO works well by spotting big errors over larger distances, filtering out wrong matches that look too similar locally but don't fit the overall map. This helps reduce mistakes without slowing down robots in real time.
thermal visual place recognitionfoundation modelsout-of-distributionmulti-hypothesis trackingSE(2) Procrustes alignmentbatched SVDtrajectory optimizationtemporal verificationgeometric consistencytopological breaks
Authors
Zhiyuan Lu, Kanji Tanaka
Abstract
Modern thermal visual place recognition (TIR-VPR) frontends based on foundation models achieve remarkable closed-set retrieval but suffer from an overconfident forced-matching failure mode. Under out-of-distribution (OOD) or unmapped conditions, they generate highly plausible yet false loop candidates without a drop in similarity scores. While classical multi-hypothesis tracking (MHT) backends can mitigate these ambiguities by maintaining divergent trajectory beliefs, their exponential computational overhead violates real-time robotic constraints. To bridge this gap, we present Trajectory-Anchor Optimization (TAO). To counter the combinatorial challenge of evaluating parallel hypotheses (e.g., K=100), TAO compresses multi-view temporal verification into a batched SE(2) Procrustes alignment problem. By leveraging tensor-level vectorization and single-invocation batched SVD, this formulation bypasses the dynamic tree expansion of MHT, guaranteeing a strictly bounded per-frame execution loop of O(KN). Under a strict zero-leakage evaluation protocol, we show that while a passive geometric backend cannot mathematically separate metric localization errors from coherent hallucinations at a micro-scale (<5m) due to local visual ambiguities, TAO serves as an efficient fail-safe filter at a macro-scale. Within a 5m radius, hallucinations often possess a locally consistent geometry that deceives rigid alignment. However, beyond this threshold, the K=100 disparate hypotheses disperse spatially across the global map. This dispersion breaks the rigid temporal co-visibility constraint within the sliding window (N=20), causing the joint optimization residual to escalate sharply. Consequently, TAO establishes a distinct macroscopic convergence basin (10m) where multi-view geometric consistency reliably isolates catastrophic topological breaks and suppresses critical false acceptances.