Understanding Identity Continuity in Thermal Video through Scene-Level Consistency
For thermal pedestrian tracking applications, the paper shows that simple post-processing can recover identity continuity more effectively than increasing tracker complexity.
The paper addresses trajectory fragmentation in thermal pedestrian multi-object tracking by adding a lightweight identity-repair backend to a YOLOv8+SORT baseline, achieving IDF1 improvement from 82.25 to 84.93 on the PBVS Thermal benchmark while preserving MOTA.
Thermal pedestrian MOT remains challenging because weak appearance cues and frequent detection interruptions cause severe trajectory fragmentation. We study whether lightweight post-processing can recover identity continuity without relying on heavy re-identification models or complex online association. Starting from a YOLOv8 and SORT baseline, we add a modular identity-repair backend consisting of online short-gap remapping and offline tracklet relinking based on temporal, spatial, motion, and border cues. Controlled ablations on a fixed validation split and evaluation on the official PBVS Thermal Pedestrian MOT benchmark show that the main identity gains arise from conservative relinking, improving IDF1 from 82.25 to 84.93 while preserving MOTA, whereas many heuristic thresholds remain stable across broad operating ranges. These results suggest that, in low-information thermal imagery, robust identity recovery can be achieved more effectively through high-precision trajectory relinking than through increasing tracker complexity. These results provide a controlled analysis of identity recovery in thermal video, showing that scene-level spatial-temporal consistency plays a dominant role in identity continuity compared to local frame-to-frame association.