Online method improves real-time scene change detection speed and accuracy
O-SCD++: Replay-Free Online Scene Change Detection via Recursive Evidence Fusion
Computer Vision and Pattern Recognition
Summary
Detecting changes in a scene while being there in real time is tricky because you can't look ahead or store all past views. The authors improve a previous method by making it faster and more accurate without needing to replay old images. They represent the scene using a special 3D map and update it quickly with each new observation. This means robots or devices can detect changes more accurately and twice as fast, even when moving around freely.
What this means in practice
- •For robotics developers: Enable robots to detect environmental changes accurately and quickly in real time while exploring or monitoring.
- •For industrial inspection teams: Improve on-site detection of structural or environment changes during routine inspections without needing to revisit past data.
Authors
Chamuditha Jayanga Galappaththige, Jason Lai, Lloyd Windrim, Timothy Patten, Donald G. Dansereau, Niko Suenderhauf, Dimity Miller
Abstract
Online scene change detection requires an agent to detect what has changed in a previously mapped environment while it is still on site, observing from unconstrained viewpoints and without access to future observations. This causal setting is strictly harder than its offline counterpart, and online methods have consistently trailed offline accuracy. O-SCD closed that gap by treating change as a persistent property of a 3D Gaussian splatting map of the reference scene, surpassing the strongest offline methods in change detection accuracy while operating at over 10 frames per second. O-SCD optimizes a change field over the Gaussians of the reference map, refitting it to all past cue maps at every frame, a step that consumes more than half of the per-frame budget and forces accuracy to be traded against speed. We present a replay-free formulation that eliminates this trade-off. Because the reference map stays fixed, rendering the change field is a linear operation. Each new observation can therefore be carried onto the map's Gaussians directly, by a single backward pass of the renderer, which reduces multi-view fusion to an exact two-scalar recursion per Gaussian. Past observations are never stored or revisited. The self-supervised objective that O-SCD minimizes by descent also determines the decision threshold exactly, by sorting, yielding a label-free per-frame cutoff whose margin provides a selective-prediction signal. On PASLCD, our method improves mean intersection over union from 0.489 to 0.575 and throughput from 11.8 to 25.6 frames per second, even exceeding O-SCD's offline result while remaining strictly causal.