Lifelong Change Detection: Continuous Domain Adaptation for Small Object Change Detection in Every Robot Navigation
This addresses the need for automated change detection in robot navigation without costly manual labeling, though it appears incremental as it builds on existing self-supervised ideas.
The paper tackles the problem of ground-view small object change detection in robotics without manual annotations by introducing a fully self-supervised approach that reuses detected changes as priors for future tasks, achieving verification in a challenging application scenario.
The recently emerging research area in robotics, ground view change detection, suffers from its ill-posed-ness because of visual uncertainty combined with complex nonlinear perspective projection. To regularize the ill-posed-ness, the commonly applied supervised learning methods (e.g., CSCD-Net) rely on manually annotated high-quality object-class-specific priors. In this work, we consider general application domains where no manual annotation is available and present a fully self-supervised approach. The present approach adopts the powerful and versatile idea that object changes detected during everyday robot navigation can be reused as additional priors to improve future change detection tasks. Furthermore, a robustified framework is implemented and verified experimentally in a new challenging practical application scenario: ground-view small object change detection.