Enhancing Egocentric Object Detection in Static Environments using Graph-based Spatial Anomaly Detection and Correction
This work addresses reliability issues in object detection for static environments, offering an incremental improvement over existing methods.
The paper tackled inconsistent object detection in static environments by proposing a graph-based post-processing pipeline that models spatial relationships to correct detection anomalies, resulting in mAP@50 gains of up to 4%.
In many real-world applications involving static environments, the spatial layout of objects remains consistent across instances. However, state-of-the-art object detection models often fail to leverage this spatial prior, resulting in inconsistent predictions, missed detections, or misclassifications, particularly in cluttered or occluded scenes. In this work, we propose a graph-based post-processing pipeline that explicitly models the spatial relationships between objects to correct detection anomalies in egocentric frames. Using a graph neural network (GNN) trained on manually annotated data, our model identifies invalid object class labels and predicts corrected class labels based on their neighbourhood context. We evaluate our approach both as a standalone anomaly detection and correction framework and as a post-processing module for standard object detectors such as YOLOv7 and RT-DETR. Experiments demonstrate that incorporating this spatial reasoning significantly improves detection performance, with mAP@50 gains of up to 4%. This method highlights the potential of leveraging the environment's spatial structure to improve reliability in object detection systems.