Improving Place Recognition Using Dynamic Object Detection
This addresses the problem of place recognition for mobile agents in dynamic environments, with incremental improvements.
The paper tackles place recognition in dynamic environments by incorporating object detection preprocessing, resulting in improved recognition and reduced memory/storage requirements for mobile agents.
We present a novel approach to place recognition well-suited to environments with many dynamic objects--objects that may or may not be present in an agent's subsequent visits. By incorporating an object-detecting preprocessing step, our approach yields high-quality place representations that incorporate object information. Not only does this result in significantly improved place recognition in dynamic environments, it also significantly reduces memory/storage requirements, which may increase the effectiveness of mobile agents with limited resources.