Monocular SLAM Supported Object Recognition
This addresses the problem of robust object recognition in dynamic environments for robotics or AR applications, but it appears incremental as it builds on existing SLAM and recognition techniques.
The paper tackles object recognition by integrating monocular SLAM to improve performance over frame-by-frame methods, achieving strong recognition results on the UW RGB-D Dataset with scalable run-time.
In this work, we develop a monocular SLAM-aware object recognition system that is able to achieve considerably stronger recognition performance, as compared to classical object recognition systems that function on a frame-by-frame basis. By incorporating several key ideas including multi-view object proposals and efficient feature encoding methods, our proposed system is able to detect and robustly recognize objects in its environment using a single RGB camera in near-constant time. Through experiments, we illustrate the utility of using such a system to effectively detect and recognize objects, incorporating multiple object viewpoint detections into a unified prediction hypothesis. The performance of the proposed recognition system is evaluated on the UW RGB-D Dataset, showing strong recognition performance and scalable run-time performance compared to current state-of-the-art recognition systems.