Monocular SLAM Supported Object Recognition

TL;DR

This paper presents a monocular SLAM-aware object recognition system that leverages multi-view proposals and efficient encoding to improve recognition accuracy and speed using a single RGB camera.

Contribution

It introduces a novel SLAM-aware recognition approach that integrates multi-view object proposals with efficient feature encoding for real-time performance.

Findings

Achieves stronger recognition performance than classical frame-by-frame systems

Operates in near-constant time with scalable runtime performance

Demonstrates effectiveness on the UW RGB-D Dataset

Abstract

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.