Monocular SLAM Supported Object Recognition

By Sudeep Pillai, John J. Leonard. 2015

140 citations recorded by the source corpus.

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.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

The limits and potentials of deep learning for robotics (2018, neutral): “As an extension of reasoning over individual objects, inference over the geometry of the whole scene is important for robotic vision, and closely related to the problems of object-based mapping or object-based SLAM [19], [86], [98], [114].”
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016, neutral): “felt [206] label different rooms, while Pillai and Leonard [201] segment several known objects in the map.”
Fusion++: Volumetric Object-Level SLAM (2018, methodology): “In RGB-only SLAM for object detection, Pillai and Leonard [26] use ORB-SLAM [21] to assist object recognition.”
Probabilistic data association for semantic SLAM (2017, background): “Many other approaches [14]–[19] extract both metric and semantic information but typically the two processes are carried out separately and the results are merged afterwards.”
VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem (2017, background): “This usually takes the form of detecting the scale objects in the scene (Castle, Klein, and Murray 2010) (Pillai and Leonard 2015) (Salas-Moreno et al.”
Meaningful maps with object-oriented semantic mapping (2016, methodology): “Pillai and Leonard [7] used a monocular SLAM system to boost the performance of object recognition”
CosyPose: Consistent multi-view multi-object 6D pose estimation (2020, background): “In addition, [31,32] do not consider full 6D pose of objects, and [20,33] only consider scenes with a single instance of each object.”