View-Invariant Loop Closure with Oriented Semantic Landmarks

Recent work on semantic simultaneous localization and mapping (SLAM) have shown the utility of natural objects as landmarks for improving localization accuracy and robustness. In this paper we present a monocular semantic SLAM system that uses object identity and inter-object geometry for view-invariant loop detection and drift correction. Our system's ability to recognize an area of the scene even under large changes in viewing direction allows it to surpass the mapping accuracy of ORB-SLAM, which uses only local appearance-based features that are not robust to large viewpoint changes. Experiments on real indoor scenes show that our method achieves mean drift reduction of 70% when compared directly to ORB-SLAM. Additionally, we propose a method for object orientation estimation, where we leverage the tracked pose of a moving camera under the SLAM setting to overcome ambiguities caused by object symmetry. This allows our SLAM system to produce geometrically detailed semantic maps with object orientation, translation, and scale.

Authors

• Jimmy Li 0001
• Karim Koreitem
• David Meger
• Gregory Dudek

Keywords

• Cameras
• Simultaneous localization and mapping
• Semantics
• Trajectory
• Layout
• Robustness
• Estimation
• Loop Closure
• Semantic Landmarks
• Large Changes
• Local Features
• Object-oriented
• Semantic Map
• Orientation Estimation
• Viewpoint Changes
• Loop Detection
• Degrees Of Freedom
• Reference Frame
• Object Detection
• Bounding Box
• Cell Phone
• Nonlinear Programming
• Viewing Angle
• Mirror Symmetry
• Mapping System
• Camera Pose
• Loop Corrections
• Cylindrical Objects
• Object Pose
• Object Matching
• System A
• Flipped Images
• Similar Viewpoints
• Camera Motion
• Similarity Transformation