Robust on-line model-based object detection from range images

A mobile robot that accomplishes high level tasks needs to be able to classify the objects in the environment and to determine their location. In this paper, we address the problem of online object detection in 3D laser range data. The object classes are represented by 3D point-clouds that can be obtained from a set of range scans. Our method relies on the extraction of point features from range images that are computed from the point-clouds. Compared to techniques that directly operate on a full 3D representation of the environment, our approach requires less computation time while retaining the robustness of full 3D matching. Experiments demonstrate that the proposed approach is even able to deal with partially occluded scenes and to fulfill the runtime requirements of online applications.

Authors

• Bastian Steder
• Giorgio Grisetti
• Mark Van Loock
• Wolfram Burgard

Keywords

• Robustness
• Object detection
• Clouds
• Feature extraction
• Layout
• Mobile robots
• Data mining
• Service robots
• Simultaneous localization and mapping
• Intelligent robots
• Point Cloud
• Feature Points
• 3D Point Cloud
• Laser Ranging
• False Positive
• Image Resolution
• Feature Space
• Scoring Function
• Object Recognition
• Point Model
• 3D Scanning
• 3D Point
• Object Position
• Feature Matching
• Object Distance
• Valid Point
• Objects In The Scene
• Object Instances
• Scene Features
• Scene Point
• False Matches
• Object Pose
• Spherical Image
• Feature Pairs
• Descriptive Characteristics
• point clouds
• range images