3D spatial relationships for improving object detection

This work demonstrates how 3D qualitative spatial relationships can be used to improve object detection by differentiating between true and false positive detections. Our method identifies the most likely subset of 3D detections using seven types of 3D relationships and adjusts detection confidence scores to improve the average precision. A model is learned using a structured support vector machine [1] from examples of 3D layouts of objects in offices and kitchens. We test our method on synthetic detections to determine how factors such as localization accuracy, number of detections and detection scores change the effectiveness of 3D spatial relationships for improving object detection rates. Finally, we describe a technique for generating 3D detections from 2D image-based object detections and demonstrate how our method improves the average precision of these 3D detections.

Authors

• Tristram Southey
• James J. Little

Keywords

• Robots
• Three-dimensional displays
• Layout
• Object Detection
• Improve Object Detection
• 3D Spatial Relationships
• False Positive
• Average Precision
• Positive Detection
• False Positive Detection
• 3D Detection
• True Detection
• Qualitative Relationship
• True Positive Detection
• Training Data
• True Positive
• Scoring Function
• Bounding Box
• Major Axis
• Detection In Images
• Simultaneous Detection
• Large Objects
• Camera Position
• Fiducial Markers
• Objects In The Scene
• Improvement In Precision
• Simultaneous Localization And Mapping
• Minimum Bounding Box
• Typical Objects
• Markov Random Field
• Conditional Random Field
• Vertical Alignment