Physical Relation Reasoning for 3-D Object Detection

3-D object detection is an important problem in many intelligent system applications. Based on powerful spatial information provided by point clouds, existing methods focus primarily on the intrinsic geometric properties of objects while neglecting the physical relationships and interactions among the objects. This may lead to physically unreasonable predictions, such as floating objects or object volume overlaps. In this article, we propose a novel 3-D object detection method from the perspective of physical relation reasoning. Specifically, we introduce two aspects of physical relations, including stability and volume exclusion. In addition, we introduce room layouts to assist in 3-D object detection and formulate two physical constraints on the basic of volume exclusion and stability to ensure that all objects conform to real-world physics constraints. We validate our proposed model on ScanNetV2 and SUN RGB-D datasets, and the results demonstrate the effectiveness.

Authors

• Jialu Qin
• Ping Wei

Keywords

• Stability analysis
• Three-dimensional displays
• Cognition
• Object detection
• Intelligent systems
• Point cloud compression
• Computer vision
• Computer architecture
• Detection algorithms
• Physical Reasons
• Point Cloud
• Bounding Box
• Autonomous Vehicles
• Physical Constraints
• Stability Mechanism
• Excluded Volume
• Point Cloud Data
• Object Detection Methods
• Scene Understanding
• Object Bounding Boxes
• Action Of Gravity
• Scene Graph
• Contact Surface
• Intersection Over Union
• Physical Mechanisms
• Red Box
• Center Of Box
• Objects In The Scene
• Stability Score
• Vertical Relationships
• Predicted Bounding Box
• Object Pairs