Active Pose Refinement for Textureless Shiny Objects using the Structured Light Camera

6D pose estimation of textureless shiny objects has become an essential problem in many robotic applications. Many pose estimators require high-quality depth data, often measured by structured light cameras. However, when objects have shiny surfaces (e. g. , metal parts), these cameras fail to sense complete depths from a single viewpoint due to the specular reflection, resulting in a significant drop in the final pose accuracy. To mitigate this issue, we present a complete active vision framework for 6D object pose refinement and next-best-view prediction. Specifically, we first develop an optimization-based pose refinement module for the structured light camera. Our system then selects the next best camera viewpoint to collect depth measurements by minimizing the predicted uncertainty of the object pose. Compared to previous approaches, we additionally predict measurement uncertainties of future viewpoints by online rendering, which significantly improves the next-best-view prediction performance. We test our method on the real-world ROBI dataset. The results show that our pose refinement module outperforms the traditional ICP-based approach when given the same input depth data, and our next-best-view strategy can achieve high object pose accuracy with significantly fewer viewpoints than the heuristic-based policies.

Authors

• Jun Yang 0053
• Jian Yao
• Steven L. Waslander

Keywords

• Accuracy
• Uncertainty
• Robot vision systems
• Pose estimation
• Measurement uncertainty
• Metals
• Cameras
• Rendering (computer graphics)
• Reflection
• Intelligent robots
• Structured Illumination
• Pose Refinement
• Shiny Objects
• Structured Light Camera
• Real-world Datasets
• Depth Data
• Depth Measurements
• Specular Reflection
• Metal Parts
• Human Pose Estimation
• Object Pose
• Accurate Pose
• Shiny Surface
• Camera Viewpoint
• Light Source
• Point Cloud
• Depth Map
• 3D Point
• Signed Distance Function
• Iterative Closest Point
• Fisher Information
• Reflective Functioning
• Amount Of Light
• Iterative Closest Point Algorithm
• High Dynamic Range
• Sum Of Squared Differences
• Pixel Depth
• Light Projection