Bingham procrustean alignment for object detection in clutter

A new system for object detection in cluttered RGB-D images is presented. Our main contribution is a new method called Bingham Procrustean Alignment (BPA) to align models with the scene. BPA uses point correspondences between oriented features to derive a probability distribution over possible model poses. The orientation component of this distribution, conditioned on the position, is shown to be a Bingham distribution. This result also applies to the classic problem of least-squares alignment of point sets, when point features are orientation-less, and gives a principled, probabilistic way to measure pose uncertainty in the rigid alignment problem. Our detection system leverages BPA to achieve more reliable object detections in clutter.

• Publication year

  2013

• Venue

  2013 IEEE/RSJ International Conference on Intelligent Robots and Systems

• Publication date

  2013-04-27

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1109/IROS.2013.6696658arXiv 1304.7399
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A Global Hypotheses Verification Method for 3D Object Recognition

  2012influential reference
• A textured object recognition pipeline for color and depth image data

  2012cited by this paper
• Monte Carlo Pose Estimation with Quaternion Kernels and the Bingham Distribution

  2011cited by this paper
• Unique Signatures of Histograms for Local Surface Description

  2010influential reference
• Fast Point Feature Histograms (FPFH) for 3D registration

  2009cited by this paper
• A Close-form Solution of Absolute Orientation Using Unit Quaternions

  2007cited by this paper
• Robust camera pose recovery using stochastic geometry

  2001cited by this paper
• Object recognition from local scale-invariant features

  1999cited by this paper
• A Method for Registration of 3-D Shapes

  1992cited by this paper
• Localizing Overlapping Parts by Searching the Interpretation Tree

  1987cited by this paper
• Generalizing the Hough transform to detect arbitrary shapes

  1981cited by this paper
• An Antipodally Symmetric Distribution on the Sphere

  1974cited by this paper

• GraspClutter6D: A Large-Scale Real-World Dataset for Robust Perception and Grasping in Cluttered Scenes

  2025cites this paper
• High Precision 6-DoF Grasp Detection in Cluttered Scenes Based on Network Optimization and Pose Propagation

  2024cites this paper
• Semi-supervised active learning hypothesis verification for improved geometric expression in three-dimensional object recognition

  2023cites this paper
• Bayesian iterative closest point for mobile robot localization

  2022cites this paper
• A Novel Distribution for Representation of 6D Pose Uncertainty

  2022cites this paper
• A training free technique for 3D object recognition using the concept of vibration, energy and frequency

  2021cites this paper
• Robotic Grasping With Multi-View Image Acquisition and Model-Based Pose Estimation

  2021cites this paper
• Are Current 3D Descriptors Ready for Real-time Object Recognition?

  2020cites this paper
• Efficient sampling from the Bingham distribution

  2020cites this paper
• Robotic Grasping Using Semantic Segmentation and Primitive Geometric Model Based 3D Pose Estimation

  2020cites this paper
• Object recognition based on convex hull alignment

  2020cites this paper
• Estimating Motion Uncertainty with Bayesian ICP

  2020cites this paper
• Towards automating construction tasks: Large‐scale object mapping, segmentation, and manipulation

  2020cites this paper
• A Survey on Training Free 3D Texture-less Object Recognition Techniques

  2020cites this paper
• Geometry-driven Deterministic Sampling for Nonlinear Bingham Filtering

  2019cites this paper
• Approach for improving efficiency of three-dimensional object recognition in light-field display

  2019cites this paper
• 3D Object Recognition in Cluttered Scenes With Robust Shape Description and Correspondence Selection

  2017cites this paper
• Deliberative Perception

  2017cites this paper
• Prediction of ICP pose uncertainties using Monte Carlo simulation with synthetic depth images

  2017cites this paper
• Visual Grasp Affordance Localization in Point Clouds Using Curved Contact Patches

  2017cites this paper
• Learning the state of the world: object-based world modeling for mobile manipulation robots

  2017cites this paper
• 3D compositional hierarchies for object categorization

  2017cites this paper
• Automated calculation of udder depth and rear leg angle in Holstein-Friesian cows using a multi-Kinect cow scanning system

  2017cites this paper
• Grasp Pose Detection in Point Clouds

  2017cites this paper
• Learning the state of the world: object-based world modeling for mobile manipulation robots

  2017cites this paper
• A multi-modal RGB-D object recognizer

  2016cites this paper
• Open world assistive grasping using laser selection

  2016cites this paper
• A Global Hypothesis Verification Framework for 3D Object Recognition in Clutter

  2016cites this paper
• Discriminatively-guided Deliberative Perception for Pose Estimation of Multiple 3D Object Instances

  2016cites this paper
• Real-time object segmentation for soccer robots based on depth images

  2016cites this paper
• Monte Carlo Registration and Its Application with Autonomous Robots

  2016cites this paper
• Grasp Pose Detection in Dense Clutter

  2016cites this paper
• Point cloud segmentation for mobile robot manipulation

  2016influential citation
• The axes of random infinitesimal rotations and the propagation of orientation uncertainty

  2015cites this paper
• Localizing antipodal grasps in point clouds

  2015cites this paper
• PERCH: Perception via search for multi-object recognition and localization

  2015cites this paper
• Shape Dependency of ICP Pose Uncertainties in the Context of Pose Estimation Systems

  2015cites this paper
• Towards perception driven robot-assisted task-oriented therapy

  2015cites this paper
• Robot In a Room: Toward Perfect Object Recognition in Closed Environments

  2015cites this paper
• Using Geometry to Detect Grasp Poses in 3D Point Clouds

  2015cites this paper
• Learning the State of the World : Object-based State Estimation for Mobile-Manipulation Robots

  2015cites this paper
• Using Geometry to Detect Grasps in 3D Point Clouds

  2015cites this paper
• Sliding Shapes for 3D Object Detection in Depth Images

  2014cites this paper
• Parallelized Two-Stage Object Detection in Cluttered RGB-D Scenes by

  2014cites this paper
• On the Automation of “ Ground Truth ” Annotation for RGB-D Object Instance Recognition Datasets

  2014cites this paper
• A new benchmark for pose estimation with ground truth from virtual reality

  2014cites this paper
• Bayesian Orientation Estimation and Local Surface Informativeness for Active Object Pose Estimation

  2014cites this paper
• Automation of “ground truth” annotation for multi-view RGB-D object instance recognition datasets

  2014cites this paper
• Living and Searching in the World: Object-Based State Estimation for Mobile Robots

  2014cites this paper
• Tracking the spin on a ping pong ball with the quaternion Bingham filter

  2014cites this paper
• Localizing Handle-Like Grasp Affordances in 3D Point Clouds

  2014cites this paper
• Unsupervised object individuation from RGB-D image sequences

  2014cites this paper
• Computer Vision – ECCV 2014

  2014cites this paper
• Localizing Grasp Affordances in 3-D Points Clouds Using Taubin Quadric Fitting

  2013cites this paper