Efficient multi-view object recognition and full pose estimation

By Alvaro Collet, Siddhartha S. Srinivasa. 2010

84 citations recorded by the source corpus.

We present an approach for efficiently recognizing all objects in a scene and estimating their full pose from multiple views. Our approach builds upon a state of the art single-view algorithm which recognizes and registers learned metric 3D models using local descriptors. We extend to multiple views using a novel multi-step optimization that processes each view individually and feeds consistent hypotheses back to the algorithm for global refinement. We demonstrate that our method produces results comparable to the theoretical optimum, a full multi-view generalized camera approach, while avoiding its combinatorial time complexity. We provide experimental results demonstrating pose accuracy, speed, and robustness to model error using a three-camera rig, as well as a physical implementation of the pose output being used by an autonomous robot executing grasps in highly cluttered scenes.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

Domain randomization for transferring deep neural networks from simulation to the real world (2017, background): “Most successful approaches rely on using multiple camera frames [6] or depth information [44].”
Pairwise Decomposition of Image Sequences for Active Multi-view Recognition (2016, background): “If multiple views are available at testing, images can be combined and treated as a single, larger image [31], an approach which can also be addressed in two stages, by processing the individual images ﬁrst to reduce the search space [5].”
Monocular SLAM Supported Object Recognition (2015, background): “Multi-view Object Detection While classical object detection methods focus on single-view-based recognition performance, some of these methods have been extended to the multi-view case [11, 32], by aggregating object evidence across disparate views.”
The MOPED framework: Object recognition and pose estimation for manipulation (2011, background): “Keywords Object recognition, pose estimation, scene complexity, efficiency analysis, scalability analysis, architecture optimization, robotic manipulation, personal robotics”
CosyPose: Consistent multi-view multi-object 6D pose estimation (2020, methodology): “The object pose estimation problem [15,16] has been approached either by estimating the pose from 2D-3D correspondences using local invariant features [3,13], or directly by estimating the object pose using template-matching [14].”