The MOPED framework: Object recognition and pose estimation for manipulation

Abstract

We present MOPED, a framework for Multiple Object Pose Es-timation and Detection that seamlessly integrates single-image and multi-image object recognition and pose estimation in one optimized, robust, and scalable framework. We address two main challenges in computer vision for robotics: robust perfor-mance in complex scenes, and low latency for real-time opera-tion. We achieve robust performance with Iterative Clustering-Estimation (ICE), a novel algorithm that iteratively combines feature clustering with robust pose estimation. Feature cluster-ing quickly partitions the scene and produces object hypotheses. The hypotheses are used to further refine the feature clusters, and the two steps iterate until convergence. ICE is easy to parallelize, and easily integrates single- and multi-camera ob-ject recognition and pose estimation. We also introduce a novel object hypothesis scoring function based on M-estimator the-ory, and a novel pose clustering algorithm that robustly handles recognition outliers. We achieve scalability and low latency with an improved fea-ture matching algorithm for large databases, a GPU/CPU hy-brid architecture that exploits parallelism at all levels, and an optimized resource scheduler. We provide extensive experimen-tal results demonstrating state-of-the-art performance in terms of recognition, scalability, and latency in real-world robotic ap-plications. 1