Published on Wed Mar 31 2021

Online Learning of a Probabilistic and Adaptive Scene Representation

Zike Yan, Xin Wang, Hongbin Zha
0
0
0
Abstract

Constructing and maintaining a consistent scene model on-the-fly is the core task for online spatial perception, interpretation, and action. In this paper, we represent the scene with a Bayesian nonparametric mixture model, seamlessly describing per-point occupancy status with a continuous probability density function. Instead of following the conventional data fusion paradigm, we address the problem of online learning the process how sequential point cloud data are generated from the scene geometry. An incremental and parallel inference is performed to update the parameter space in real-time. We experimentally show that the proposed representation achieves state-of-the-art accuracy with promising efficiency. The consistent probabilistic formulation assures a generative model that is adaptive to different sensor characteristics, and the model complexity can be dynamically adjusted on-the-fly according to different data scales.

Tue Sep 22 2020
Machine Learning
Data-Driven Distributed State Estimation and Behavior Modeling in Sensor Networks
tracking real-world objects often faces two key challenges. First, due to the limitation of individual sensors, state estimation needs to be solved in a collaborative manner. Second, the objects' movement behavior is unknown, and must be learned using sensor observations.
0
0
0
Fri Jul 06 2018
Computer Vision
Fast and Accurate Point Cloud Registration using Trees of Gaussian Mixtures
Point cloud registration sits at the core of many important and challenging 3D perception problems including autonomous navigation, SLAM, object/scene recognition, and augmented reality. We present a new algorithm that is able to achieve state-of-the-art speed and accuracy through its use of a hierarchical Gaussian Mixture Model.
0
0
0
Mon Nov 09 2020
Computer Vision
Learning to Localize in New Environments from Synthetic Training Data
Most existing approaches for visual localization either need a detailed 3Dmodel of the environment or, in the case of learning-based methods, must be retrained for each new scene. We present an approach that can generalize to new scenes by applying specific changes to the model.
1
0
0
Sat Jul 17 2010
Machine Learning
A Machine Learning Approach to Recovery of Scene Geometry from Images
Recovering the 3D structure of the scene from images yields useful information for tasks such as shape and scene recognition, object detection, or motion planning and object grasping in robotics. In this thesis, we introduce a general machine learning approach called unsupervised CRF learning based on maximizing the conditional likelihood.
0
0
0
Wed Dec 04 2019
Machine Learning
Dynamic Hilbert Maps: Real-Time Occupancy Predictions in Changing Environment
This paper addresses the problem of learning instantaneous occupancy levels of dynamic environments and predicting future occupancy levels. We propose a method to capture the spatial uncertainty of moving objects and incorporate this information into a continuous occupancy map.
0
0
0
Fri Apr 27 2018
Artificial Intelligence
Persistent Monitoring of Stochastic Spatio-temporal Phenomena with a Small Team of Robots
This paper presents a solution for persistent monitoring of real-world phenomena using a small number of mobile robot sensors. Each robot samples a belief point from the GM and locally optimizes a set of informative regions by greedy optimizing entropy function.
0
0
0