Active Sensing Representations for Navigation and Visual Scene Analysis

Abstract

This project, kicked off in September of 2015, aimed at developing analytical and computational tools to infer optimal representations for decision and control actions based on visual data. Specifically, corresponding to (classes of) tasks, different representations can be designed. For localization tasks, EO imaging and inertial sensors can be used to develop a representation that is minimal-sufficient (an attributed point cloud) and invariant to changes of illumination and partial occlusion. The result is a posterior estimate of the sensor trajectory in SE(3) given all measurements up to the current time, marginalized with respect to all nuisance variability. Semantic understanding of the scene requires more sophisticated representations than point cloud.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 28, 2018
Accession Number
AD1064790

Entities

People

  • Stefano Soatto

Organizations

  • University of California, Los Angeles

Tags

Communities of Interest

  • Autonomy
  • Energy and Power Technologies
  • Sensors

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Neural Networks
  • Computer Vision
  • Computers
  • Data Association
  • Data Science
  • Decision Theory
  • Deep Learning
  • Detectors
  • Differential Equations
  • Image Processing
  • Image Recognition
  • Information Science
  • Information Theory
  • Invariance
  • Inverse Problems
  • Learning
  • Machine Learning
  • Navigation
  • Network Architecture
  • Neural Networks
  • Partial Differential Equations
  • Pattern Recognition
  • Point Clouds
  • Recognition
  • Robotics
  • Scientific Research
  • Statistical Decision Theory
  • Topology
  • Vascular System Injuries

Readers

  • Distributed Systems and Data Platform Development
  • Image Processing and Computer Vision.
  • Statistical inference.

Technology Areas

  • AI & ML