scispace - formally typeset
O

Oscar Pizarro

Researcher at University of Sydney

Publications -  158
Citations -  6335

Oscar Pizarro is an academic researcher from University of Sydney. The author has contributed to research in topics: Computer science & Remotely operated underwater vehicle. The author has an hindex of 41, co-authored 145 publications receiving 5518 citations. Previous affiliations of Oscar Pizarro include University of Michigan & Woods Hole Oceanographic Institution.

Papers
More filters
Proceedings ArticleDOI

Decoding, Calibration and Rectification for Lenselet-Based Plenoptic Cameras

TL;DR: This work derives a novel physically based 4D intrinsic matrix relating each recorded pixel to its corresponding ray in 3D space as part of a decoding, calibration and rectification procedure for lenselet-based plenoptic cameras appropriate for a range of computer vision applications.
Journal ArticleDOI

BioTIME: A database of biodiversity time series for the Anthropocene

Maria Dornelas, +286 more
TL;DR: The BioTIME database contains raw data on species identities and abundances in ecological assemblages through time to enable users to calculate temporal trends in biodiversity within and amongst assemblage using a broad range of metrics.
Journal IssueDOI

Generation and visualization of large-scale three-dimensional reconstructions from underwater robotic surveys

TL;DR: A robust, automated system for large-scale three-dimensional reconstruction and visualization that takes stereo imagery from an autonomous underwater vehicle (AUV) and SLAM-based vehicle poses to deliver detailed 3D models of the seafloor in the form of textured polygonal meshes is presented.
Journal ArticleDOI

Efficient View-Based SLAM Using Visual Loop Closures

TL;DR: This paper presents a simultaneous localization and mapping algorithm suitable for large-scale visual navigation based on the viewpoint augmented navigation (VAN) framework using an extended information filter.
Journal ArticleDOI

Visually Augmented Navigation for Autonomous Underwater Vehicles

TL;DR: The multisensor VAN framework is outlined and demonstrated to have compelling advantages over a purely vision-only approach by improving the robustness of low-overlap underwater image registration; setting the free gauge scale; and allowing for a disconnected camera-constraint topology.