Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

University of Central Florida

Integrating Close-Range 3D Computer Vision

University of Central Florida via YouTube

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore a comprehensive guest presentation by Olaf Hellwich on integrating close-range 3D computer vision with synthetic aperture radar satellite remote sensing. Delve into topics such as medical image processing, 3D reconstruction techniques, semantic analysis of point clouds, and SAR data processing. Learn about advanced concepts like compressive sampling, sparse signal representation, and multibaseline SAR acquisition. Gain insights into the TUB Computer Vision & Remote Sensing Research Group's projects and discover potential future research directions in ubiquitous 3D reconstructions.

Syllabus

Integrating Close-Range 3D Computer Vision and Synthetic Aperture Radar Satellite Remote Sensing
TUB Computer Vision & Remote Sensing Research Group
Medical Image Processing Projects
3D-Reconstruction Tool Chain
Discovering How Images Cover Object Graph of image triplets • Descriptor variance similarity to identify loop
OpenOF • Framework for sparse non-inear least squares optimization on a GPU
Image Measurements and knowledge: Camera Orientation Relative to Rectangle
Semantic Analysis • Various disciplines require semantic analysis of point clouds
Simplification - MDL Implies Trade-Off and fitting the measurements? . MDL principle: Transmitter wants to encode the information
Point Cloud Data Reduction Using MDL Principle
Segmentation into Low-Curvature and High-Curvature Segments
Voronoi-Based Extraction of a Feature Skeleton 11
Noise Influence on Point Cloud Segmentation
Performance Comparison of Point Cloud Segmentation Algorithms
Synthetic Aperture Radar (SAR) Remote Sensing
SAR Raw Data Processing Matched Filtering
Processing of SAR Data
Differential Interferometric SAR Phase Difference = f(Movement)
Compressive Sampling! Sparse Signal Representation Signal f can be transformed to a domain where it is sparse using an orthonormal basis eg a wavelet transform
Sparsity: Images in Wavelet Domain
Compressive Sampling II
Multibaseline SAR Acquisition
Proposal for Future Research: Use of Ubiquitous 3D Reconstructions

Taught by

UCF CRCV

Reviews

Start your review of Integrating Close-Range 3D Computer Vision

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.