Call Us 080-41656200 (Mon-Sat: 10AM-8PM)
Free Shipping above Rs. 1499
Cash On Delivery*

Improving the Efficiency of SfM and its Applications

 

Marketed By :  LAP LAMBERT Academic Publishing   Sold By :  Kamal Books International  
Delivery in :  10-12 Business Days

 

Check Your Delivery Options

 
Rs. 3,651

Availability: In stock

 
  • Product Description
 

Large scale reconstructions from community photo collections is rich in information that can interpreted as a sampling of the geometry and appearance of the underlying space. In this dissertation, we encode the visibility information between and among points and cameras as visibility probabilities. The conditional visibility probability of a set of points on a point (or a set of cameras on a camera) can be used to select points (or cameras) based on their dependence or independence. We use it to efficiently solve the problems of image localization and feature triangulation. Other than image localization and feature triangulation, bundle adjustment is a key component of the reconstruction pipeline and often its slowest and the most computational resource intensive. We also a present a hybrid implementation of sparse bundle adjustment on the GPU using CUDA, with the CPU working in parallel. The algorithm is decomposed into smaller steps, each of which is scheduled on the GPU or the CPU. We develop efficient kernels for the steps and make use of existing libraries for several steps. Our implementation outperforms the CPU implementation significantly, achieving a speedup of 30-40 times.

Product Specifications
SKU :COC65318
AuthorSiddharth Choudhary
LanguageEnglish
BindingPaperback
Number of Pages92
Publishing Year2013-03-13T00:00:00.000
ISBN9783659361746
Edition1 st
Book TypeComputer networking & communications
Country of ManufactureIndia
Product BrandLAP LAMBERT Academic Publishing
Product Packaging InfoBox
In The Box1 Piece
Product First Available On ClickOnCare.com2015-07-08 00:00:00