0
Your cart

Your cart is empty

Books > Social sciences > Education

Buy Now

Electronic Image Stabilization for Mobile Robotic Vision Systems (Paperback) Loot Price: R1,427
Discovery Miles 14 270
Electronic Image Stabilization for Mobile Robotic Vision Systems (Paperback): Michael John Smith

Electronic Image Stabilization for Mobile Robotic Vision Systems (Paperback)

Michael John Smith

 (sign in to rate)
Loot Price R1,427 Discovery Miles 14 270 | Repayment Terms: R134 pm x 12*

Bookmark and Share

Expected to ship within 10 - 15 working days

When a camera is affixed on a dynamic mobile robot, image stabilization is the first step towards more complex analysis on the video feed. This thesis presents a novel electronic image stabilization (EIS) algorithm for small inexpensive highly dynamic mobile robotic platforms with onboard camera systems. The algorithm combines optical flow motion parameter estimation with angular rate data provided by a strapdown inertial measurement unit (IMU). A discrete Kalman filter in feedforward configuration is used for optimal fusion of the two data sources. Performance evaluations are conducted by a simulated video truth model (capturing the effects of image translation, rotation, blurring, and moving objects), and live test data. Live data was collected from a camera and IMU affixed to the DAGSI Whegs mobile robotic platform as it navigated through a hallway. Template matching, feature detection, optical flow, and inertial measurement techniques are compared and analyzed to determine the most suitable algorithm for this specific type of image stabilization. Pyramidal Lucas- Kanade optical flow using Shi-Tomasi good features in combination with inertial measurement is the EIS algorithm found to be superior. In the presence of moving objects, fusion of inertial measurement reduces optical flow root-mean-squared(RMS) error in motion parameter estimates by 40%. No previous image stabilization algorithm to date directly fuses optical flow estimation with inertial measurement by way of Kalman filtering.

General

Imprint: Biblioscholar
Country of origin: United States
Release date: November 2012
First published: November 2012
Authors: Michael John Smith
Dimensions: 246 x 189 x 7mm (L x W x T)
Format: Paperback - Trade
Pages: 124
ISBN-13: 978-1-288-31354-9
Categories: Books > Social sciences > Education > General
LSN: 1-288-31354-3
Barcode: 9781288313549

Is the information for this product incomplete, wrong or inappropriate? Let us know about it.

Does this product have an incorrect or missing image? Send us a new image.

Is this product missing categories? Add more categories.

Review This Product

No reviews yet - be the first to create one!

Partners