|
Accession Number
|
ADA567167
|
|
Title
|
Multi-Frame Object Detection.
|
|
Publication Date
|
Sep 2012
|
|
Media Count
|
45p
|
|
Personal Author
|
M. J. Laielli
|
|
Abstract
|
This thesis describes an object detection system that extracts and combines appearance information over multiple consecutive video frames, inherently gaining and analyzing information related to motion. Objects that exhibit characteristic motion over the course of multiple frames are able to be detected at smaller scales than is achievable using a single-frame detector. Our method builds on the detection work of Viola and Jones, with our extension being the added ability to combine information from multiple frames. Our implementation detects an object in synthetic images at very small scales, down to 3x3 pixels, and has a low false-alarm rate.
|
|
Keywords
|
Appearance information
Automation
Boosting
C programming language
Cascades
Classification
Computer programs
Computer vision
Consecutive video frames
False alarms
Feature extraction
Full-motion video
Haar features
Image sequences
Integral images
Intensity
Learning machines
Motion
Motion information
Motion pictures
Multi-frame detection
Multiple consecutive frames
Multiple-frame object detection
Negative images
Opencv computer program
Pixels
Positive images
Raw pixel intensities
Small scales
Target detection
Theses
Training
Video frames
Video images
Visual object detection
|
|
|
Source Agency
|
Non Paid ADAS
|
|
NTIS Subject Category
|
62 - Computers, Control & Information Theory
82B - Photographic Techniques & Equipment
63F - Optical Detection
63 - Detection & Countermeasures
|
|
Corporate Author
|
Naval Postgraduate School, Monterey, CA. Dept. of Informational Sciences.
|
|
Document Type
|
Thesis
|
|
Title Note
|
Master's thesis.
|
|
NTIS Issue Number
|
1308
|
|
Contract Number
|
N/A
|
