Vehicle Detection Using Partial Least Squares

Detecting vehicles in aerial images has a wide range of applications, from urban planning to visual surveillance. We describe a vehicle detector that improves upon previous approaches by incorporating a very large and rich set of image descriptors. A new feature set called Color Probability Maps is...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2011-06, Vol.33 (6), p.1250-1265
Main Authors: Kembhavi, A, Harwood, D, Davis, L S
Format: Article
Language:English
Subjects:
Algorithms
Applied sciences
Artificial Intelligence
Color
Colorimetry - methods
Computer science
control theory
systems
Detectors
Exact sciences and technology
Feature extraction
feature selection
Image color analysis
Image Enhancement - methods
Intelligence
Least squares method
Least-Squares Analysis
Motor Vehicles
partial least squares
Pattern analysis
Pattern Recognition, Automated - methods
Pattern recognition. Digital image processing. Computational geometry
Pixel
Principal component analysis
Statistics
Studies
Training
Urban planning
Vehicle detection
Vehicles
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Detecting vehicles in aerial images has a wide range of applications, from urban planning to visual surveillance. We describe a vehicle detector that improves upon previous approaches by incorporating a very large and rich set of image descriptors. A new feature set called Color Probability Maps is used to capture the color statistics of vehicles and their surroundings, along with the Histograms of Oriented Gradients feature and a simple yet powerful image descriptor that captures the structural characteristics of objects named Pairs of Pixels. The combination of these features leads to an extremely high-dimensional feature set (approximately 70,000 elements). Partial Least Squares is first used to project the data onto a much lower dimensional subspace. Then, a powerful feature selection analysis is employed to improve the performance while vastly reducing the number of features that must be calculated. We compare our system to previous approaches on two challenging data sets and show superior performance.
ISSN:0162-8828
1939-3539
2160-9292
DOI:10.1109/TPAMI.2010.182