An efficient Naive Bayes approach to category-level object detection

Kasim Terzic; J. M.H. Du Buf

doi:10.1109/ICIP.2014.7025332

An efficient Naive Bayes approach to category-level object detection

Kasim Terzic, J. M.H. Du Buf

School of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We present a fast Bayesian algorithm for category-level object detection in natural images. We modify the popular Naive Bayes Nearest Neighbour classification algorithm to make it suitable for evaluating multiple sub-regions in an image, and offer a fast, filtering-based alternative to the multi-scale sliding window approach. Our algorithm is example-based and requires no learning. Tests on standard datasets and robotic scenarios show competitive detection rates and real-time performance of our algorithm.

Original language	English
Title of host publication	2014 IEEE International Conference on Image Processing, ICIP 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1658-1662
Number of pages	5
ISBN (Electronic)	9781479957514
DOIs	https://doi.org/10.1109/ICIP.2014.7025332
Publication status	Published - 28 Jan 2014

Keywords

Computer vision
Nearest neighbour
Object detection
Real time systems
Robot vision

Access to Document

10.1109/ICIP.2014.7025332

Cite this

@inproceedings{6da759a246ff4496a5c68cc491fc7631,

title = "An efficient Naive Bayes approach to category-level object detection",

abstract = "We present a fast Bayesian algorithm for category-level object detection in natural images. We modify the popular Naive Bayes Nearest Neighbour classification algorithm to make it suitable for evaluating multiple sub-regions in an image, and offer a fast, filtering-based alternative to the multi-scale sliding window approach. Our algorithm is example-based and requires no learning. Tests on standard datasets and robotic scenarios show competitive detection rates and real-time performance of our algorithm.",

keywords = "Computer vision, Nearest neighbour, Object detection, Real time systems, Robot vision",

author = "Kasim Terzic and {Du Buf}, {J. M.H.}",

year = "2014",

month = jan,

day = "28",

doi = "10.1109/ICIP.2014.7025332",

language = "English",

pages = "1658--1662",

booktitle = "2014 IEEE International Conference on Image Processing, ICIP 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

}

TY - GEN

T1 - An efficient Naive Bayes approach to category-level object detection

AU - Terzic, Kasim

AU - Du Buf, J. M.H.

PY - 2014/1/28

Y1 - 2014/1/28

N2 - We present a fast Bayesian algorithm for category-level object detection in natural images. We modify the popular Naive Bayes Nearest Neighbour classification algorithm to make it suitable for evaluating multiple sub-regions in an image, and offer a fast, filtering-based alternative to the multi-scale sliding window approach. Our algorithm is example-based and requires no learning. Tests on standard datasets and robotic scenarios show competitive detection rates and real-time performance of our algorithm.

AB - We present a fast Bayesian algorithm for category-level object detection in natural images. We modify the popular Naive Bayes Nearest Neighbour classification algorithm to make it suitable for evaluating multiple sub-regions in an image, and offer a fast, filtering-based alternative to the multi-scale sliding window approach. Our algorithm is example-based and requires no learning. Tests on standard datasets and robotic scenarios show competitive detection rates and real-time performance of our algorithm.

KW - Computer vision

KW - Nearest neighbour

KW - Object detection

KW - Real time systems

KW - Robot vision

UR - http://www.scopus.com/inward/record.url?scp=84983094638&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2014.7025332

DO - 10.1109/ICIP.2014.7025332

M3 - Conference contribution

AN - SCOPUS:84983094638

SP - 1658

EP - 1662

BT - 2014 IEEE International Conference on Image Processing, ICIP 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

An efficient Naive Bayes approach to category-level object detection

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this