Local feature-based multi-object recognition scheme for surveillance

Daehoon Kim, Seungmin Rho, Een Jun Hwang

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

In this paper, we propose an efficient multi-object recognition scheme for surveillance based on interest points of objects and their feature descriptors. In this scheme, we first define a set of object types of interest and collect their sample images. For each sample image, we detect interest points and construct their feature descriptors using SURF. Next, we perform a statistical analysis of the local features to select representative points among them. Intuitively, the representative points of an object are the interest points that best characterize the object. Finally, we calculate thresholds of each object for object recognition. User query is processed in a similar way. A given query images local feature descriptors are extracted and then compared with the representative points of objects in the database. Especially, to reduce the number of comparisons required, we propose a method for merging descriptors of similar representative points into a single descriptor. This descriptor is different from typical SURF descriptor in that each element represents not a single value but a range. By using this merged descriptor, we can calculate the similarity between input image descriptor and multiple descriptors in database efficiently. In addition, since our scheme treats all the objects independently, it can recognize multiple objects simultaneously.

Original languageEnglish
Pages (from-to)1373-1380
Number of pages8
JournalEngineering Applications of Artificial Intelligence
Volume25
Issue number7
DOIs
Publication statusPublished - 2012 Oct 1

Fingerprint

Object recognition
Merging
Statistical methods

Keywords

  • Feature descriptor
  • Local feature
  • Object recognition
  • SURF
  • Surveillance

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Local feature-based multi-object recognition scheme for surveillance. / Kim, Daehoon; Rho, Seungmin; Hwang, Een Jun.

In: Engineering Applications of Artificial Intelligence, Vol. 25, No. 7, 01.10.2012, p. 1373-1380.

Research output: Contribution to journalArticle

@article{487a40880eef448bb826bcd97af1b9c8,
title = "Local feature-based multi-object recognition scheme for surveillance",
abstract = "In this paper, we propose an efficient multi-object recognition scheme for surveillance based on interest points of objects and their feature descriptors. In this scheme, we first define a set of object types of interest and collect their sample images. For each sample image, we detect interest points and construct their feature descriptors using SURF. Next, we perform a statistical analysis of the local features to select representative points among them. Intuitively, the representative points of an object are the interest points that best characterize the object. Finally, we calculate thresholds of each object for object recognition. User query is processed in a similar way. A given query images local feature descriptors are extracted and then compared with the representative points of objects in the database. Especially, to reduce the number of comparisons required, we propose a method for merging descriptors of similar representative points into a single descriptor. This descriptor is different from typical SURF descriptor in that each element represents not a single value but a range. By using this merged descriptor, we can calculate the similarity between input image descriptor and multiple descriptors in database efficiently. In addition, since our scheme treats all the objects independently, it can recognize multiple objects simultaneously.",
keywords = "Feature descriptor, Local feature, Object recognition, SURF, Surveillance",
author = "Daehoon Kim and Seungmin Rho and Hwang, {Een Jun}",
year = "2012",
month = "10",
day = "1",
doi = "10.1016/j.engappai.2012.03.005",
language = "English",
volume = "25",
pages = "1373--1380",
journal = "Engineering Applications of Artificial Intelligence",
issn = "0952-1976",
publisher = "Elsevier Limited",
number = "7",

}

TY - JOUR

T1 - Local feature-based multi-object recognition scheme for surveillance

AU - Kim, Daehoon

AU - Rho, Seungmin

AU - Hwang, Een Jun

PY - 2012/10/1

Y1 - 2012/10/1

N2 - In this paper, we propose an efficient multi-object recognition scheme for surveillance based on interest points of objects and their feature descriptors. In this scheme, we first define a set of object types of interest and collect their sample images. For each sample image, we detect interest points and construct their feature descriptors using SURF. Next, we perform a statistical analysis of the local features to select representative points among them. Intuitively, the representative points of an object are the interest points that best characterize the object. Finally, we calculate thresholds of each object for object recognition. User query is processed in a similar way. A given query images local feature descriptors are extracted and then compared with the representative points of objects in the database. Especially, to reduce the number of comparisons required, we propose a method for merging descriptors of similar representative points into a single descriptor. This descriptor is different from typical SURF descriptor in that each element represents not a single value but a range. By using this merged descriptor, we can calculate the similarity between input image descriptor and multiple descriptors in database efficiently. In addition, since our scheme treats all the objects independently, it can recognize multiple objects simultaneously.

AB - In this paper, we propose an efficient multi-object recognition scheme for surveillance based on interest points of objects and their feature descriptors. In this scheme, we first define a set of object types of interest and collect their sample images. For each sample image, we detect interest points and construct their feature descriptors using SURF. Next, we perform a statistical analysis of the local features to select representative points among them. Intuitively, the representative points of an object are the interest points that best characterize the object. Finally, we calculate thresholds of each object for object recognition. User query is processed in a similar way. A given query images local feature descriptors are extracted and then compared with the representative points of objects in the database. Especially, to reduce the number of comparisons required, we propose a method for merging descriptors of similar representative points into a single descriptor. This descriptor is different from typical SURF descriptor in that each element represents not a single value but a range. By using this merged descriptor, we can calculate the similarity between input image descriptor and multiple descriptors in database efficiently. In addition, since our scheme treats all the objects independently, it can recognize multiple objects simultaneously.

KW - Feature descriptor

KW - Local feature

KW - Object recognition

KW - SURF

KW - Surveillance

UR - http://www.scopus.com/inward/record.url?scp=84866742102&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866742102&partnerID=8YFLogxK

U2 - 10.1016/j.engappai.2012.03.005

DO - 10.1016/j.engappai.2012.03.005

M3 - Article

AN - SCOPUS:84866742102

VL - 25

SP - 1373

EP - 1380

JO - Engineering Applications of Artificial Intelligence

JF - Engineering Applications of Artificial Intelligence

SN - 0952-1976

IS - 7

ER -