Keypoints of interest based on spatio-temporal feature and MRF for cloud recognition system

Takahiro Suzuki, Takeshi Ikenaga

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Keypoint extraction has lately attracted attention in computer vision. Particularly, Scale-Invariant Feature Transform (SIFT) is one of them and invariant for scale, rotation and illumination change. In addition, the recent advance of machine learning becomes possible to recognize a lot of objects by learning large amount of keypoints. Recently, cloud system starts to be utilized to maintain large-scale database which includes learning keypoint. Some network devices have to access these systems and match keypoints. Kepoint extraction algorithm utilizes only spatial information. Thus, many unnecessary keypoints for recognition are detected. If only Keypoints of Interest (KOI) are extracted from input images, it achieves reduction of descriptor data and high-precision recognition. This paper proposes the keypoint selection algorithm from many keypoints including unnecessary ones based on spatio-temporal feature and Markov Random Field (MRF). This algorithm calculats weight on each keypoint using 3 kinds of features (intensity gradient, optical flow and previous state) and reduces noise by comparing with states of surrounding keypoints. The state of keypoints is connected by using the distance of keypoints. Evaluation results show that the 90% reduction of keypoints comparing conventional keypoint extraction by adding small computational complexity.

Original languageEnglish
Title of host publication2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013
DOIs
Publication statusPublished - 2013
Event2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013 - Kaohsiung
Duration: 2013 Oct 292013 Nov 1

Other

Other2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013
CityKaohsiung
Period13/10/2913/11/1

Fingerprint

Optical flows
Computer vision
Learning systems
Computational complexity
Lighting
Mathematical transformations

ASJC Scopus subject areas

  • Information Systems
  • Signal Processing

Cite this

Suzuki, T., & Ikenaga, T. (2013). Keypoints of interest based on spatio-temporal feature and MRF for cloud recognition system. In 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013 [6694141] https://doi.org/10.1109/APSIPA.2013.6694141

Keypoints of interest based on spatio-temporal feature and MRF for cloud recognition system. / Suzuki, Takahiro; Ikenaga, Takeshi.

2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013. 2013. 6694141.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Suzuki, T & Ikenaga, T 2013, Keypoints of interest based on spatio-temporal feature and MRF for cloud recognition system. in 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013., 6694141, 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013, Kaohsiung, 13/10/29. https://doi.org/10.1109/APSIPA.2013.6694141
Suzuki T, Ikenaga T. Keypoints of interest based on spatio-temporal feature and MRF for cloud recognition system. In 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013. 2013. 6694141 https://doi.org/10.1109/APSIPA.2013.6694141
Suzuki, Takahiro ; Ikenaga, Takeshi. / Keypoints of interest based on spatio-temporal feature and MRF for cloud recognition system. 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013. 2013.
@inproceedings{ae873406ad524aabaa0901cde2046776,
title = "Keypoints of interest based on spatio-temporal feature and MRF for cloud recognition system",
abstract = "Keypoint extraction has lately attracted attention in computer vision. Particularly, Scale-Invariant Feature Transform (SIFT) is one of them and invariant for scale, rotation and illumination change. In addition, the recent advance of machine learning becomes possible to recognize a lot of objects by learning large amount of keypoints. Recently, cloud system starts to be utilized to maintain large-scale database which includes learning keypoint. Some network devices have to access these systems and match keypoints. Kepoint extraction algorithm utilizes only spatial information. Thus, many unnecessary keypoints for recognition are detected. If only Keypoints of Interest (KOI) are extracted from input images, it achieves reduction of descriptor data and high-precision recognition. This paper proposes the keypoint selection algorithm from many keypoints including unnecessary ones based on spatio-temporal feature and Markov Random Field (MRF). This algorithm calculats weight on each keypoint using 3 kinds of features (intensity gradient, optical flow and previous state) and reduces noise by comparing with states of surrounding keypoints. The state of keypoints is connected by using the distance of keypoints. Evaluation results show that the 90{\%} reduction of keypoints comparing conventional keypoint extraction by adding small computational complexity.",
author = "Takahiro Suzuki and Takeshi Ikenaga",
year = "2013",
doi = "10.1109/APSIPA.2013.6694141",
language = "English",
isbn = "9789869000604",
booktitle = "2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013",

}

TY - GEN

T1 - Keypoints of interest based on spatio-temporal feature and MRF for cloud recognition system

AU - Suzuki, Takahiro

AU - Ikenaga, Takeshi

PY - 2013

Y1 - 2013

N2 - Keypoint extraction has lately attracted attention in computer vision. Particularly, Scale-Invariant Feature Transform (SIFT) is one of them and invariant for scale, rotation and illumination change. In addition, the recent advance of machine learning becomes possible to recognize a lot of objects by learning large amount of keypoints. Recently, cloud system starts to be utilized to maintain large-scale database which includes learning keypoint. Some network devices have to access these systems and match keypoints. Kepoint extraction algorithm utilizes only spatial information. Thus, many unnecessary keypoints for recognition are detected. If only Keypoints of Interest (KOI) are extracted from input images, it achieves reduction of descriptor data and high-precision recognition. This paper proposes the keypoint selection algorithm from many keypoints including unnecessary ones based on spatio-temporal feature and Markov Random Field (MRF). This algorithm calculats weight on each keypoint using 3 kinds of features (intensity gradient, optical flow and previous state) and reduces noise by comparing with states of surrounding keypoints. The state of keypoints is connected by using the distance of keypoints. Evaluation results show that the 90% reduction of keypoints comparing conventional keypoint extraction by adding small computational complexity.

AB - Keypoint extraction has lately attracted attention in computer vision. Particularly, Scale-Invariant Feature Transform (SIFT) is one of them and invariant for scale, rotation and illumination change. In addition, the recent advance of machine learning becomes possible to recognize a lot of objects by learning large amount of keypoints. Recently, cloud system starts to be utilized to maintain large-scale database which includes learning keypoint. Some network devices have to access these systems and match keypoints. Kepoint extraction algorithm utilizes only spatial information. Thus, many unnecessary keypoints for recognition are detected. If only Keypoints of Interest (KOI) are extracted from input images, it achieves reduction of descriptor data and high-precision recognition. This paper proposes the keypoint selection algorithm from many keypoints including unnecessary ones based on spatio-temporal feature and Markov Random Field (MRF). This algorithm calculats weight on each keypoint using 3 kinds of features (intensity gradient, optical flow and previous state) and reduces noise by comparing with states of surrounding keypoints. The state of keypoints is connected by using the distance of keypoints. Evaluation results show that the 90% reduction of keypoints comparing conventional keypoint extraction by adding small computational complexity.

UR - http://www.scopus.com/inward/record.url?scp=84893316967&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893316967&partnerID=8YFLogxK

U2 - 10.1109/APSIPA.2013.6694141

DO - 10.1109/APSIPA.2013.6694141

M3 - Conference contribution

AN - SCOPUS:84893316967

SN - 9789869000604

BT - 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013

ER -