Classification of corresponding points for 3D measurement using moving monocular camera attached with 6-axis sensor

Toshihiro Akamatsu; Fangyan Dong; Kaoru Hirota

Classification of corresponding points for 3D measurement using moving monocular camera attached with 6-axis sensor

Toshihiro Akamatsu, Fangyan Dong, Kaoru Hirota

Tokyo Institute of Technology

科研成果: 会议稿件 › 论文 › 同行评审

摘要

A classification method of corresponding points is proposed, which uses a moving monocular camera attached with a 6-axis sensor. It classifies corresponding points between two consecutive frames containing still/moving objects and chooses appropriate corresponding points for 3D measurement. Corresponding point classification experiment with original CG images shows that accuracy, precision, and recall are 0.94, 0.85, and 1.00, respectively. In addition, it is confirmed that erroneous correspondences are removed by outlier detection using Interquartile Range for proposed evaluation function calculated on each corresponding point. The proposed method is planning to be included in 3D measurement method with actual images containing still/moving objects and also to be applied to obstacles avoidance for vehicles or vision system for mobile robots.

源语言	英语
页	110-116
页数	7
出版状态	已出版 - 2014
已对外发布	是
活动	Joint International Conference of the 10th China-Japan International Workshop on Information Technology and Control Applications and the 6th International Symposium on Computational Intelligence and Industrial Applications, ITCA and ISCIIA 2014 - Changsha, 中国期限: 15 9月 2014 → 20 9月 2014

会议

会议	Joint International Conference of the 10th China-Japan International Workshop on Information Technology and Control Applications and the 6th International Symposium on Computational Intelligence and Industrial Applications, ITCA and ISCIIA 2014
国家/地区	中国
市	Changsha
时期	15/09/14 → 20/09/14

其它文件与链接

链接到 Scopus 的出版物

引用此

Akamatsu, T., Dong, F., & Hirota, K. (2014). Classification of corresponding points for 3D measurement using moving monocular camera attached with 6-axis sensor. 110-116. 论文发表于 Joint International Conference of the 10th China-Japan International Workshop on Information Technology and Control Applications and the 6th International Symposium on Computational Intelligence and Industrial Applications, ITCA and ISCIIA 2014, Changsha, 中国.

Akamatsu, Toshihiro ; Dong, Fangyan ; Hirota, Kaoru. / Classification of corresponding points for 3D measurement using moving monocular camera attached with 6-axis sensor. 论文发表于 Joint International Conference of the 10th China-Japan International Workshop on Information Technology and Control Applications and the 6th International Symposium on Computational Intelligence and Industrial Applications, ITCA and ISCIIA 2014, Changsha, 中国.7 页码

@conference{c11f31a98b814381a790dcc90ef7f03f,

title = "Classification of corresponding points for 3D measurement using moving monocular camera attached with 6-axis sensor",

abstract = "A classification method of corresponding points is proposed, which uses a moving monocular camera attached with a 6-axis sensor. It classifies corresponding points between two consecutive frames containing still/moving objects and chooses appropriate corresponding points for 3D measurement. Corresponding point classification experiment with original CG images shows that accuracy, precision, and recall are 0.94, 0.85, and 1.00, respectively. In addition, it is confirmed that erroneous correspondences are removed by outlier detection using Interquartile Range for proposed evaluation function calculated on each corresponding point. The proposed method is planning to be included in 3D measurement method with actual images containing still/moving objects and also to be applied to obstacles avoidance for vehicles or vision system for mobile robots.",

keywords = "3D measurement, 6-axis sensor, Corresponding points classification, Fundamental matrix estimation, Moving camera",

author = "Toshihiro Akamatsu and Fangyan Dong and Kaoru Hirota",

year = "2014",

language = "English",

pages = "110--116",

note = "Joint International Conference of the 10th China-Japan International Workshop on Information Technology and Control Applications and the 6th International Symposium on Computational Intelligence and Industrial Applications, ITCA and ISCIIA 2014 ; Conference date: 15-09-2014 Through 20-09-2014",

}

Akamatsu, T, Dong, F & Hirota, K 2014, 'Classification of corresponding points for 3D measurement using moving monocular camera attached with 6-axis sensor', 论文发表于 Joint International Conference of the 10th China-Japan International Workshop on Information Technology and Control Applications and the 6th International Symposium on Computational Intelligence and Industrial Applications, ITCA and ISCIIA 2014, Changsha, 中国, 15/09/14 - 20/09/14 页码 110-116.

Classification of corresponding points for 3D measurement using moving monocular camera attached with 6-axis sensor. / Akamatsu, Toshihiro; Dong, Fangyan; Hirota, Kaoru.
2014. 110-116 论文发表于 Joint International Conference of the 10th China-Japan International Workshop on Information Technology and Control Applications and the 6th International Symposium on Computational Intelligence and Industrial Applications, ITCA and ISCIIA 2014, Changsha, 中国.

科研成果: 会议稿件 › 论文 › 同行评审

TY - CONF

T1 - Classification of corresponding points for 3D measurement using moving monocular camera attached with 6-axis sensor

AU - Akamatsu, Toshihiro

AU - Dong, Fangyan

AU - Hirota, Kaoru

PY - 2014

Y1 - 2014

N2 - A classification method of corresponding points is proposed, which uses a moving monocular camera attached with a 6-axis sensor. It classifies corresponding points between two consecutive frames containing still/moving objects and chooses appropriate corresponding points for 3D measurement. Corresponding point classification experiment with original CG images shows that accuracy, precision, and recall are 0.94, 0.85, and 1.00, respectively. In addition, it is confirmed that erroneous correspondences are removed by outlier detection using Interquartile Range for proposed evaluation function calculated on each corresponding point. The proposed method is planning to be included in 3D measurement method with actual images containing still/moving objects and also to be applied to obstacles avoidance for vehicles or vision system for mobile robots.

AB - A classification method of corresponding points is proposed, which uses a moving monocular camera attached with a 6-axis sensor. It classifies corresponding points between two consecutive frames containing still/moving objects and chooses appropriate corresponding points for 3D measurement. Corresponding point classification experiment with original CG images shows that accuracy, precision, and recall are 0.94, 0.85, and 1.00, respectively. In addition, it is confirmed that erroneous correspondences are removed by outlier detection using Interquartile Range for proposed evaluation function calculated on each corresponding point. The proposed method is planning to be included in 3D measurement method with actual images containing still/moving objects and also to be applied to obstacles avoidance for vehicles or vision system for mobile robots.

KW - 3D measurement

KW - 6-axis sensor

KW - Corresponding points classification

KW - Fundamental matrix estimation

KW - Moving camera

UR - http://www.scopus.com/inward/record.url?scp=84964031087&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84964031087

SP - 110

EP - 116

T2 - Joint International Conference of the 10th China-Japan International Workshop on Information Technology and Control Applications and the 6th International Symposium on Computational Intelligence and Industrial Applications, ITCA and ISCIIA 2014

Y2 - 15 September 2014 through 20 September 2014

ER -

Akamatsu T, Dong F, Hirota K. Classification of corresponding points for 3D measurement using moving monocular camera attached with 6-axis sensor. 2014. 论文发表于 Joint International Conference of the 10th China-Japan International Workshop on Information Technology and Control Applications and the 6th International Symposium on Computational Intelligence and Industrial Applications, ITCA and ISCIIA 2014, Changsha, 中国.

Classification of corresponding points for 3D measurement using moving monocular camera attached with 6-axis sensor

摘要

会议

其它文件与链接

指纹

引用此