TY - GEN
T1 - Accuracy improvement in human detection using HOG features on train-mounted camera
AU - Saika, Shintaro
AU - Takahashi, Saki
AU - Takeuchi, Masara
AU - Katto, Jiro
N1 - Funding Information:
This research is supported by Research and Development on Fundamental and Utilization Technologies for Social Big Data of NICT in Japan, and by Grant-in-Aid for Scientific Research (A) (15H01684) of JSPS in Japanc
Publisher Copyright:
© 2016 IEEE.
PY - 2016/12/27
Y1 - 2016/12/27
N2 - Nowadays, researches on accident prevention using train-mounted cameras had been progressing. Our proposed method considers temporal continuity between frames by using motion vectors in addition to conventional thresholding on similarity values obtained by a human detection method using HOG features. Experiments show the effectiveness of our method as compared with a previous method using only HOG features.
AB - Nowadays, researches on accident prevention using train-mounted cameras had been progressing. Our proposed method considers temporal continuity between frames by using motion vectors in addition to conventional thresholding on similarity values obtained by a human detection method using HOG features. Experiments show the effectiveness of our method as compared with a previous method using only HOG features.
KW - HOG features
KW - Human detection
KW - Optical flow
UR - http://www.scopus.com/inward/record.url?scp=85010332958&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85010332958&partnerID=8YFLogxK
U2 - 10.1109/GCCE.2016.7800373
DO - 10.1109/GCCE.2016.7800373
M3 - Conference contribution
AN - SCOPUS:85010332958
T3 - 2016 IEEE 5th Global Conference on Consumer Electronics, GCCE 2016
BT - 2016 IEEE 5th Global Conference on Consumer Electronics, GCCE 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 5th IEEE Global Conference on Consumer Electronics, GCCE 2016
Y2 - 11 October 2016 through 14 October 2016
ER -