A Novel Fast Pedestrian Detection Method
2015 ◽
Vol 738-739
◽
pp. 538-541
Keyword(s):
This paper presents novel pedestrian detection approach in video streaming, which could process frames rapidly. The method is based on cascades of HOG-LBP (Histograms of Oriented Gradients-Local Binary Pattern), but combines non-negative factorization to reduce the length of the feature, aiming at realizing a more efficient way of detection, remedying the slowness of the original method. Experiments show our method can process faster than HOG and HOG-LBP, and more accurate than HOG, which has better performance in pedestrian detection in video streaming.
2012 ◽
Vol 542-543
◽
pp. 937-940
Keyword(s):
2011 ◽
Vol 317-319
◽
pp. 877-880
2014 ◽
Vol 571-572
◽
pp. 757-763
Keyword(s):
2015 ◽
Vol 2015
◽
pp. 1-11
◽
2021 ◽
Vol 31
(4)
◽
pp. 821-829