TY - GEN
T1 - Unsupervised pedestrian sample extraction for model training
AU - Yu, Hao
AU - Maples, Daryl
AU - Liu, Ying
AU - Xu, Zhijie
N1 - Publisher Copyright:
© Copyright 2019 IADIS Press. All rights reserved.
PY - 2019
Y1 - 2019
N2 - Many researches on pedestrian detection use benchmarking datasets such as INRIA for model training. However, models trained with standard video database do not usually obtain satisfying performance in real-life conditions. Hence, supervised training through manually labelled instances is often required to help achieving better detection result. In this research, an innovative unsupervised training approach is proposed. By analyzing the histogram of adjacent pixels modelled from the video sequences, separated pedestrians can be extracted without manual intervention. Experiments have shown consistent performance that is superior over the state-of-the-art methods.
AB - Many researches on pedestrian detection use benchmarking datasets such as INRIA for model training. However, models trained with standard video database do not usually obtain satisfying performance in real-life conditions. Hence, supervised training through manually labelled instances is often required to help achieving better detection result. In this research, an innovative unsupervised training approach is proposed. By analyzing the histogram of adjacent pixels modelled from the video sequences, separated pedestrians can be extracted without manual intervention. Experiments have shown consistent performance that is superior over the state-of-the-art methods.
KW - Crowd Analysis
KW - Pedestrian Detection
KW - Unsupervised Learning
UR - http://www.scopus.com/inward/record.url?scp=85073102143&partnerID=8YFLogxK
U2 - 10.33965/cgv2019_201906l036
DO - 10.33965/cgv2019_201906l036
M3 - Conference Proceeding
AN - SCOPUS:85073102143
T3 - Multi Conference on Computer Science and Information Systems, MCCSIS 2019 - Proceedings of the International Conferences on Interfaces and Human Computer Interaction 2019, Game and Entertainment Technologies 2019 and Computer Graphics, Visualization, Computer Vision and Image Processing 2019
SP - 291
EP - 298
BT - Multi Conference on Computer Science and Information Systems, MCCSIS 2019 - Proceedings of the International Conferences on Interfaces and Human Computer Interaction 2019, Game and Entertainment Technologies 2019 and Computer Graphics, Visualization, Computer Vision and Image Processing 2019
A2 - Blashki, Katherine
A2 - Xiao, Yingcai
A2 - Rodrigues, Luis
PB - IADIS Press
T2 - 13th International Conference on Interfaces and Human Computer Interaction 2019, IHCI 2019, 12th International Conference on Game and Entertainment Technologies 2019, GET 2019 and 13th International Conference on Computer Graphics, Visualization, Computer Vision and Image Processing 2019, CGVCVIP 2019
Y2 - 16 July 2019 through 18 July 2019
ER -