|
Title:
|
UNSUPERVISED PEDESTRIAN SAMPLE EXTRACTION
FOR MODEL TRAINING |
|
Author(s):
|
Hao Yu, Daryl Maples, Ying Liu and Zhijie Xu |
|
ISBN:
|
978-989-8533-91-3 |
|
Editors:
|
Katherine Blashki and Yingcai Xiao |
|
Year:
|
2019 |
|
Edition:
|
Single |
|
Keywords:
|
Pedestrian Detection, Crowd Analysis, Unsupervised Learning |
|
Type:
|
Full Paper |
|
First Page:
|
291 |
|
Last Page:
|
298 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
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. |
|
|
|
|
|
|
