Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)

Pedestrian Recognition based on Human Semantics and PCA-HOG

Authors
Enyuan Yang, Rong Xie
Corresponding Author
Enyuan Yang
Available Online April 2019.
DOI
https://doi.org/10.2991/icmeit-19.2019.120How to use a DOI?
Keywords
Human semantics, PCA-HOG, Feature mosaic, Loss function.
Abstract
In real monitoring scenarios, pedestrian semantics, such as gender and clothing type, is very important for pedestrian retrieval and pedestrian recognition. Traditional pedestrian semantics attribute recognition algorithm adopts manual feature extraction and cannot express the association between pedestrian semantics features. This paper proposes a pedestrian semantics recognition method based on improved AlexNet convolution neural network to obtain pedestrian semantics features. Vector. At the same time, a large number of experiments show that HOG descriptors have a good effect in pedestrian recognition, but the number is too large. In this paper, PCA-HOG descriptors are used to express pedestrians and obtain low-dimensional PCA-HOG eigenvectors. Finally, PCA-HOG feature vectors and pedestrian semantic feature vectors are joined together, and LR model is used to predict pedestrian recognition. Compared with traditional methods, the algorithm is simpler, more practical and has higher recognition accuracy.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Proceedings
Part of series
Advances in Computer Science Research
Publication Date
April 2019
ISBN
978-94-6252-708-9
ISSN
2352-538X
DOI
https://doi.org/10.2991/icmeit-19.2019.120How to use a DOI?
Open Access
This is an open access article distributed under the CC BY-NC license.

Cite this article

TY  - CONF
AU  - Enyuan Yang
AU  - Rong Xie
PY  - 2019/04
DA  - 2019/04
TI  - Pedestrian Recognition based on Human Semantics and PCA-HOG
PB  - Atlantis Press
SP  - 754
EP  - 759
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmeit-19.2019.120
DO  - https://doi.org/10.2991/icmeit-19.2019.120
ID  - Yang2019/04
ER  -