Welcome to the InfoSci Platform
A New Pedestrian Feature Description Method Named Neighborhood Descriptor of Oriented Gradients

A New Pedestrian Feature Description Method Named Neighborhood Descriptor of Oriented Gradients

Qian Liu, Feng Yang, XiaoFen Tang
Copyright: © 2021 |Volume: 16 |Issue: 1 |Pages: 33
ISSN: 1554-1045|EISSN: 1554-1053|EISBN13: 9781799859741|DOI: 10.4018/IJITWE.2021010102
Cite Article Cite Article

MLA

Liu, Qian, et al. "A New Pedestrian Feature Description Method Named Neighborhood Descriptor of Oriented Gradients." IJITWE vol.16, no.1 2021: pp.23-55. http://doi.org/10.4018/IJITWE.2021010102

APA

Liu, Q., Yang, F., & Tang, X. (2021). A New Pedestrian Feature Description Method Named Neighborhood Descriptor of Oriented Gradients. International Journal of Information Technology and Web Engineering (IJITWE), 16(1), 23-55. http://doi.org/10.4018/IJITWE.2021010102

Chicago

Liu, Qian, Feng Yang, and XiaoFen Tang. "A New Pedestrian Feature Description Method Named Neighborhood Descriptor of Oriented Gradients," International Journal of Information Technology and Web Engineering (IJITWE) 16, no.1: 23-55. http://doi.org/10.4018/IJITWE.2021010102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

In view of the issue of the mechanism for enhancing the neighbourhood relationship of blocks of HOG, this paper proposes neighborhood descriptor of oriented gradients (NDOG), an improved feature descriptor based on HOG, for pedestrian detection. To obtain the NDOG feature vector, the algorithm calculates the local weight vector of the HOG feature descriptor, while integrating spatial correlation among blocks, concatenates this weight vector to the tail of the HOG feature descriptor, and uses the gradient norm to normalize this new feature vector. With the proposed NDOG feature vector along with a linear SVM classifier, this paper develops a complete pedestrian detection approach. Experimental results for the INRIA, Caltech-USA, and ETH pedestrian datasets show that the approach achieves a lower miss rate and a higher average precision compared with HOG and other advanced methods for pedestrian detection especially in the case of insufficient training samples.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.