Specific patches decorrelation channel feature on pedestrian detection
Joint Authors
Source
The International Arab Journal of Information Technology
Issue
Vol. 18, Issue 4 (31 Jul. 2021), pp.493-503, 11 p.
Publisher
Zarqa University Deanship of Scientific Research
Publication Date
2021-07-31
Country of Publication
Jordan
No. of Pages
11
Main Subjects
Information Technology and Computer Science
Abstract EN
Typical Local Decorrelation Channel Feature (LDCF) for pedestrian detection generates filters derived from decorrelation for each entire positive sample, using Principle Component Analysis (PCA) method.
Meanwhile, extensive pedestrian detection methods, which utilize statistic human shape to guide filters design, point out that the head-shoulder area is the most discriminative patches in typical classification stage.
Inspired by above mentioned local decorrelation operation and discriminative areas that most classifiers indicate, in this paper we propose to integrate human shape priority into image patch decorrelation to generate novel filters.
To be specific, we extract covariance from salient patches that contain discriminative features, instead of each entire positive sample.
Furthermore, we also propose to share covariance matrix within grouping channels.
Our method is efficient as it avoids extracting uninformative filters from redundant covariance of convergent patches, due to embedded prior human shape info.
Experiments on INRIA and Caltech-USA public pedestrian dataset has been done to demonstrate effectiveness of our proposed methods.
The result shows that our proposed method could decrease log-average miss rate with detection speed retained compared to LDCF and most non-deep methods.
American Psychological Association (APA)
Ding, Xueming& Ji, Dongfei. 2021. Specific patches decorrelation channel feature on pedestrian detection. The International Arab Journal of Information Technology،Vol. 18, no. 4, pp.493-503.
https://search.emarefa.net/detail/BIM-1434245
Modern Language Association (MLA)
Ding, Xueming& Ji, Dongfei. Specific patches decorrelation channel feature on pedestrian detection. The International Arab Journal of Information Technology Vol. 18, no. 4 (Jul. 2021), pp.493-503.
https://search.emarefa.net/detail/BIM-1434245
American Medical Association (AMA)
Ding, Xueming& Ji, Dongfei. Specific patches decorrelation channel feature on pedestrian detection. The International Arab Journal of Information Technology. 2021. Vol. 18, no. 4, pp.493-503.
https://search.emarefa.net/detail/BIM-1434245
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references : p. 502
Record ID
BIM-1434245