Pedestrian detection in the embedded system, such as video surveillance equipment, usually involves low-resolution pedestrian samples and requires a low computational cost. Many pedestrian detectors rely on a large feature pool and suffer in their efficiency and performance for real-time monitoring. In this paper, a set of light-weight features is proposed to enhance the pedestrian detection performance when a small-medium scale of training data with low-resolution images is available. To address this issue, a difference matrix projection (DMP) is developed to compute aggregated multi-oriented pixel differences using global matrix operations. Both the pixel differences and aggregation are computed using global matrix projection to avoid the laborious iterative operations. We tested our method on the INRIA, Daimler Chrysler classification (Daimler-CB), NICTA, and Caltech Pedestrian datasets. The experiments on these benchmark data sets show encouraging results in terms of detection performance, particularly for image datasets with low-resolution pedestrians.
Pedestrian Detection Using Pixel Difference Matrix Projection
IEEE Transactions on Intelligent Transportation Systems ; 21 , 4 ; 1441-1454
01.04.2020
3410665 byte
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Pedestrian forward projection impact
Kraftfahrwesen | 2002
|Vehicle-pedestrian collisions: Validated models for pedestrian impact and projection
SAGE Publications | 2005
|Vehicle-pedestrian collisions: validated models for pedestrian impact and projection
Online Contents | 2005
|Vehicle-pedestrian collisions: validated models for pedestrian impact and projection
Kraftfahrwesen | 2005
|