Pedestrian detection based on hierarchical co-occurrence model for occlusion handling

Neurocomputing 10 (2015)
Download Edit this record How to cite View on PhilPapers
Abstract
In pedestrian detection, occlusions are typically treated as an unstructured source of noise and explicit models have lagged behind those for object appearance, which will result in degradation of detection performance. In this paper, a hierarchical co-occurrence model is proposed to enhance the semantic representation of a pedestrian. In our proposed hierarchical model, a latent SVM structure is employed to model the spatial co-occurrence relations among the parent–child pairs of nodes as hidden variables for handling the partial occlusions. Moreover, the visibility statuses of the pedestrian can be generated by learning co-occurrence relations from the positive training data with large numbers of synthetically occluded instances. Finally, based on the proposed hierarchical co-occurrence model, a pedestrian detection algorithm is implemented to incorporate visibility statuses by means of a Random Forest ensemble. The experimental results on three public datasets demonstrate the log-average miss rate of the proposed algorithm has 5% improvement for pedestrians with partial occlusions compared with the state-of-the-arts.
Categories
(categorize this paper)
PhilPapers/Archive ID
ZHAPDB
Revision history
Archival date: 2015-11-21
View upload history
References found in this work BETA

No references found.

Add more references

Citations of this work BETA
Global Lagrange Stability of Complex-Valued Neural Networks of Neutral Type with Time-Varying Delays.Tu, Zhengwen; Cao, Jinde; Alsaedi, Ahmed; Alsaadi, Fuad E. & Hayat, Tasawar

Add more citations

Added to PP index
2015-06-08

Total views
355 ( #7,558 of 39,000 )

Recent downloads (6 months)
33 ( #13,245 of 39,000 )

How can I increase my downloads?

Monthly downloads since first upload
This graph includes both downloads from PhilArchive and clicks to external links.