Limits...
Feature Selection and Pedestrian Detection Based on Sparse Representation.

Yao S, Wang T, Shen W, Pan S, Chong Y, Ding F - PLoS ONE (2015)

Bottom Line: Sparse subsets of the fusion features can be rapidly generated by avoiding calculation of the corresponding index of dimension numbers of these feature descriptors; thus, the calculation speed of the feature dimension reduction is improved and the pedestrian detection time is reduced.Experimental results show that sparse feature subsets are capable of keeping the important components of these six feature descriptors.The ratios of the sparse feature subsets of HOG and LSS to their full sets are the highest among the six, and thus these two features can be used to best describe the characteristics of the pedestrian and the sparse feature subsets of the combination of HOG-LSS show better distinguishing ability and parsimony.

View Article: PubMed Central - PubMed

Affiliation: State Key Laboratory for Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China.

ABSTRACT
Pedestrian detection have been currently devoted to the extraction of effective pedestrian features, which has become one of the obstacles in pedestrian detection application according to the variety of pedestrian features and their large dimension. Based on the theoretical analysis of six frequently-used features, SIFT, SURF, Haar, HOG, LBP and LSS, and their comparison with experimental results, this paper screens out the sparse feature subsets via sparse representation to investigate whether the sparse subsets have the same description abilities and the most stable features. When any two of the six features are fused, the fusion feature is sparsely represented to obtain its important components. Sparse subsets of the fusion features can be rapidly generated by avoiding calculation of the corresponding index of dimension numbers of these feature descriptors; thus, the calculation speed of the feature dimension reduction is improved and the pedestrian detection time is reduced. Experimental results show that sparse feature subsets are capable of keeping the important components of these six feature descriptors. The sparse features of HOG and LSS possess the same description ability and consume less time compared with their full features. The ratios of the sparse feature subsets of HOG and LSS to their full sets are the highest among the six, and thus these two features can be used to best describe the characteristics of the pedestrian and the sparse feature subsets of the combination of HOG-LSS show better distinguishing ability and parsimony.

No MeSH data available.


Related in: MedlinePlus

(a) The detection time of the sparse feature subsets and the full features on the INRIA dataset. (b) The detection time of the sparse feature subsets and full features on the Daimler dataset.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4546602&req=5

pone.0134242.g005: (a) The detection time of the sparse feature subsets and the full features on the INRIA dataset. (b) The detection time of the sparse feature subsets and full features on the Daimler dataset.

Mentions: Pedestrian detection is under constant pressure to increase both its quality and speed. Such progress allows for new applications. A higher speed enables its inclusion into larger systems that can perform extensive subsequent processing. The detection time is a critical indicator for pedestrian detection. Fig 5 shows the detection time of the sparse feature subsets and the full features with different classifiers on the two datasets. When Adaboost is taken as the classifier, the detection time for the full features is approximately 10~15 times greater than that of the sparse feature subsets. When SVM is used as the classifier, the detection time of the full features is approximately 4~20 times greater than that of the sparse feature subsets. Regardless of which classifier is used, the detection time of the sparse feature subsets is far less than that of the full features.


Feature Selection and Pedestrian Detection Based on Sparse Representation.

Yao S, Wang T, Shen W, Pan S, Chong Y, Ding F - PLoS ONE (2015)

(a) The detection time of the sparse feature subsets and the full features on the INRIA dataset. (b) The detection time of the sparse feature subsets and full features on the Daimler dataset.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4546602&req=5

pone.0134242.g005: (a) The detection time of the sparse feature subsets and the full features on the INRIA dataset. (b) The detection time of the sparse feature subsets and full features on the Daimler dataset.
Mentions: Pedestrian detection is under constant pressure to increase both its quality and speed. Such progress allows for new applications. A higher speed enables its inclusion into larger systems that can perform extensive subsequent processing. The detection time is a critical indicator for pedestrian detection. Fig 5 shows the detection time of the sparse feature subsets and the full features with different classifiers on the two datasets. When Adaboost is taken as the classifier, the detection time for the full features is approximately 10~15 times greater than that of the sparse feature subsets. When SVM is used as the classifier, the detection time of the full features is approximately 4~20 times greater than that of the sparse feature subsets. Regardless of which classifier is used, the detection time of the sparse feature subsets is far less than that of the full features.

Bottom Line: Sparse subsets of the fusion features can be rapidly generated by avoiding calculation of the corresponding index of dimension numbers of these feature descriptors; thus, the calculation speed of the feature dimension reduction is improved and the pedestrian detection time is reduced.Experimental results show that sparse feature subsets are capable of keeping the important components of these six feature descriptors.The ratios of the sparse feature subsets of HOG and LSS to their full sets are the highest among the six, and thus these two features can be used to best describe the characteristics of the pedestrian and the sparse feature subsets of the combination of HOG-LSS show better distinguishing ability and parsimony.

View Article: PubMed Central - PubMed

Affiliation: State Key Laboratory for Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China.

ABSTRACT
Pedestrian detection have been currently devoted to the extraction of effective pedestrian features, which has become one of the obstacles in pedestrian detection application according to the variety of pedestrian features and their large dimension. Based on the theoretical analysis of six frequently-used features, SIFT, SURF, Haar, HOG, LBP and LSS, and their comparison with experimental results, this paper screens out the sparse feature subsets via sparse representation to investigate whether the sparse subsets have the same description abilities and the most stable features. When any two of the six features are fused, the fusion feature is sparsely represented to obtain its important components. Sparse subsets of the fusion features can be rapidly generated by avoiding calculation of the corresponding index of dimension numbers of these feature descriptors; thus, the calculation speed of the feature dimension reduction is improved and the pedestrian detection time is reduced. Experimental results show that sparse feature subsets are capable of keeping the important components of these six feature descriptors. The sparse features of HOG and LSS possess the same description ability and consume less time compared with their full features. The ratios of the sparse feature subsets of HOG and LSS to their full sets are the highest among the six, and thus these two features can be used to best describe the characteristics of the pedestrian and the sparse feature subsets of the combination of HOG-LSS show better distinguishing ability and parsimony.

No MeSH data available.


Related in: MedlinePlus