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.
Highlights
With the development of intelligent cities, computers are involved in the field of intelligent monitoring and intelligent transportation control to conduct pedestrian detection from a large number of images
Six frequently used features are analyzed in detail, and Histogram of Oriented Gradient (HOG)-Local SelfSimilarity (LSS) would be considered as a new pedestrian detection feature that contains all of the image descriptive operators
We find that the sparse representation method has the ability to perform feature selection, which can remove redundant information and shorten the feature dimension, and a supervised key-feature subset selection method is used to select the most distinctive features from the analyzed features
Summary
With the development of intelligent cities, computers are involved in the field of intelligent monitoring and intelligent transportation control to conduct pedestrian detection from a large number of images. The embedded methods, using classification or regression as an optimization with specified loss and penalty functions [21,22,23], attempt to simultaneously maximize the classification performance and minimize the number of features used [24] These methods are more efficient than wrapper methods because a filter algorithm is built with a classifier to guide the feature selection procedure. Based on the previous studies, we apply sparse theory to pedestrian feature detection and adopt a supervised key-feature subset selection method in our research. SIFT, SURF, Haar, HOG, LBP, and LSS are extracted from a typical image and are analyzed in detail below
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.