Comparative Study of Various Feature Extraction Techniques for Pedestrian Detection

This paper presents, feature extraction techniques such as center symmetric local binary pattern (CSLBP), extended CSLBP (XCSLBP), speeded-up robust feature (SURF) with 64 and 128 feature descriptors and histograms of oriented gradients (HOG) applied on a set of images from INRIA person database, to detect pedestrians. About fifteen feature sets created using different combinations of the aforementioned methods are compared using two detectors, random forest (RF) and support vector machine (SVM). Performance validation is done based on the accuracy, precision, recall and space required for storing feature vectors. Experimental results have shown that CSLBP and the novel XCSLBP+CSLBP feature sets yield 100% accuracy, when used with RF classifier, whereas, the novel SURF-128+XCSLBP combination and SVM linear classifier gave 99.2% accuracy in detecting pedestrians.

Language

  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01722317
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Jul 19 2019 3:14PM