Method of predetermined road object recognition in images and vehicle driving assistance device
作者： Siav Kuong Kuoch , Julien Rebut
DOI:
关键词: Histogram of oriented gradients 、 Engineering 、 Artificial intelligence 、 Computer vision 、 Classifier (UML) 、 Pixel 、 Cognitive neuroscience of visual object recognition 、 Vehicle driving
摘要: The invention relates to a method of predetermined road object recognition in images, including : - first stage detection (101), detect object-like regions done by sliding search window through an image and checking whether region is classified as said or non-predetermined object, second validation (102), classify into objects non- objects, characterized that descriptors computed inside from extracting features based on histogram oriented gradients (HOG), Fourier-Mellin transformation (FMT) the pixels, supplies both classifier objects. also vehicle driving assistance device implement recognition.
lens.org 参考文章(4)
Roberto Brunelli, Template Matching Techniques in Computer Vision: Theory and Practice ,(2009)
S Hakuli, H Winner, G Wolf, Handbuch Fahrerassistenzsysteme. Grundlagen, Komponenten und Systeme fuer aktive Sicherheit und Komfort ,(2009)
Haiqiang Zuo, Xi Li, Ou Wu, Weiming Hu, Guan Luo, Image spam filtering using Fourier-Mellin invariant features international conference on acoustics, speech, and signal processing. pp. 849- 852 ,(2009) , 10.1109/ICASSP.2009.4959717
Philip Geismann, Georg Schneider, A two-staged approach to vision-based pedestrian recognition using Haar and HOG features ieee intelligent vehicles symposium. pp. 554- 559 ,(2008) , 10.1109/IVS.2008.4621148