Multimodel approach for pedestrian detection

Junhyuk Hyun, Jeonghyun Baek, Jisu Kim, Peyman Hosseinzajeh Kassani, Euntai Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Good performance of pedestrian detection in an automatic driving system is a necessary task. Many pedestrian detection algorithm use Histogram Oriented Gradient (HOG) for feature extraction and Support Vector Machine (SVM) for classification. Some papers use additional features with HOG, such as Local Binary Pattern (HOG-LBP), to improve the performance. Neural Network and Extreme Learning Machine (ELM) are also used for classification like SVM, but SVM always finds global optimum for classification. This paper adds algorithm to this HOG, SVM system for improving the detection performance. This paper proposes a new method which uses pose of pedestrian. The proposed model outperforms conventional method in SDL dataset.

Original languageEnglish
Title of host publicationiFUZZY 2014 - 2014 International Conference on Fuzzy Theory and Its Applications, Conference Digest
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages199-202
Number of pages4
ISBN (Electronic)9781479945887
DOIs
Publication statusPublished - 2014 Apr 21
Event2014 International Conference on Fuzzy Theory and Its Applications, iFUZZY 2014 - Kaohsiung, Taiwan, Province of China
Duration: 2014 Nov 262014 Nov 28

Publication series

NameiFUZZY 2014 - 2014 International Conference on Fuzzy Theory and Its Applications, Conference Digest

Other

Other2014 International Conference on Fuzzy Theory and Its Applications, iFUZZY 2014
CountryTaiwan, Province of China
CityKaohsiung
Period14/11/2614/11/28

All Science Journal Classification (ASJC) codes

  • Control and Optimization
  • Logic
  • Computational Theory and Mathematics
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Multimodel approach for pedestrian detection'. Together they form a unique fingerprint.

Cite this