Real-time pedestrian detection with deformable part models

Hyunggi Cho, Paul E. Rybski, Aharon Bar-Hillel, Wende Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

59 Scopus citations


We describe a real-time pedestrian detection system intended for use in automotive applications. Our system demonstrates superior detection performance when compared to many state-of-the-art detectors and is able to run at a speed of 14 fps on an Intel Core i7 computer when applied to 640x480 images. Our approach uses an analysis of geometric constraints to efficiently search feature pyramids and increases detection accuracy by using a multiresolution representation of a pedestrian model to detect small pixel-sized pedestrians normally missed by a single representation approach. We have evaluated our system on the Caltech Pedestrian benchmark which is currently the largest publicly available pedestrian dataset at the time of this publication. Our system shows a detection rate of 61% with 1 false positive per image (FPPI) whereas recent other state-of-the-art detectors show a detection rate of 50% ∼ 61% under the 'reasonable' test scenario (explained later). Furthermore, we also demonstrate the practicality of our system by conducting a series of use case experiments on selected videos of Caltech dataset.

Original languageEnglish
Title of host publication2012 IEEE Intelligent Vehicles Symposium, IV 2012
Number of pages8
StatePublished - 20 Aug 2012
Externally publishedYes
Event2012 IEEE Intelligent Vehicles Symposium, IV 2012 - Alcal de Henares, Madrid, Spain
Duration: 3 Jun 20127 Jun 2012

Publication series

NameIEEE Intelligent Vehicles Symposium, Proceedings


Conference2012 IEEE Intelligent Vehicles Symposium, IV 2012
CityAlcal de Henares, Madrid

ASJC Scopus subject areas

  • Modeling and Simulation
  • Automotive Engineering
  • Computer Science Applications


Dive into the research topics of 'Real-time pedestrian detection with deformable part models'. Together they form a unique fingerprint.

Cite this