Scribd
Upload
67 views1 page

Real-Time Pedestrian Detection and Tracking at Nighttime For Driver-Assistance Systems

This document proposes a real-time pedestrian detection and tracking system for nighttime driver assistance using a near-infrared camera. It uses a three module cascade approach including region-of-interest generation using dual-threshold segmentation, a two-stage object classification using Haar-like and HOG features, and template matching tracking. Extensive testing on urban and suburban videos showed a detection rate over 90% with about 10 false alarms per hour while running in real-time at 30 frames per second on a Pentium IV computer, demonstrating feasibility for practical applications.

Uploaded by

achuu1987
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
67 views1 page

Real-Time Pedestrian Detection and Tracking at Nighttime For Driver-Assistance Systems

This document proposes a real-time pedestrian detection and tracking system for nighttime driver assistance using a near-infrared camera. It uses a three module cascade approach including region-of-interest generation using dual-threshold segmentation, a two-stage object classification using Haar-like and HOG features, and template matching tracking. Extensive testing on urban and suburban videos showed a detection rate over 90% with about 10 false alarms per hour while running in real-time at 30 frames per second on a Pentium IV computer, demonstrating feasibility for practical applications.

Uploaded by

achuu1987
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
You are on page 1/ 1

REAL-TIME PEDESTRIAN DETECTION AND TRACKING AT NIGHTTIME

FOR DRIVER-ASSISTANCE SYSTEMS


ABSTRACT
Pedestrian detection is one of the most important components in
driver-assistance systems. In this paper, we propose a monocular
vision system for real-time pedestrian detection and tracking during
nighttime driving with a near-infrared (NIR) camera. Three modules
(region-of-interest (ROI) generation, object classification, and
tracking) are integrated in a cascade, and each utilizes complementary
visual features to distinguish the objects from the cluttered
background in the range of 20-80 m. Based on the common fact that
the objects appear brighter than the nearby background in nighttime
NIR images, efficient ROI generation is done based on the dualthreshold segmentation algorithm.
As there is large intraclass variability in the pedestrian class, a
tree-structured, two-stage detector is proposed to tackle the problem
through training separate classifiers on disjoint subsets of different
image sizes and arranging the classifiers based on Haar-like and
histogram-of-oriented-gradients (HOG) features in a coarse-to-fine
manner. To suppress the false alarms and fill the detection gaps,
template-matching-based tracking is adopted, and multiframe
validation is used to obtain the final results. Results from extensive
tests on both urban and suburban videos indicate that the algorithm
can produce a detection rate of more than 90% at the cost of about 10
false alarms/h and perform as fast as the frame rate (30 frames/s) on
a Pentium IV 3.0-GHz personal computer, which also demonstrates
that the proposed system is feasible for practical applications and
enjoys the advantage of low implementation cost

You might also like