Pedestrian/Vehicle Detection Using a 2.5-D Multi-Layer Laser Scanner

Beomseong Kim, Baehoon Choi, Seongkeun Park, Hyunju Kim, Euntai Kim

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Laser scanners are widely used as the primary sensor for autonomous driving. When the commercialization of autonomous driving is considered, a 2.5-D multi-layer laser scanner is one of the best sensor options. In this paper, a new method is presented to detect pedestrians and vehicles using a 2.5-D multi-layer laser scanner. The proposed method consists of three steps: 1) segmentation; 2) feature extraction; and 3) classification; this paper focuses on the last two steps. In feature extraction, new features for the multi-layer laser scanner are proposed to improve the classification performance. In classification, radial basis function additive kernel support vector machine is employed to reduce the computation time while maintaining the performance. The proposed method is implemented on a real vehicle, and its performance is tested in a real-world environment. The experiments indicate that the proposed method has good performance in many real-life situations.

Original languageEnglish
Article number7286756
Pages (from-to)400-408
Number of pages9
JournalIEEE Sensors Journal
Volume16
Issue number2
DOIs
Publication statusPublished - 2016 Jan 15

Fingerprint

scanners
vehicles
Lasers
pattern recognition
lasers
Feature extraction
commercialization
sensors
Sensors
Support vector machines
Experiments

All Science Journal Classification (ASJC) codes

  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

Kim, Beomseong ; Choi, Baehoon ; Park, Seongkeun ; Kim, Hyunju ; Kim, Euntai. / Pedestrian/Vehicle Detection Using a 2.5-D Multi-Layer Laser Scanner. In: IEEE Sensors Journal. 2016 ; Vol. 16, No. 2. pp. 400-408.
@article{f0c92eadac864bc18d6867ec13cfce08,
title = "Pedestrian/Vehicle Detection Using a 2.5-D Multi-Layer Laser Scanner",
abstract = "Laser scanners are widely used as the primary sensor for autonomous driving. When the commercialization of autonomous driving is considered, a 2.5-D multi-layer laser scanner is one of the best sensor options. In this paper, a new method is presented to detect pedestrians and vehicles using a 2.5-D multi-layer laser scanner. The proposed method consists of three steps: 1) segmentation; 2) feature extraction; and 3) classification; this paper focuses on the last two steps. In feature extraction, new features for the multi-layer laser scanner are proposed to improve the classification performance. In classification, radial basis function additive kernel support vector machine is employed to reduce the computation time while maintaining the performance. The proposed method is implemented on a real vehicle, and its performance is tested in a real-world environment. The experiments indicate that the proposed method has good performance in many real-life situations.",
author = "Beomseong Kim and Baehoon Choi and Seongkeun Park and Hyunju Kim and Euntai Kim",
year = "2016",
month = "1",
day = "15",
doi = "10.1109/JSEN.2015.2480742",
language = "English",
volume = "16",
pages = "400--408",
journal = "IEEE Sensors Journal",
issn = "1530-437X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

Pedestrian/Vehicle Detection Using a 2.5-D Multi-Layer Laser Scanner. / Kim, Beomseong; Choi, Baehoon; Park, Seongkeun; Kim, Hyunju; Kim, Euntai.

In: IEEE Sensors Journal, Vol. 16, No. 2, 7286756, 15.01.2016, p. 400-408.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Pedestrian/Vehicle Detection Using a 2.5-D Multi-Layer Laser Scanner

AU - Kim, Beomseong

AU - Choi, Baehoon

AU - Park, Seongkeun

AU - Kim, Hyunju

AU - Kim, Euntai

PY - 2016/1/15

Y1 - 2016/1/15

N2 - Laser scanners are widely used as the primary sensor for autonomous driving. When the commercialization of autonomous driving is considered, a 2.5-D multi-layer laser scanner is one of the best sensor options. In this paper, a new method is presented to detect pedestrians and vehicles using a 2.5-D multi-layer laser scanner. The proposed method consists of three steps: 1) segmentation; 2) feature extraction; and 3) classification; this paper focuses on the last two steps. In feature extraction, new features for the multi-layer laser scanner are proposed to improve the classification performance. In classification, radial basis function additive kernel support vector machine is employed to reduce the computation time while maintaining the performance. The proposed method is implemented on a real vehicle, and its performance is tested in a real-world environment. The experiments indicate that the proposed method has good performance in many real-life situations.

AB - Laser scanners are widely used as the primary sensor for autonomous driving. When the commercialization of autonomous driving is considered, a 2.5-D multi-layer laser scanner is one of the best sensor options. In this paper, a new method is presented to detect pedestrians and vehicles using a 2.5-D multi-layer laser scanner. The proposed method consists of three steps: 1) segmentation; 2) feature extraction; and 3) classification; this paper focuses on the last two steps. In feature extraction, new features for the multi-layer laser scanner are proposed to improve the classification performance. In classification, radial basis function additive kernel support vector machine is employed to reduce the computation time while maintaining the performance. The proposed method is implemented on a real vehicle, and its performance is tested in a real-world environment. The experiments indicate that the proposed method has good performance in many real-life situations.

UR - http://www.scopus.com/inward/record.url?scp=84961707453&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961707453&partnerID=8YFLogxK

U2 - 10.1109/JSEN.2015.2480742

DO - 10.1109/JSEN.2015.2480742

M3 - Article

AN - SCOPUS:84961707453

VL - 16

SP - 400

EP - 408

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

SN - 1530-437X

IS - 2

M1 - 7286756

ER -