Street object classification via LIDARs with only a single or a few layers

Zoltan Rozsa, T. Szirányi

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

Abstract

LIDAR sensors are part of the sensor system of several intelligent vehicles and transportation systems providing both object and free-space detection capabilities. In this paper a recognition method is proposed for LIDARs with only a few detection planes. Our method is especially useful in the case when angular resolution of the scan is sufficient, but in the vertical direction the planes are far from each other. The proposed method uses new features including Fourier based descriptor, deep learning classification and exploits additional 3D information if it is available. We tested the method on ten thousands of samples from a large public database. This paper gives an effective solution for a hard problem of LIDAR based recognition problems, namely the far-object detection in case of mobile LIDARs of limited or poor vertical resolution.

Original languageEnglish
Title of host publicationIEEE 3rd International Conference on Image Processing, Applications and Systems, IPAS 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages156-161
Number of pages6
ISBN (Electronic)9781728102474
DOIs
Publication statusPublished - May 6 2019
Event3rd IEEE International Conference on Image Processing, Applications and Systems, IPAS 2018 - Sophia Antipolis, France
Duration: Dec 12 2018Dec 14 2018

Publication series

NameIEEE 3rd International Conference on Image Processing, Applications and Systems, IPAS 2018

Conference

Conference3rd IEEE International Conference on Image Processing, Applications and Systems, IPAS 2018
CountryFrance
CitySophia Antipolis
Period12/12/1812/14/18

Fingerprint

Intelligent vehicle highway systems
Sensors
Object detection
Deep learning

Keywords

  • Intelligent vehicles
  • LIDAR
  • recognition

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Computer Graphics and Computer-Aided Design

Cite this

Rozsa, Z., & Szirányi, T. (2019). Street object classification via LIDARs with only a single or a few layers. In IEEE 3rd International Conference on Image Processing, Applications and Systems, IPAS 2018 (pp. 156-161). [8708881] (IEEE 3rd International Conference on Image Processing, Applications and Systems, IPAS 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IPAS.2018.8708881

Street object classification via LIDARs with only a single or a few layers. / Rozsa, Zoltan; Szirányi, T.

IEEE 3rd International Conference on Image Processing, Applications and Systems, IPAS 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 156-161 8708881 (IEEE 3rd International Conference on Image Processing, Applications and Systems, IPAS 2018).

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

Rozsa, Z & Szirányi, T 2019, Street object classification via LIDARs with only a single or a few layers. in IEEE 3rd International Conference on Image Processing, Applications and Systems, IPAS 2018., 8708881, IEEE 3rd International Conference on Image Processing, Applications and Systems, IPAS 2018, Institute of Electrical and Electronics Engineers Inc., pp. 156-161, 3rd IEEE International Conference on Image Processing, Applications and Systems, IPAS 2018, Sophia Antipolis, France, 12/12/18. https://doi.org/10.1109/IPAS.2018.8708881
Rozsa Z, Szirányi T. Street object classification via LIDARs with only a single or a few layers. In IEEE 3rd International Conference on Image Processing, Applications and Systems, IPAS 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 156-161. 8708881. (IEEE 3rd International Conference on Image Processing, Applications and Systems, IPAS 2018). https://doi.org/10.1109/IPAS.2018.8708881
Rozsa, Zoltan ; Szirányi, T. / Street object classification via LIDARs with only a single or a few layers. IEEE 3rd International Conference on Image Processing, Applications and Systems, IPAS 2018. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 156-161 (IEEE 3rd International Conference on Image Processing, Applications and Systems, IPAS 2018).
@inproceedings{2d1f6389239b4fa8a842276297e37f96,
title = "Street object classification via LIDARs with only a single or a few layers",
abstract = "LIDAR sensors are part of the sensor system of several intelligent vehicles and transportation systems providing both object and free-space detection capabilities. In this paper a recognition method is proposed for LIDARs with only a few detection planes. Our method is especially useful in the case when angular resolution of the scan is sufficient, but in the vertical direction the planes are far from each other. The proposed method uses new features including Fourier based descriptor, deep learning classification and exploits additional 3D information if it is available. We tested the method on ten thousands of samples from a large public database. This paper gives an effective solution for a hard problem of LIDAR based recognition problems, namely the far-object detection in case of mobile LIDARs of limited or poor vertical resolution.",
keywords = "Intelligent vehicles, LIDAR, recognition",
author = "Zoltan Rozsa and T. Szir{\'a}nyi",
year = "2019",
month = "5",
day = "6",
doi = "10.1109/IPAS.2018.8708881",
language = "English",
series = "IEEE 3rd International Conference on Image Processing, Applications and Systems, IPAS 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "156--161",
booktitle = "IEEE 3rd International Conference on Image Processing, Applications and Systems, IPAS 2018",

}

TY - GEN

T1 - Street object classification via LIDARs with only a single or a few layers

AU - Rozsa, Zoltan

AU - Szirányi, T.

PY - 2019/5/6

Y1 - 2019/5/6

N2 - LIDAR sensors are part of the sensor system of several intelligent vehicles and transportation systems providing both object and free-space detection capabilities. In this paper a recognition method is proposed for LIDARs with only a few detection planes. Our method is especially useful in the case when angular resolution of the scan is sufficient, but in the vertical direction the planes are far from each other. The proposed method uses new features including Fourier based descriptor, deep learning classification and exploits additional 3D information if it is available. We tested the method on ten thousands of samples from a large public database. This paper gives an effective solution for a hard problem of LIDAR based recognition problems, namely the far-object detection in case of mobile LIDARs of limited or poor vertical resolution.

AB - LIDAR sensors are part of the sensor system of several intelligent vehicles and transportation systems providing both object and free-space detection capabilities. In this paper a recognition method is proposed for LIDARs with only a few detection planes. Our method is especially useful in the case when angular resolution of the scan is sufficient, but in the vertical direction the planes are far from each other. The proposed method uses new features including Fourier based descriptor, deep learning classification and exploits additional 3D information if it is available. We tested the method on ten thousands of samples from a large public database. This paper gives an effective solution for a hard problem of LIDAR based recognition problems, namely the far-object detection in case of mobile LIDARs of limited or poor vertical resolution.

KW - Intelligent vehicles

KW - LIDAR

KW - recognition

UR - http://www.scopus.com/inward/record.url?scp=85066331443&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066331443&partnerID=8YFLogxK

U2 - 10.1109/IPAS.2018.8708881

DO - 10.1109/IPAS.2018.8708881

M3 - Conference contribution

T3 - IEEE 3rd International Conference on Image Processing, Applications and Systems, IPAS 2018

SP - 156

EP - 161

BT - IEEE 3rd International Conference on Image Processing, Applications and Systems, IPAS 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -