A foreground object based quantitative assessment of dense stereo approaches for use in automotive environments

Oliver K. Hamilton, Toby P. Breckon, Xuejiao Bai, Seiichiro Kamata

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

12 Citations (Scopus)

Abstract

There has been significant recent interest in stereo correspondence algorithms for use in the urban automotive environment [1, 2, 3]. In this paper we evaluate a range of dense stereo algorithms, using a unique evaluation criterion which provides quantitative analysis of accuracy against range, based on ground truth 3D annotated object information. The results show that while some algorithms provide greater scene coverage, we see little differentiation in accuracy over short ranges, while the converse is shown over longer ranges. Within our long range accuracy analysis we see a distinct separation of relative algorithm performance. This study extends prior work on dense stereo evaluation of Block Matching (BM)[4], Semi-Global Block Matching (SGBM)[5], No Maximal Disparity (NoMD)[6], Cross[7], Adaptive Dynamic Programming (AdptDP)[8], Efficient Large Scale (ELAS)[9], Minimum Spanning Forest (MSF)[10] and Non-Local Aggregation (NLA)[11] using a novel quantitative metric relative to object range.

Original languageEnglish
Title of host publication2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings
Pages418-422
Number of pages5
DOIs
Publication statusPublished - 2013
Event2013 20th IEEE International Conference on Image Processing, ICIP 2013 - Melbourne, VIC
Duration: 2013 Sep 152013 Sep 18

Other

Other2013 20th IEEE International Conference on Image Processing, ICIP 2013
CityMelbourne, VIC
Period13/9/1513/9/18

Fingerprint

Dynamic programming
Agglomeration
Chemical analysis

Keywords

  • Disparity
  • Quantitative Assessment
  • Registration
  • Stereo Vision

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Hamilton, O. K., Breckon, T. P., Bai, X., & Kamata, S. (2013). A foreground object based quantitative assessment of dense stereo approaches for use in automotive environments. In 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings (pp. 418-422). [6738086] https://doi.org/10.1109/ICIP.2013.6738086

A foreground object based quantitative assessment of dense stereo approaches for use in automotive environments. / Hamilton, Oliver K.; Breckon, Toby P.; Bai, Xuejiao; Kamata, Seiichiro.

2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings. 2013. p. 418-422 6738086.

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

Hamilton, OK, Breckon, TP, Bai, X & Kamata, S 2013, A foreground object based quantitative assessment of dense stereo approaches for use in automotive environments. in 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings., 6738086, pp. 418-422, 2013 20th IEEE International Conference on Image Processing, ICIP 2013, Melbourne, VIC, 13/9/15. https://doi.org/10.1109/ICIP.2013.6738086
Hamilton OK, Breckon TP, Bai X, Kamata S. A foreground object based quantitative assessment of dense stereo approaches for use in automotive environments. In 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings. 2013. p. 418-422. 6738086 https://doi.org/10.1109/ICIP.2013.6738086
Hamilton, Oliver K. ; Breckon, Toby P. ; Bai, Xuejiao ; Kamata, Seiichiro. / A foreground object based quantitative assessment of dense stereo approaches for use in automotive environments. 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings. 2013. pp. 418-422
@inproceedings{e4731d517a0f481b8807189a6a65b9cb,
title = "A foreground object based quantitative assessment of dense stereo approaches for use in automotive environments",
abstract = "There has been significant recent interest in stereo correspondence algorithms for use in the urban automotive environment [1, 2, 3]. In this paper we evaluate a range of dense stereo algorithms, using a unique evaluation criterion which provides quantitative analysis of accuracy against range, based on ground truth 3D annotated object information. The results show that while some algorithms provide greater scene coverage, we see little differentiation in accuracy over short ranges, while the converse is shown over longer ranges. Within our long range accuracy analysis we see a distinct separation of relative algorithm performance. This study extends prior work on dense stereo evaluation of Block Matching (BM)[4], Semi-Global Block Matching (SGBM)[5], No Maximal Disparity (NoMD)[6], Cross[7], Adaptive Dynamic Programming (AdptDP)[8], Efficient Large Scale (ELAS)[9], Minimum Spanning Forest (MSF)[10] and Non-Local Aggregation (NLA)[11] using a novel quantitative metric relative to object range.",
keywords = "Disparity, Quantitative Assessment, Registration, Stereo Vision",
author = "Hamilton, {Oliver K.} and Breckon, {Toby P.} and Xuejiao Bai and Seiichiro Kamata",
year = "2013",
doi = "10.1109/ICIP.2013.6738086",
language = "English",
isbn = "9781479923410",
pages = "418--422",
booktitle = "2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings",

}

TY - GEN

T1 - A foreground object based quantitative assessment of dense stereo approaches for use in automotive environments

AU - Hamilton, Oliver K.

AU - Breckon, Toby P.

AU - Bai, Xuejiao

AU - Kamata, Seiichiro

PY - 2013

Y1 - 2013

N2 - There has been significant recent interest in stereo correspondence algorithms for use in the urban automotive environment [1, 2, 3]. In this paper we evaluate a range of dense stereo algorithms, using a unique evaluation criterion which provides quantitative analysis of accuracy against range, based on ground truth 3D annotated object information. The results show that while some algorithms provide greater scene coverage, we see little differentiation in accuracy over short ranges, while the converse is shown over longer ranges. Within our long range accuracy analysis we see a distinct separation of relative algorithm performance. This study extends prior work on dense stereo evaluation of Block Matching (BM)[4], Semi-Global Block Matching (SGBM)[5], No Maximal Disparity (NoMD)[6], Cross[7], Adaptive Dynamic Programming (AdptDP)[8], Efficient Large Scale (ELAS)[9], Minimum Spanning Forest (MSF)[10] and Non-Local Aggregation (NLA)[11] using a novel quantitative metric relative to object range.

AB - There has been significant recent interest in stereo correspondence algorithms for use in the urban automotive environment [1, 2, 3]. In this paper we evaluate a range of dense stereo algorithms, using a unique evaluation criterion which provides quantitative analysis of accuracy against range, based on ground truth 3D annotated object information. The results show that while some algorithms provide greater scene coverage, we see little differentiation in accuracy over short ranges, while the converse is shown over longer ranges. Within our long range accuracy analysis we see a distinct separation of relative algorithm performance. This study extends prior work on dense stereo evaluation of Block Matching (BM)[4], Semi-Global Block Matching (SGBM)[5], No Maximal Disparity (NoMD)[6], Cross[7], Adaptive Dynamic Programming (AdptDP)[8], Efficient Large Scale (ELAS)[9], Minimum Spanning Forest (MSF)[10] and Non-Local Aggregation (NLA)[11] using a novel quantitative metric relative to object range.

KW - Disparity

KW - Quantitative Assessment

KW - Registration

KW - Stereo Vision

UR - http://www.scopus.com/inward/record.url?scp=84897731453&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897731453&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2013.6738086

DO - 10.1109/ICIP.2013.6738086

M3 - Conference contribution

AN - SCOPUS:84897731453

SN - 9781479923410

SP - 418

EP - 422

BT - 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

ER -