by Klette, R, Krüger, N, Vaudrey, T, Pauwels, K, Van Hulle, M, Morales, S, Kandil, FI, Haeusler, R, Pugeault, N, Rabe, C and Lappe, M
Abstract:
This paper discusses options for testing correspondence algorithms in stereo or motion analysis that are designed or considered for vision-based driver assistance. It introduces a globally available database, with a main focus on testing on video sequences of real-world data. We suggest the classification of recorded video data into situations defined by a cooccurrence of some events in recorded traffic scenes. About 100-400 stereo frames (or 4-16 s of recording) are considered a basic sequence, which will be identified with one particular situation. Future testing is expected to be on data that report on hours of driving, and multiple hours of long video data may be segmented into basic sequences and classified into situations. This paper prepares for this expected development. This paper uses three different evaluation approaches (prediction error, synthesized sequences, and labeled sequences) for demonstrating ideas, difficulties, and possible ways in this future field of extensive performance tests in vision-based driver assistance, particularly for cases where the ground truth is not available. This paper shows that the complexity of real-world data does not support the identification of general rankings of correspondence techniques on sets of basic sequences that show different situations. It is suggested that correspondence techniques should adaptively be chosen in real time using some type of statistical situation classifiers. © 2011 IEEE.
Reference:
Performance of correspondence algorithms in vision-based driver assistance using an online image sequence database (Klette, R, Krüger, N, Vaudrey, T, Pauwels, K, Van Hulle, M, Morales, S, Kandil, FI, Haeusler, R, Pugeault, N, Rabe, C and Lappe, M), In IEEE Transactions on Vehicular Technology, volume 60, 2011.
Bibtex Entry:
@article{klette2011performancedatabase,
author = "Klette, R and Krüger, N and Vaudrey, T and Pauwels, K and Van Hulle, M and Morales, S and Kandil, FI and Haeusler, R and Pugeault, N and Rabe, C and Lappe, M",
journal = "IEEE Transactions on Vehicular Technology",
month = "Jun",
pages = "2012--2026",
title = "Performance of correspondence algorithms in vision-based driver assistance using an online image sequence database",
volume = "60",
year = "2011",
abstract = "This paper discusses options for testing correspondence algorithms in stereo or motion analysis that are designed or considered for vision-based driver assistance. It introduces a globally available database, with a main focus on testing on video sequences of real-world data. We suggest the classification of recorded video data into situations defined by a cooccurrence of some events in recorded traffic scenes. About 100-400 stereo frames (or 4-16 s of recording) are considered a basic sequence, which will be identified with one particular situation. Future testing is expected to be on data that report on hours of driving, and multiple hours of long video data may be segmented into basic sequences and classified into situations. This paper prepares for this expected development. This paper uses three different evaluation approaches (prediction error, synthesized sequences, and labeled sequences) for demonstrating ideas, difficulties, and possible ways in this future field of extensive performance tests in vision-based driver assistance, particularly for cases where the ground truth is not available. This paper shows that the complexity of real-world data does not support the identification of general rankings of correspondence techniques on sets of basic sequences that show different situations. It is suggested that correspondence techniques should adaptively be chosen in real time using some type of statistical situation classifiers. © 2011 IEEE.",
doi = "10.1109/TVT.2011.2148134",
issn = "0018-9545",
issue = "5",
keyword = "Basic sequences",
keyword = "ground truth",
keyword = "motion analysis",
keyword = "optical flow",
keyword = "performance evaluation",
keyword = "situations",
keyword = "stereo analysis",
keyword = "video data",
keyword = "vision-based driver assistance",
language = "eng",
}