Performance of Correspondence Algorithms in Vision-Based Driver Assistance Using an Online Image Sequence Database
Performance of Correspondence Algorithms in Vision-Based Driver Assistance Using an Online Image Sequence Database
复制标题
DOI：
10.1109/tvt.2011.2148134
复制
发表时间：
2011-05
影响因子：
6.8
通讯作者：
R. Klette;N. Krüger;Tobi Vaudrey;Karl Pauwels;M. V. Hulle;Sandino Morales;F. I. Kandil;R. Haeusler;N. Pugeault;C. Rabe;M. Lappe
中科院分区：
文献类型：
--
作者：
R. Klette;N. Krüger;Tobi Vaudrey;Karl Pauwels;M. V. Hulle;Sandino Morales;F. I. Kandil;R. Haeusler;N. Pugeault;C. Rabe;M. Lappe
本文讨论了在立体或运动分析中测试对应算法的选项，这些算法是为基于视觉的驾驶员辅助而设计或考虑的。它引入了一个全球可用的数据库，主要侧重于测试真实世界数据的视频序列。我们建议将录制的视频数据分类为由录制的交通场景中同时发生的某些事件定义的情况。大约 100-400 个立体声帧（或 4-16 秒的录制）被视为一个基本序列，将根据一种特定情况进行识别。未来的测试预计将针对报告驾驶时间的数据，多个小时的长视频数据可能会被分割成基本序列并按情况分类。本文是为这一预期的发展做准备的。本文使用三种不同的评估方法（预测误差、合成序列和标记序列）来展示基于视觉的驾驶员辅助的广泛性能测试的未来领域的想法、困难和可能的方法，特别是在地面事实不可用的情况下。本文表明，现实世界数据的复杂性不支持在显示不同情况的基本序列集上识别对应技术的一般排名。建议使用某种类型的统计情况分类器实时自适应地选择对应技术。
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.